CN118508440B - Power distribution terminal self-adaptive adjustment method and system based on multi-source data - Google Patents
Power distribution terminal self-adaptive adjustment method and system based on multi-source data Download PDFInfo
- Publication number
- CN118508440B CN118508440B CN202410962003.7A CN202410962003A CN118508440B CN 118508440 B CN118508440 B CN 118508440B CN 202410962003 A CN202410962003 A CN 202410962003A CN 118508440 B CN118508440 B CN 118508440B
- Authority
- CN
- China
- Prior art keywords
- factor
- power distribution
- adjustment
- energy
- distribution network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims abstract description 55
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000007405 data analysis Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 10
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a power distribution terminal self-adaptive adjustment method and a system based on multi-source data, which relate to the technical field of intelligent power grids and comprise the following steps: receiving first switching frequency distribution information, fitting through a power distribution network state prediction network, and generating a power distribution network prediction state matrix; carrying out multi-source data analysis through a power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor; receiving a network loss expected factor, a load distribution expected factor and an energy expected factor in unit time length; carrying out adjustment probability analysis according to the power distribution network loss factor, the load distribution factor, the energy factor in unit time length and the corresponding expected factors, and generating adjustment convergence probability; and when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold value, carrying out self-adaptive adjustment on the power distribution terminal. The invention solves the technical problem that the prior art lacks of real-time power distribution adjustment according to the user's expectations, and achieves the technical effect of self-adaptive power distribution adjustment according to the user's expectations.
Description
Technical Field
The invention relates to the technical field of intelligent power grids, in particular to a power distribution terminal self-adaptive adjustment method and system based on multi-source data.
Background
With the continuous development of the power industry and the wide application of smart grid technology, the requirements of users on the operation efficiency and the safety of a power distribution system are increasingly improved. The traditional power distribution terminal control method is mainly based on preset fixed parameters or a simple feedback mechanism, lacks the capability of real-time adjustment according to the user's expectations, and is difficult to meet the high-efficiency, intelligent and personalized operation requirements of the modern power network.
Disclosure of Invention
The application provides a power distribution terminal self-adaptive adjustment method and system based on multi-source data, which are used for solving the technical problem that the prior art lacks real-time power distribution adjustment according to user expectations.
In view of the above problems, the application provides a power distribution terminal self-adaptive adjustment method and system based on multi-source data.
In a first aspect of the present application, there is provided a method for adaptively adjusting a power distribution terminal based on multi-source data, the method comprising:
Receiving first switching frequency distribution information, fitting through a power distribution network state prediction network, and generating a power distribution network prediction state matrix; carrying out multi-source data analysis through the power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor; receiving a network loss expected factor, a load distribution expected factor and an energy expected factor in unit time length through a user side; according to the power distribution network loss factor, the load distribution factor and the energy factor in unit time length, combining the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length to carry out adjustment probability analysis, and generating adjustment convergence probability; and when the adjustment convergence probability is greater than or equal to an adjustment convergence probability threshold value, carrying out self-adaptive adjustment on the power distribution terminal according to the first switching frequency distribution information.
In a second aspect of the present application, there is provided a multi-source data based power distribution terminal adaptive regulation system, the system comprising:
The power distribution network prediction state matrix generation module receives the first switching frequency distribution information, and fits through a power distribution network prediction network to generate a power distribution network prediction state matrix; the multi-source data analysis module is used for carrying out multi-source data analysis through the power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor; the expected factor receiving module receives the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length through a user side; the adjustment probability analysis module is used for carrying out adjustment probability analysis according to the power distribution network loss factor, the load distribution factor and the unit duration energy factor and combining the network loss expected factor, the load distribution expected factor and the unit duration energy expected factor to generate adjustment convergence probability; and the power distribution terminal self-adaptive adjusting module is used for carrying out power distribution terminal self-adaptive adjustment according to the first switching frequency distribution information when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold value.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method comprises the steps of receiving first switching frequency distribution information, fitting through a power distribution network state prediction network, and generating a power distribution network prediction state matrix; carrying out multi-source data analysis through a power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor; receiving a network loss expected factor, a load distribution expected factor and an energy expected factor in unit time length through a user side; according to the power distribution network loss factors, the load distribution factors and the energy factors in unit time length, carrying out adjustment probability analysis by combining the network loss expected factors, the load distribution expected factors and the energy expected factors in unit time length, and generating adjustment convergence probability; and when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold, carrying out self-adaptive adjustment on the power distribution terminal according to the first switching frequency distribution information. The application solves the technical problem that the prior art lacks of real-time power distribution adjustment according to the user's expectations, and achieves the technical effect of self-adaptive power distribution adjustment according to the user's expectations by analyzing the running state of the power grid in real time and combining with the user's expectations, automatically adjusting the control parameters and strategies of the power distribution terminal.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for adaptively adjusting a power distribution terminal based on multi-source data according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of a power distribution terminal adaptive adjustment system based on multi-source data according to an embodiment of the present application.
Reference numerals illustrate: the power distribution network prediction state matrix generation module 11, the multi-source data analysis module 12, the expected factor receiving module 13, the adjustment probability analysis module 14 and the power distribution terminal self-adaptation adjustment module 15.
Detailed Description
The application aims at solving the technical problem that the prior art lacks of real-time power distribution adjustment according to user expectations by providing the power distribution terminal self-adaptive adjustment method and system based on multi-source data, and achieves the technical effect of self-adaptive power distribution adjustment according to the user expectations by analyzing the running state of a power grid in real time and combining with the user expectations to automatically adjust the control parameters and strategies of the power distribution terminal.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a method for adaptively adjusting a power distribution terminal based on multi-source data, the method comprising:
step S100: and receiving the first switching frequency distribution information, and fitting through a power distribution network state prediction network to generate a power distribution network prediction state matrix.
In the embodiment of the application, the operation frequency data of each switch is collected in real time through the sensor and the monitoring system in the power distribution network, the collected original data is subjected to cleaning, denoising and standardization, and the preprocessed data is used as first switch frequency distribution information to be input into a power distribution network state prediction network for fitting.
And obtaining a predicted state matrix of the power distribution network through fitting, wherein the predicted state matrix of the power distribution network comprises predicted state information, such as voltage, current, power and the like, of each key node in the power distribution network.
Step S200: and carrying out multi-source data analysis through the power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor.
In the embodiment of the application, data related to power grid loss is extracted from a power distribution network prediction state matrix. The line losses of the distribution network are then estimated by means of a special network loss calculation software or algorithm, such as the root mean square current method. And comparing the loss calculation result with the total transmission electric quantity of the power grid, and calculating the loss factor of the power distribution network.
Load data of each node are extracted from the power distribution network prediction state matrix. And carrying out statistics and analysis on the load data of each node by using a data analysis tool to obtain the distribution condition of the load in the power grid. And calculating a load distribution factor by comparing the proportion of the load of each node to the total load of the power grid.
And extracting real-time power data of the power grid from the predicted state matrix of the power distribution network. The total energy per unit time is obtained by integrating the real-time power data or other suitable calculation method. The energy factor of the unit time length is obtained by comparing the ratio of the total energy in the unit time to the theoretical maximum energy.
Step S300: and receiving the network loss expected factor, the load distribution expected factor and the energy expected factor of unit time length through the user side.
In the embodiment of the application, the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length uploaded by the user are received through the user side.
The network loss expected factor is a quantitative index of a user on the expected loss degree of the power grid in the process of transmitting electric energy. It reflects a user's desire for grid efficiency, i.e. the power grid is delivering power, where the user wishes that the loss of power be controlled within an acceptable range. The lower the value of the grid loss expectancy factor, the higher the expectancy of the user for the transmission efficiency of the power grid.
The load distribution desirability factor is a quantitative indicator of the user's desirability of the degree of load distribution balancing in the grid. In the power grid, if the load can be evenly distributed, the operation of the power grid is more stable, and the service life of the equipment is correspondingly prolonged.
The energy per unit time period desirability factor is a quantitative indicator of the desire of the user to power the grid for a unit time. This factor reflects the customer's demand for grid power stability and supply capacity.
Step S400: and according to the power distribution network loss factor, the load distribution factor and the energy factor in unit time length, combining the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length to carry out adjustment probability analysis, and generating adjustment convergence probability.
In the embodiment of the application, the loss factor, the load distribution factor and the energy factor in unit time length of the power distribution network are compared with the corresponding expected factors, the sizes of the actual factors and the expected factors are judged, and the actual factors and the expected factors are substituted into the corresponding adjustment probability analysis functions according to the size relation among the factors. And obtaining the adjustment convergence probability through calculation of the adjustment probability analysis function.
Step S500: and when the adjustment convergence probability is greater than or equal to an adjustment convergence probability threshold value, carrying out self-adaptive adjustment on the power distribution terminal according to the first switching frequency distribution information.
In the embodiment of the application, the calculated adjustment convergence probability is compared with the preset adjustment convergence probability threshold, and when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold, the performance and the stability of the power grid are at an acceptable and reliable level. Wherein the convergence probability threshold is preset by a technical expert based on industry specifications when being adjusted.
At this time, the power distribution terminal is adaptively adjusted according to the first switching frequency distribution information, that is, the power distribution terminal is controlled according to the operating frequency in the first switching frequency distribution information.
Further, the power distribution network state prediction network construction step includes:
Carrying out graph neural network simulation according to the power distribution network topology, and constructing a graph neural network topology, wherein the graph neural network topology is identical to the power distribution network topology;
the graph neural network topology is provided with a plurality of switch distribution nodes, and input nodes of the graph neural network topology are built for the switch distribution nodes;
Based on the power distribution network topology, collecting switching frequency distribution record information and power distribution network preset state record information of a plurality of switching distribution nodes;
and taking the preset state record information of the power distribution network as output supervision of the graph neural network topology, and taking the switching frequency distribution record information as input to perform model parameter configuration of the graph neural network topology, so as to generate the power distribution network state prediction network.
In the embodiment of the application, a power distribution network topological structure is acquired by using power distribution network management software. The topology structure of the power distribution network comprises a plurality of types such as tree, ring, net and the like, and meanwhile, the topology structure has connection relations of various components in the power distribution network, such as switch distribution nodes, transformers, lines and the like.
Based on the topological structure of the power distribution network, constructing a graph neural network topology identical to the graph neural network topology. In particular, the components in each distribution network, such as the switch distribution nodes, are corresponding to one node in the graph neural network, and the connection relationship between the components is represented by the edges of the graph neural network. In the graph neural network topology, each switch distribution node corresponds to an input node in the graph neural network.
And (3) monitoring and recording the switching frequency distribution record information of each switching distribution node in real time by using a sensor arranged in the power distribution network. And meanwhile, collecting preset state record information of the power distribution network, wherein the preset state record information of the power distribution network comprises current record information, voltage record information, power record information, load rated capacity record information and the like. And cleaning, denoising and standardizing the collected data, ensuring the accuracy and consistency of the data, and improving the training effect of the graph neural network.
And taking the preprocessed switching frequency distribution record information as input of the graphic neural network, and taking preset state data of the power distribution network as target output. And by utilizing the optimization technologies of a back propagation algorithm, gradient descent and the like, the weights and bias parameters of the graph neural network are continuously adjusted through repeated iterative training, so that the output of the network is as close to the preset state data as possible.
The model was evaluated after training was completed to verify its performance. And verifying and testing the model by using online real-time data, and calculating indexes such as accuracy, recall rate and the like of the model to evaluate the performance of the model. And when the model performance meets the requirement, generating a power distribution network state prediction network.
Further, step S200 in the method provided in the application embodiment further includes:
Extracting a feeder line segment state set according to the predicted state matrix of the power distribution network to perform network loss analysis, and generating the power distribution network loss factor;
according to the predicted state matrix of the power distribution network, a branch load state set is extracted to carry out load distribution analysis, and the load distribution factor is generated;
And extracting output power state, current state information and voltage state information according to the predicted state matrix of the power distribution network, and generating the energy factor of unit duration.
In an embodiment of the application, a feeder segment state set is extracted from a predicted state matrix of the distribution network, the feeder segment state set including a current, a voltage drop, a power factor, etc. of the feeder segment. These status information reflect the operational condition of the feeder segment at a particular point in time. And then calculating the electric energy loss of the feeder line segment by using the data in the feeder line segment state set through a network loss analysis algorithm such as a root mean square current method. And according to the result of the network loss analysis, calculating the loss factor of the power distribution network by combining the total transmission electric quantity of the feeder section.
Load state information of each branch is extracted from the power distribution network prediction state matrix, wherein the load state information comprises load size and load type. And (3) carrying out spatial analysis on the extracted load state information by combining with a geographic information system technology, and determining the distribution condition of the load in the power distribution network. And carrying out quantitative evaluation on the load distribution condition by a quantitative evaluation method, such as a load balance index, and generating a load distribution factor.
And integrating real-time state information of output power, current and voltage from the predicted state matrix of the power distribution network. The actual energy per unit time is calculated by an integration algorithm or other mathematical method using the data of the output power, current and voltage. And calculating the energy factor of the unit duration by comparing the proportion of the actual energy to the theoretical maximum energy of the power distribution network.
Further, according to the predicted state matrix of the power distribution network, extracting a feeder line segment state set for network loss analysis, and generating the power distribution network loss factor, the method further comprises:
The feeder line segment state set comprises an ith feeder line segment resistor, an ith feeder line segment active power, an ith feeder line segment reactive power and an ith feeder line segment end node voltage, i is an integer, i epsilon [1, N ], N represents the total number of feeder line segments, and an i initial value is equal to 1;
Calculating a square sum characteristic value of the i-th feeder line segment active power and the i-th feeder line segment reactive power, and calculating a square characteristic value of the i-th feeder line segment end node voltage;
calculating the ratio of the square sum characteristic value to the square characteristic value, setting the ratio as a first net loss factor, and carrying out product operation on the first net loss factor and the ith feeder line segment resistance to generate an ith feeder line segment net loss factor;
And when i is larger than N, adding the first feeder section loss factors until the Nth feeder section loss factors, and generating the distribution network loss factors.
In an embodiment of the application, the feeder segment state set includes state sets from 1 st to nth feeder segments, where N characterizes the total number of feeder segments.
And extracting relevant state information of all feeder segments from the feeder segment state set, namely extracting all feeder segment resistances, active power, reactive power and terminal node voltages.
For each feeder section, the square of the real power and the square of the reactive power in that feeder section are added to obtain a sum of squares eigenvalues. And simultaneously square the voltage in the feeder section to obtain a square eigenvalue.
And then, calculating the ratio of the square sum characteristic value to the square characteristic value, and taking the calculated numerical value as a first network loss factor. And performing product operation on the first network loss factor and the feeder section resistance to obtain the feeder section network loss factor.
And repeating the calculation process to obtain the network loss factors of the 1 st to N th feeder sections, and finally adding the network loss factors to generate the power distribution network loss factors.
Further, according to the predicted state matrix of the power distribution network, a branch load state set is extracted to perform load distribution analysis, and the load distribution factor is generated, and the method comprises the following steps:
The user side of the power distribution network is interacted to obtain a k branch load characteristic value, wherein k is an integer, k is E [1, M ], M represents the number of branches, and the initial value of k is equal to 1;
the branch load state set comprises a kth branch load rated capacity;
Calculating the ratio of the load characteristic value of the kth branch to the rated capacity of the load of the kth branch to generate a load distribution characteristic factor of the kth branch;
And when k is more than M, solving variances of the load distribution characteristic factors of the first branch and the second branch until the load distribution characteristic factor of the Mth branch to generate the load distribution factor.
In the embodiment of the application, interaction is carried out with a user side of the power distribution network, a k branch load characteristic value is obtained through a smart electric meter, a sensor or other measuring equipment, k is an integer, k epsilon [1, M ], M represents the number of branches, and the initial value of k is equal to 1. I.e. all branch load characteristic values can be obtained by interaction with the user side of the distribution network.
And for the kth branch, extracting the load rated capacity of the kth branch from the predicted state matrix of the power distribution network. And then calculating the ratio of the load characteristic value of the kth branch to the load rated capacity to obtain the load distribution characteristic factor of the kth branch.
Through the process, the load distribution characteristic factors of the branches from 1to M are calculated, and variance calculation is carried out on the M calculated load distribution characteristic factors to obtain the load distribution factors.
Further, according to the predicted state matrix of the power distribution network, extracting output power state, current state information and voltage state information, and generating the energy factor of unit duration, the method further comprises:
The user side of the power distribution network is interacted to obtain energy of unit duration required by the j user side, wherein j is an integer, j is E [1, Q ], Q represents the number of access users, and the initial value of j is equal to 1;
Performing energy supply analysis according to the output power state, the current state information and the voltage state information to generate energy of a j-th user prediction unit duration;
Calculating a j-th deviation square characteristic value of the j-th user side demand unit duration energy and the j-th user prediction unit duration energy;
when j is more than Q, calculating the difference between the maximum value and the minimum value of the first deviation square characteristic value and the second deviation square characteristic value until the Q-th deviation square characteristic value, and setting the difference as the energy factor of the first unit duration;
Calculating the sum and the evolution results from the first deviation square characteristic value to the second deviation square characteristic value to the Q-th deviation square characteristic value, and setting the sum and the evolution results as a second unit duration energy factor;
And adding the first unit time length energy factor and the second unit time length energy factor into the unit time length energy factor.
In the embodiment of the present application, the energy of the unit time length required by the jth user side is obtained in the same way as the above method, and the unit is set by itself, such as one day, one hour, etc. Wherein j is an integer, j is [1, Q ], Q represents the number of access users, and the initial value of j is equal to 1.
The predicted output power state data is used to convert it into energy. If the output power is given in units of power, such as kilowatts, the energy is calculated by multiplying the power by the unit duration. Since there is already a predicted output power for a unit time period, e.g. an hour, a day, etc., the predicted energy for the unit time period is obtained directly by multiplying the time period. The energy of the unit duration predicted by the jth user is obtained through the process.
And comparing the energy of the unit time length of the j-th user with the energy of the predicted unit time length, calculating the deviation of the energy of the unit time length of the j-th user and the energy of the predicted unit time length, and squaring the deviation to obtain a j-th deviation square characteristic value. The above steps are repeated to calculate square-of-deviation eigenvalues for Q users.
After all user data are processed, the maximum value and the minimum value in all deviation square characteristic values are found, the difference between the maximum value and the minimum value is calculated, and the difference is set as a first unit duration energy factor. And adding and squaring the deviation square characteristic values of all users, and setting the calculation result as a second unit duration energy factor.
And finally, adding the first unit-time-length energy factor and the second unit-time-length energy factor into a set of the unit-time-length energy factors.
Further, step S400 in the method provided in the application embodiment further includes:
Constructing a first-order analysis function of the adjustment probability:
wherein, Characterizing the expected factors of network loss,The load profile expected factor is characterized by,Characterizing the energy expectancy factor per unit of time,Representing the loss factor of the distribution network,Characterizing load distribution factorsThe energy factor per unit time length is characterized,、AndCharacterizing the weight parameters, and minf characterizing the analysis parameters;
constructing a regulating probability secondary analysis function:
wherein, The adjustment convergence probability is characterized, and e is a constant.
In the embodiment of the application, the network loss expected factors, the load distribution expected factors and the energy expected factors in unit time length are compared with the corresponding power distribution network loss factors, load distribution factors and energy factors in unit time length, and the factors are substituted into corresponding formulas in the first-level analysis function of the adjustment probability according to the magnitude relation to calculate, and the calculated analysis parameters are used. In adjusting the probability primary analysis function,、AndThe value of (2) is preset by a technical expert.
Substituting the calculated analysis parameters into a second-stage analysis function of the adjustment probability, and obtaining the adjustment convergence probability through calculation.
Further, the method further comprises:
when the adjustment convergence probability is smaller than an adjustment convergence probability threshold value, the first switching frequency distribution information is adjusted to generate second switching frequency distribution information;
performing adjustment convergence probability analysis according to the second switching frequency distribution information, and performing self-adaptive adjustment of the power distribution terminal according to the second switching frequency distribution information if the adjustment convergence probability threshold is met;
If not, the method is circularly regulated.
In the embodiment of the application, when the adjustment convergence probability is smaller than the adjustment convergence probability threshold, the first switching frequency distribution information is adjusted, and the adjustment comprises changing the operation timing of a specific switch, increasing or decreasing the switching times, and the like. The adjustment is gradual, changing only a small fraction of the parameters at a time to avoid instability of the system.
And acquiring second switching frequency distribution information through adjustment. And carrying out adjustment convergence probability analysis according to the second switching frequency distribution information, and carrying out self-adaptive adjustment of the power distribution terminal according to the second switching frequency distribution information when the adjustment convergence probability of the second switching frequency distribution information is larger than an adjustment convergence probability threshold value. And if the switching frequency distribution information does not meet the adjustment convergence probability threshold, repeating the adjustment process until the switching frequency distribution information meeting the adjustment convergence probability threshold is found out to adjust the power distribution terminal.
In summary, the embodiment of the present application has at least the following technical effects:
The method comprises the steps of receiving first switching frequency distribution information, fitting through a power distribution network state prediction network, and generating a power distribution network prediction state matrix; carrying out multi-source data analysis through a power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor; receiving a network loss expected factor, a load distribution expected factor and an energy expected factor in unit time length through a user side; according to the power distribution network loss factors, the load distribution factors and the energy factors in unit time length, carrying out adjustment probability analysis by combining the network loss expected factors, the load distribution expected factors and the energy expected factors in unit time length, and generating adjustment convergence probability; and when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold, carrying out self-adaptive adjustment on the power distribution terminal according to the first switching frequency distribution information. The application solves the technical problem that the prior art lacks of real-time power distribution adjustment according to the user's expectations, and achieves the technical effect of self-adaptive power distribution adjustment according to the user's expectations by analyzing the running state of the power grid in real time and combining with the user's expectations, automatically adjusting the control parameters and strategies of the power distribution terminal.
Example two
Based on the same inventive concept as the power distribution terminal adaptive adjustment method based on multi-source data in the foregoing embodiment, as shown in fig. 2, the present application provides a power distribution terminal adaptive adjustment system based on multi-source data, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
The power distribution network prediction state matrix generation module 11 receives the first switching frequency distribution information, and fits through a power distribution network prediction network to generate a power distribution network prediction state matrix;
The multi-source data analysis module 12 performs multi-source data analysis through the power distribution network prediction state matrix by the multi-source data analysis module 12 to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor;
The expected factor receiving module 13, wherein the expected factor receiving module 13 receives the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length through a user side;
The adjustment probability analysis module 14, wherein the adjustment probability analysis module 14 performs adjustment probability analysis according to the power distribution network loss factor, the load distribution factor and the unit duration energy factor by combining the network loss expected factor, the load distribution expected factor and the unit duration energy expected factor to generate adjustment convergence probability;
And the power distribution terminal self-adaptive adjusting module 15 is used for carrying out power distribution terminal self-adaptive adjustment according to the first switching frequency distribution information when the adjustment convergence probability is greater than or equal to the adjustment convergence probability threshold value by the power distribution terminal self-adaptive adjusting module 15.
Further, the system is further configured to implement the following functions:
Carrying out graph neural network simulation according to the power distribution network topology, and constructing a graph neural network topology, wherein the graph neural network topology is identical to the power distribution network topology;
the graph neural network topology is provided with a plurality of switch distribution nodes, and input nodes of the graph neural network topology are built for the switch distribution nodes;
Based on the power distribution network topology, collecting switching frequency distribution record information and power distribution network preset state record information of a plurality of switching distribution nodes;
and taking the preset state record information of the power distribution network as output supervision of the graph neural network topology, and taking the switching frequency distribution record information as input to perform model parameter configuration of the graph neural network topology, so as to generate the power distribution network state prediction network.
Further, the system is further configured to implement the following functions:
Extracting a feeder line segment state set according to the predicted state matrix of the power distribution network to perform network loss analysis, and generating the power distribution network loss factor;
according to the predicted state matrix of the power distribution network, a branch load state set is extracted to carry out load distribution analysis, and the load distribution factor is generated;
And extracting output power state, current state information and voltage state information according to the predicted state matrix of the power distribution network, and generating the energy factor of unit duration.
Further, the system is further configured to implement the following functions:
The feeder line segment state set comprises an ith feeder line segment resistor, an ith feeder line segment active power, an ith feeder line segment reactive power and an ith feeder line segment end node voltage, i is an integer, i epsilon [1, N ], N represents the total number of feeder line segments, and an i initial value is equal to 1;
Calculating a square sum characteristic value of the i-th feeder line segment active power and the i-th feeder line segment reactive power, and calculating a square characteristic value of the i-th feeder line segment end node voltage;
calculating the ratio of the square sum characteristic value to the square characteristic value, setting the ratio as a first net loss factor, and carrying out product operation on the first net loss factor and the ith feeder line segment resistance to generate an ith feeder line segment net loss factor;
And when i is larger than N, adding the first feeder section loss factors until the Nth feeder section loss factors, and generating the distribution network loss factors.
Further, the system is further configured to implement the following functions:
The user side of the power distribution network is interacted to obtain a k branch load characteristic value, wherein k is an integer, k is E [1, M ], M represents the number of branches, and the initial value of k is equal to 1;
the branch load state set comprises a kth branch load rated capacity;
Calculating the ratio of the load characteristic value of the kth branch to the rated capacity of the load of the kth branch to generate a load distribution characteristic factor of the kth branch;
And when k is more than M, solving variances of the load distribution characteristic factors of the first branch and the second branch until the load distribution characteristic factor of the Mth branch to generate the load distribution factor.
Further, the system is further configured to implement the following functions:
The user side of the power distribution network is interacted to obtain energy of unit duration required by the j user side, wherein j is an integer, j is E [1, Q ], Q represents the number of access users, and the initial value of j is equal to 1;
Performing energy supply analysis according to the output power state, the current state information and the voltage state information to generate energy of a j-th user prediction unit duration;
Calculating a j-th deviation square characteristic value of the j-th user side demand unit duration energy and the j-th user prediction unit duration energy;
when j is more than Q, calculating the difference between the maximum value and the minimum value of the first deviation square characteristic value and the second deviation square characteristic value until the Q-th deviation square characteristic value, and setting the difference as the energy factor of the first unit duration;
Calculating the sum and the evolution results from the first deviation square characteristic value to the second deviation square characteristic value to the Q-th deviation square characteristic value, and setting the sum and the evolution results as a second unit duration energy factor;
And adding the first unit time length energy factor and the second unit time length energy factor into the unit time length energy factor.
Further, the system is further configured to implement the following functions:
Constructing a first-order analysis function of the adjustment probability:
wherein, Characterizing the expected factors of network loss,The load profile expected factor is characterized by,Characterizing the energy expectancy factor per unit of time,Representing the loss factor of the distribution network,Characterizing load distribution factorsThe energy factor per unit time length is characterized,、AndCharacterizing the weight parameters, and minf characterizing the analysis parameters;
constructing a regulating probability secondary analysis function:
wherein, The adjustment convergence probability is characterized, and e is a constant.
Further, the system is further configured to implement the following functions:
when the adjustment convergence probability is smaller than an adjustment convergence probability threshold value, the first switching frequency distribution information is adjusted to generate second switching frequency distribution information;
performing adjustment convergence probability analysis according to the second switching frequency distribution information, and performing self-adaptive adjustment of the power distribution terminal according to the second switching frequency distribution information if the adjustment convergence probability threshold is met;
If not, the method is circularly regulated.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, nor the sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The power distribution terminal self-adaptive adjustment method based on the multi-source data is characterized by comprising the following steps of:
Receiving first switching frequency distribution information, fitting through a power distribution network state prediction network, and generating a power distribution network prediction state matrix;
carrying out multi-source data analysis through the power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor;
Receiving a network loss expected factor, a load distribution expected factor and an energy expected factor in unit time length through a user side;
According to the power distribution network loss factor, the load distribution factor and the energy factor in unit time length, combining the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length to carry out adjustment probability analysis, and generating adjustment convergence probability;
when the adjustment convergence probability is greater than or equal to an adjustment convergence probability threshold value, carrying out self-adaptive adjustment on the power distribution terminal according to the first switching frequency distribution information;
according to the power distribution network loss factor, the load distribution factor and the energy factor in unit time length, the adjustment probability analysis is performed by combining the power distribution loss expected factor, the load distribution expected factor and the energy factor in unit time length, and the adjustment convergence probability generation method comprises the following steps:
Constructing a first-order analysis function of the adjustment probability:
；
wherein, Characterizing the expected factors of network loss,The load profile expected factor is characterized by,Characterizing the energy expectancy factor per unit of time,Representing the loss factor of the distribution network,Characterizing load distribution factorsThe energy factor per unit time length is characterized,、AndCharacterizing the weight parameters, and minf characterizing the analysis parameters;
constructing a regulating probability secondary analysis function:
；
wherein, The probability of convergence is characterized by the adjustment,Is constant.
2. The method of claim 1, wherein the power distribution network state prediction network construction step comprises:
Carrying out graph neural network simulation according to the power distribution network topology, and constructing a graph neural network topology, wherein the graph neural network topology is identical to the power distribution network topology;
the graph neural network topology is provided with a plurality of switch distribution nodes, and input nodes of the graph neural network topology are built for the switch distribution nodes;
Based on the power distribution network topology, collecting switching frequency distribution record information and power distribution network preset state record information of a plurality of switching distribution nodes;
and taking the preset state record information of the power distribution network as output supervision of the graph neural network topology, and taking the switching frequency distribution record information as input to perform model parameter configuration of the graph neural network topology, so as to generate the power distribution network state prediction network.
3. The method of claim 1, wherein generating the power distribution network loss factor, the load distribution factor, and the energy per unit time period factor by multi-source data analysis of the power distribution network prediction state matrix comprises:
Extracting a feeder line segment state set according to the predicted state matrix of the power distribution network to perform network loss analysis, and generating the power distribution network loss factor;
according to the predicted state matrix of the power distribution network, a branch load state set is extracted to carry out load distribution analysis, and the load distribution factor is generated;
And extracting output power state, current state information and voltage state information according to the predicted state matrix of the power distribution network, and generating the energy factor of unit duration.
4. The method of claim 3, wherein extracting a feeder segment state set for grid loss analysis based on the distribution network prediction state matrix to generate the distribution network loss factor comprises:
The feeder segment state set includes a first Feeder line segment resistance, the firstFeed line section active power, firstReactive power sum of feeder line segmentThe voltage at the end node of the feeder segment,Is an integer of the number of the times,，The total number of feeder segments is characterized,The initial value is equal to 1;
Calculate the first Feed line section active power and the firstCalculating the square sum characteristic value of the reactive power of the feeder sectionSquare eigenvalue of feeder line segment end node voltage;
the ratio of the square sum characteristic value to the square characteristic value is obtained and is set as a first network loss factor, and the first network loss factor are calculated The feedback line segment resistance performs product operation to generate the firstA feeder segment loss factor;
When (when) When the first feeder segment loss factor is added up to the firstAnd generating the power distribution network loss factor by using the feeder section loss factor.
5. A method according to claim 3, wherein extracting a set of branch load states for load distribution analysis based on the predicted state matrix of the distribution network, generating the load distribution factor, comprises:
the user side of the interactive power distribution network obtains the first A branch load characteristic value, wherein,Is an integer of the number of the times,，The number of branches is characterized in that,The initial value is equal to 1;
the branch load status set includes Rated capacity of branch load;
solving for the first Branch load characteristic value and the firstThe ratio of rated capacity of the branch load is generated to generate the firstBranch load distribution characteristic factors;
When (when) At the moment, the first branch load distribution characteristic factor and the second branch load distribution characteristic factor are subjected to the process ofAnd solving variances of the branch load distribution characteristic factors, and generating the load distribution factors.
6. The method of claim 3, wherein extracting output power state, current state information, and voltage state information from the distribution network prediction state matrix to generate the energy factor per unit time length comprises:
the user side of the interactive power distribution network obtains the first The user side requires energy per unit time, wherein,Is an integer of the number of the times,，The number of access users is characterized and,The initial value is equal to 1;
performing energy supply analysis according to the output power state, the current state information and the voltage state information to generate a first power supply The user predicts the energy in unit time length;
Calculate the first The user demands energy per unit time and the firstUser prediction of the first energy per unit of timeSquare of deviation eigenvalue;
When (when) Calculating the first deviation square characteristic value and the second deviation square characteristic value until the first deviation square characteristic valueThe difference between the maximum value and the minimum value of the square characteristic value of the deviation is set as an energy factor of the first unit duration;
Calculating the first deviation square eigenvalue and the second deviation square eigenvalue until the first deviation square eigenvalue The sum and the evolution result of the square characteristic value of the deviation are set as energy factors of the second unit duration;
And adding the first unit time length energy factor and the second unit time length energy factor into the unit time length energy factor.
7. The method as recited in claim 1, further comprising:
when the adjustment convergence probability is smaller than an adjustment convergence probability threshold value, the first switching frequency distribution information is adjusted to generate second switching frequency distribution information;
performing adjustment convergence probability analysis according to the second switching frequency distribution information, and performing self-adaptive adjustment of the power distribution terminal according to the second switching frequency distribution information if the adjustment convergence probability threshold is met;
If not, the method is circularly regulated.
8. A multi-source data based power distribution terminal adaptive regulation system, the system comprising:
the power distribution network prediction state matrix generation module receives the first switching frequency distribution information, and fits through a power distribution network prediction network to generate a power distribution network prediction state matrix;
the multi-source data analysis module is used for carrying out multi-source data analysis through the power distribution network prediction state matrix to generate a power distribution network loss factor, a load distribution factor and a unit duration energy factor;
The expected factor receiving module receives the network loss expected factor, the load distribution expected factor and the energy expected factor in unit time length through a user side;
The adjustment probability analysis module is used for carrying out adjustment probability analysis according to the power distribution network loss factor, the load distribution factor and the unit duration energy factor and combining the network loss expected factor, the load distribution expected factor and the unit duration energy expected factor to generate adjustment convergence probability;
The power distribution terminal self-adaptive adjusting module is used for carrying out power distribution terminal self-adaptive adjustment according to the first switching frequency distribution information when the adjustment convergence probability is greater than or equal to an adjustment convergence probability threshold value;
Wherein, the adjustment probability analysis module is further used for realizing the following functions:
Constructing a first-order analysis function of the adjustment probability:
；
wherein, Characterizing the expected factors of network loss,The load profile expected factor is characterized by,Characterizing the energy expectancy factor per unit of time,Representing the loss factor of the distribution network,Characterizing load distribution factorsThe energy factor per unit time length is characterized,、AndCharacterizing the weight parameters, and minf characterizing the analysis parameters;
constructing a regulating probability secondary analysis function:
；
wherein, The probability of convergence is characterized by the adjustment,Is constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410962003.7A CN118508440B (en) | 2024-07-18 | 2024-07-18 | Power distribution terminal self-adaptive adjustment method and system based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410962003.7A CN118508440B (en) | 2024-07-18 | 2024-07-18 | Power distribution terminal self-adaptive adjustment method and system based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118508440A CN118508440A (en) | 2024-08-16 |
| CN118508440B true CN118508440B (en) | 2024-09-27 |
Family
ID=92247516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410962003.7A Active CN118508440B (en) | 2024-07-18 | 2024-07-18 | Power distribution terminal self-adaptive adjustment method and system based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118508440B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111293685A (en) * | 2020-02-28 | 2020-06-16 | 华北电力大学 | System partition inertia evaluation method based on coherent recognition |
| CN111416539A (en) * | 2020-04-24 | 2020-07-14 | 山东大学 | Model prediction control method and system for three-level grid-connected converter |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009048964A1 (en) * | 2007-10-09 | 2009-04-16 | Schweitzer Engineering Laboratories, Inc. | Real-time power system oscillation detection using modal analysis |
| DE102013012898A1 (en) * | 2013-08-05 | 2015-02-05 | ef.ruhr GmbH | System and method for controlling the frequency and / or voltage maintenance from the distribution network |
| CN117937497B (en) * | 2024-03-13 | 2025-02-11 | 国网江苏省电力有限公司南通供电分公司 | Computing power load balancing method and device |
-
2024
- 2024-07-18 CN CN202410962003.7A patent/CN118508440B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111293685A (en) * | 2020-02-28 | 2020-06-16 | 华北电力大学 | System partition inertia evaluation method based on coherent recognition |
| CN111416539A (en) * | 2020-04-24 | 2020-07-14 | 山东大学 | Model prediction control method and system for three-level grid-connected converter |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118508440A (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110048420B (en) | Method, device and medium for random optimal scheduling of power distribution network | |
| CN110222897A (en) | A kind of distribution network reliability analysis method | |
| CN112329997A (en) | Power demand load prediction method and system, electronic device, and storage medium | |
| CN119171437B (en) | Intelligent power supply planning method based on medium-voltage distribution network | |
| CN110991519A (en) | Intelligent switch state analysis and adjustment method and system | |
| CN109378834A (en) | Large-scale grid voltage stability margin evaluation system based on maximum information correlation | |
| CN119813239B (en) | Charging pile dynamic power allocation method and device based on load prediction | |
| CN119787342B (en) | A multi-objective optimization scheduling method and system for power grid post-disaster recovery | |
| CN119275881B (en) | A distribution network mobile energy storage scheduling method, device and storage medium based on rolling forward warning | |
| CN118508440B (en) | Power distribution terminal self-adaptive adjustment method and system based on multi-source data | |
| CN115207921A (en) | Position optimization method and system for photovoltaic access power distribution network | |
| CN113283205B (en) | Opportunity constraint-based distribution transformer maximum operation life estimation method and device | |
| CN116777264B (en) | Method and system for determining distribution network resilience index considering energy storage | |
| CN116154791B (en) | Power angle stable control method, system and terminal for cooperative multiple controllable resources | |
| CN114465245B (en) | Parameter matching method and system for power grid regulation device | |
| Miroshnyk et al. | Reducing the dissymmetry of load currents in electrical networks 0, 4/0, 23 kV using artificial neural networks | |
| CN115347556A (en) | A capacity allocation method for energy storage power stations to promote new energy consumption | |
| Yasuoka et al. | Artificial neural network-based distribution substation and feeder load forecast | |
| CN120090211B (en) | Distribution network digital simulation decision analysis method and system based on artificial intelligence | |
| CN118646004B (en) | Low-internal-resistance lead-type supercapacitor system of intelligent ammeter and application method thereof | |
| CN118780618B (en) | A line loss early warning method for low voltage active network considering theoretical limit and fluctuation amplitude | |
| CN118822279B (en) | Distribution network operation risk assessment methods, devices, media, equipment and products | |
| CN120320478B (en) | Voltage-regulating power supply control method and system of multifunctional power supply | |
| CN119419715B (en) | Precise power control method for DC microgrid | |
| CN118713126A (en) | A method, device, equipment and storage medium for adjusting three-phase imbalance in a transformer area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |