CN120746319A - A method and system for intelligent pipeline laying and base station site selection based on deep learning - Google Patents
A method and system for intelligent pipeline laying and base station site selection based on deep learningInfo
- Publication number
- CN120746319A CN120746319A CN202510810742.9A CN202510810742A CN120746319A CN 120746319 A CN120746319 A CN 120746319A CN 202510810742 A CN202510810742 A CN 202510810742A CN 120746319 A CN120746319 A CN 120746319A
- Authority
- CN
- China
- Prior art keywords
- base station
- area
- service
- cost
- pipeline
- 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.)
- Pending
Links
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
本发明涉及基站选址领域，具体为一种基于深度学习的智能管线敷设与基站选址方法及系统，包括：GIS建设模块、干线规划模块、基站选址模块、支线覆盖模块和二次扩容模块，GIS建设模块用于构建GIS数字模型，生成敷设成本和用户热力图，干线规划模块用于规划服务干线区域，基站选址模块用于确定干线基站数量和各基站的选址，支线覆盖模块用于确定服务支线区域，二次扩容模块用于预测上行负载，追加建设二次基站，本发明能够保障基站与核心光纤的连接，智能优化管线路径，减少人工勘测误差，降低冗余敷设成本，缩短通信服务从规划到部署的周期，减少信号覆盖盲区，优化管线敷设路径，提升用户通信体验。
The present invention relates to the field of base station site selection, and specifically to a deep learning-based intelligent pipeline laying and base station site selection method and system, comprising: a GIS construction module, a trunk planning module, a base station site selection module, a branch line coverage module and a secondary expansion module. The GIS construction module is used to construct a GIS digital model and generate laying costs and user heat maps. The trunk planning module is used to plan the service trunk area. The base station site selection module is used to determine the number of trunk base stations and the site selection of each base station. The branch line coverage module is used to determine the service branch area. The secondary expansion module is used to predict the uplink load and additionally construct secondary base stations. The present invention can ensure the connection between the base station and the core optical fiber, intelligently optimize the pipeline path, reduce manual survey errors, reduce redundant laying costs, shorten the cycle from planning to deployment of communication services, reduce signal coverage blind spots, optimize the pipeline laying path, and enhance the user communication experience.
Description
Technical Field
The invention relates to the field of base station site selection, in particular to an intelligent pipeline laying and base station site selection method and system based on deep learning.
Background
In communication network planning, a technology of selecting a proper geographic position to deploy a base station according to factors such as technology, cost, geographic state, user requirements and the like is called a base station site selection technology. The goal of base station site selection is to achieve optimal network coverage with minimal deployment costs.
Modern 4G or 5G base stations transmit signals over optical fibers, and thus base station site selection also requires consideration of the problem of fiber optic cabling, ensuring that the base station site is located on the fiber optic line to obtain adequate communication resources.
In the process of upgrading and reforming the network base station, because the topography of regional pavement and the distribution of buildings are complex, the cost of excavating pavement, earth processing, road plugging and the like is greatly different when pipelines are laid at different positions, and the layout planning of the base station network is difficult to carry out. The conventional cellular installation mode is not suitable for base station arrangement in a complex area, the arrangement cost is high, the coverage rate of users is low, and the overload phenomenon of the base station is easy to occur.
In addition, with urban development of service areas, service flow of the base station also increases, and secondary base stations are required to be distributed in the existing base station network, but because of reasons of disordered base station installation, improper site selection and the like, the secondary base stations cannot be installed on the existing pipelines, so that the problems of low signal coverage range, optical fiber secondary construction and the like are generated, and the operation benefit of the base stations is affected.
Disclosure of Invention
The invention aims to provide an intelligent pipeline laying and base station site selection method and system based on deep learning, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the technical scheme that the intelligent pipeline laying and base station site selection system based on deep learning comprises a GIS construction module, a trunk line planning module, a base station site selection module, a branch line coverage module and a secondary capacity expansion module;
The GIS construction module is used for constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, acquiring ground height, gradient and road surface type after satellite image semantic segmentation, correlating pipeline laying cost, generating a pipeline laying cost thermodynamic diagram, estimating the density of users in each place by using a nuclear density or spatial interpolation method based on 2G base station historical traffic data, generating a user thermodynamic diagram, and calibrating by combining demographic data;
The trunk planning module is used for taking a laying starting point of the optical fiber pipeline as an origin, forming a bottom edge by using the service diameter of the base station to outwards extend a rectangular area until the rectangular area touches the edge of the base station laying area, taking the extended rectangular area as a service trunk area, planning the service trunk area in the urban GIS model by using simulation calculation software, so that the average-person pipeline laying cost in the service trunk area is minimum, and the length of the rectangular area is higher than a threshold value;
The base station site selection module is used for laying optical fiber pipelines on a rectangular central line of a service trunk area, arranging communication base stations on the optical fiber pipelines, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, being positioned on a road surface or a building with an installation space and an installation base, enabling the total installation cost of all the base stations to be minimum in the whole service trunk area, and determining the number of trunk base stations and the site selection of each base station;
The branch line coverage module is used for extending outwards again by taking each base station in the trunk line area as a starting point, generating a service branch line candidate area, ensuring that the coincidence rate of the branch line candidate area and the trunk line area is smaller than a threshold value, restricting the average cost of people and the length of branch lines of the branch lines, dividing the actual coverage area of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion for an uncovered area until all communication service areas are covered;
And the secondary capacity expansion module is used for acquiring urban geography, communication requirements, building structures and people flow density data by utilizing a multi-source sensor after the base stations are installed, modeling and analyzing environmental characteristics by utilizing a deep learning model, calculating the uplink load of each base station receiver, and when the uplink load is higher than a threshold value, selecting an address which is passed by a pipeline and has the lowest cost in the service range of the base station to additionally construct a secondary base station so as to realize the optimal selection of a dynamic link path among communication nodes.
Further, the GIS construction module comprises a pavement cost unit, a user estimation unit and a pipeline sensing unit;
the pavement cost unit is used for building an urban GIS digital model, classifying pavement types and assigning cost coefficients, wherein the pavement types comprise roads, greenbelts, buildings and water areas;
the user estimation unit is used for acquiring communication data of the 2G base stations in the area, and comprises base station coverage rate, user connection number and flow load, and estimating communication user density;
And the pipeline sensing unit is used for returning construction data to the GIS model in real time in the pipeline laying process and updating the three-dimensional model.
Further, the trunk planning module comprises an area extending unit and a cost constraint unit;
The area extending unit is used for extending the service range of the base station and determining the service trunk area;
the cost constraint unit is used for verifying the pipeline laying cost of each service trunk area and selecting the trunk laying scheme with the minimum cost.
Further, the base station site selection module comprises a communication demand unit and a site selection planning unit;
the communication demand unit is used for reducing the excavation cost by adopting a micro trenching technology and analyzing the communication density in the service trunk area;
The addressing planning unit is used for determining the distribution position of the base stations on the pipeline, so that the total installation cost of all the base stations is minimized.
Further, the branch line coverage module comprises a branch line expansion unit and a coverage verification unit;
The branch line expansion unit is used for taking a trunk line base station as a starting point, taking a base station signal coverage distance as a radius to extend to the edge of the area, generating a branch line candidate area, and determining a pipeline to lay a branch line;
and the coverage verification unit is used for verifying the coincidence rate of the branch line and the trunk line, judging the coverage condition of the regional pipeline, and triggering a new round of branch line expansion for the uncovered region until the coverage rate reaches the requirement.
Further, the secondary capacity expansion module comprises a demand monitoring unit, a deep learning unit and a secondary base station unit;
The demand monitoring unit is used for dividing the actual coverage range of each base station by using the Voronoi diagram and acquiring the communication data of the base station in real time;
the deep learning unit is used for analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model and carrying out uplink load prediction;
The secondary base station unit is used for carrying out secondary base station site selection on the existing pipeline when the uplink load of the base station is higher than a threshold value.
An intelligent pipeline laying and base station site selection method based on deep learning comprises the following steps:
S1, constructing an urban GIS digital model in a base station layout area, correlating the ground height, gradient and pavement type in the area with pipeline layout cost, generating a pipeline layout cost thermodynamic diagram, estimating user communication density based on historical telephone traffic data, and generating a user thermodynamic diagram;
S2, extending the base station service diameter to a base station layout area from the laying starting point of the optical fiber pipeline as the center until reaching the edge of the base station layout area, and planning in an urban GIS model by taking the extended rectangular area as a service trunk area to minimize the cost of the arrangement of the human-average pipelines in the service trunk area;
S3, laying an optical fiber pipeline according to the central line of the service trunk area, determining the address of a communication base station on the optical fiber pipeline, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, and enabling the total installation cost of all the base stations to be minimum;
s4, taking a base station paved on a trunk line as a starting point, taking a base station signal coverage distance as a bottom edge, extending to the edge of the area, generating a branch line candidate area, enabling the coincidence rate of the branch line candidate area and the trunk line area to be smaller than a threshold value, enabling the per-person cost and the branch line length to meet constraint conditions, dividing the coverage area of each base station, and triggering a new round of branch line expansion for an uncovered area until the coverage area meets the requirement;
S5, after the base station is installed, analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model, predicting uplink load, and determining secondary base station site selection on a laid pipeline when the uplink load is higher than a threshold value, so that the base station installation cost is the lowest.
Further, step S1 includes:
S11, constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, and acquiring ground height, gradient and road surface types by semantic segmentation of satellite images, wherein the road surface types comprise roads, greenbelts, buildings and water areas;
According to the ground height, gradient and road surface type, assigning cost coefficients, calculating the cost of laying pipelines in each region in the model, marking the cost in the GIS model, and obtaining a pipeline laying cost thermodynamic diagram;
S12, estimating the density of users in each place by utilizing a nuclear density or spatial interpolation method based on historical traffic data of the existing base station before transformation, generating a user thermodynamic diagram, and regarding coordinate points (x, y) in a GIS model, wherein the density of the users is as follows:
;
Where p (x, y) is the user density at point (x, y), N represents the number of base stations serving point (x, y), ui is the number of users of the ith base station, and di is the distance of point (x, y) to the base station.
Further, step S2 includes:
S21, enabling a scanning line segment to pass through a pipeline laying starting point, taking the pipeline laying starting point as a scanning line segment center, enabling the length of the scanning line segment to be the service diameter of a base station, enabling the scanning line segment to extend from the pipeline laying starting point to a base station laying area until reaching the edge of the base station laying area, and enabling the area where the scanning line segment passes to be used as a service trunk area;
s22, inputting a pipeline laying cost thermodynamic diagram and a user thermodynamic diagram into simulation calculation software, calculating the pipeline laying cost by the area where the central line of the service trunk area passes, and planning a unique service trunk area in the urban GIS model so as to minimize the average pipeline laying cost in the service trunk area range.
Further, step S3 includes:
S31, laying an optical fiber pipeline along the central line of a service trunk area, adopting a micro trenching technology to reduce the excavation cost, arranging base stations on the laid optical fiber pipeline, and determining a base station site selection scheme meeting the following requirements that the distance between adjacent communication base stations is smaller than the service diameter, the service capacity of the base stations meets the communication requirement in the coverage area of the base stations, and the base stations are positioned on a road surface or a building with an installation space and an installation base;
S32, evaluating all base station site selection schemes, determining the total installation cost of executing each base station site selection scheme, and selecting the base station site selection scheme with the minimum total installation cost to execute.
Further, step S4 includes:
S41, taking each base station in a trunk area as a center, taking a base station signal coverage distance as a bottom edge, extending to a base station layout area again, taking a rectangular area scanned by the bottom edge as a service branch line candidate area, and ensuring that the service branch line candidate area meets the following constraint conditions that the coincidence rate of the branch line candidate area and the trunk area is smaller than a threshold value, the average cost of branch line layout is smaller than the threshold value and the length of a branch line is higher than the threshold value;
s42, taking the service branch line candidate area with the lowest layout cost in a unit area as a service branch line area, after base station site selection is carried out on the service branch line area, dividing the actual coverage range of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion on an uncovered area until the coverage rate of the area meets the preset requirement.
Further, step S5 includes:
S51, after the base station is installed, setting a multi-source sensor at the base station to collect environmental characteristics, wherein the environmental characteristics comprise urban geography, communication requirements, building structures and people flow density data, the multi-source sensor comprises a Wi-Fi probe, a camera, BIM data and a meteorological sensor, the environmental characteristics are modeled and analyzed by a deep learning model, and the uplink load of each base station receiver is predicted based on historical communication data;
And S52, when the predicted uplink load in the next period is higher than the base station service capacity threshold, selecting an address with the lowest cost, through which a pipeline passes, from the base station service range to additionally construct a secondary base station, so that the total service capacity of the base station after the secondary base station is put into use is higher than the predicted uplink load.
Compared with the prior art, the invention has the following beneficial effects:
According to the invention, through carrying out GIS model construction on the communication service area, the cost of laying pipelines in each place is determined, and the density of users in each place is estimated through the communication data of the 2G base station, so that the service trunk area is selected, the average cost of people in the service trunk area is minimum, the signal blind area or overlapping coverage is avoided through predicting the signal coverage, the connection between the base station and the core optical fiber is ensured, the pipeline path is intelligently optimized, the manual survey error is reduced, and the redundant laying cost is reduced.
According to the invention, the optical fiber pipeline is laid on the central line of the service trunk area, and the communication base stations are arranged, so that the distance between the adjacent communication base stations is smaller than the service diameter, the total installation cost in the trunk area is minimum, the base station site selection optimization is realized, the pipeline laying path and the base station site selection are planned synchronously, the intelligent cooperativity of the whole process is improved, and the period from planning to deployment of the communication service is shortened.
According to the invention, the multisource sensor is utilized to collect urban geography, communication requirements, building structures, people flow density and other data in real time, the deep learning model is utilized to carry out modeling analysis on environmental characteristics, a secondary base station is additionally built, the optimal selection of dynamic link paths among communication nodes is realized, the signal blind area is reduced, the user experience is improved, the pipeline path is optimized, and the signal coverage rate is expanded at low cost through the dynamic optimization of the base station.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a deep learning-based intelligent pipeline laying and base station site selection system;
FIG. 2 is a schematic diagram of steps of a method for intelligent pipeline laying and base station site selection based on deep learning according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to FIG. 1, the invention provides a technical scheme that an intelligent pipeline laying and base station site selection system based on deep learning comprises a GIS construction module, a trunk planning module, a base station site selection module, a branch line coverage module and a secondary capacity expansion module;
The GIS construction module is used for constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, acquiring ground height, gradient and road surface type after satellite image semantic segmentation, correlating pipeline laying cost, generating a pipeline laying cost thermodynamic diagram, estimating the density of users in each place by using a nuclear density or spatial interpolation method based on 2G base station historical traffic data, generating a user thermodynamic diagram, and calibrating by combining demographic data;
the GIS construction module comprises a pavement cost unit, a user estimation unit and a pipeline sensing unit;
the pavement cost unit is used for building an urban GIS digital model, classifying pavement types and assigning cost coefficients, wherein the pavement types comprise roads, greenbelts, buildings and water areas;
the user estimation unit is used for acquiring communication data of the 2G base stations in the area, and comprises base station coverage rate, user connection number and flow load, and estimating communication user density;
And the pipeline sensing unit is used for returning construction data to the GIS model in real time in the pipeline laying process and updating the three-dimensional model.
The trunk planning module is used for taking a laying starting point of the optical fiber pipeline as an origin, forming a bottom edge by using the service diameter of the base station to outwards extend a rectangular area until the rectangular area touches the edge of the base station laying area, taking the extended rectangular area as a service trunk area, planning the service trunk area in the urban GIS model by using simulation calculation software, so that the average-person pipeline laying cost in the service trunk area is minimum, and the length of the rectangular area is higher than a threshold value;
the trunk planning module comprises an area extending unit and a cost constraint unit;
The area extending unit is used for extending the service range of the base station and determining the service trunk area;
the cost constraint unit is used for verifying the pipeline laying cost of each service trunk area and selecting the trunk laying scheme with the minimum cost.
The base station site selection module is used for laying optical fiber pipelines on a rectangular central line of a service trunk area, arranging communication base stations on the optical fiber pipelines, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, being positioned on a road surface or a building with an installation space and an installation base, enabling the total installation cost of all the base stations to be minimum in the whole service trunk area, and determining the number of trunk base stations and the site selection of each base station;
The base station site selection module comprises a communication demand unit and a site selection planning unit;
the communication demand unit is used for reducing the excavation cost by adopting a micro trenching technology and analyzing the communication density in the service trunk area;
The addressing planning unit is used for determining the distribution position of the base stations on the pipeline, so that the total installation cost of all the base stations is minimized.
The branch line coverage module is used for extending outwards again by taking each base station in the trunk line area as a starting point, generating a service branch line candidate area, ensuring that the coincidence rate of the branch line candidate area and the trunk line area is smaller than a threshold value, restricting the average cost of people and the length of branch lines of the branch lines, dividing the actual coverage area of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion for an uncovered area until all communication service areas are covered;
The branch line coverage module comprises a branch line expansion unit and a coverage verification unit;
The branch line expansion unit is used for taking a trunk line base station as a starting point, taking a base station signal coverage distance as a radius to extend to the edge of the area, generating a branch line candidate area, and determining a pipeline to lay a branch line;
and the coverage verification unit is used for verifying the coincidence rate of the branch line and the trunk line, judging the coverage condition of the regional pipeline, and triggering a new round of branch line expansion for the uncovered region until the coverage rate reaches the requirement.
And the secondary capacity expansion module is used for acquiring urban geography, communication requirements, building structures and people flow density data by utilizing a multi-source sensor after the base stations are installed, modeling and analyzing environmental characteristics by utilizing a deep learning model, calculating the uplink load of each base station receiver, and when the uplink load is higher than a threshold value, selecting an address which is passed by a pipeline and has the lowest cost in the service range of the base station to additionally construct a secondary base station so as to realize the optimal selection of a dynamic link path among communication nodes.
The secondary capacity expansion module comprises a demand monitoring unit, a deep learning unit and a secondary base station unit;
The demand monitoring unit is used for dividing the actual coverage range of each base station by using the Voronoi diagram and acquiring the communication data of the base station in real time;
the deep learning unit is used for analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model and carrying out uplink load prediction;
The secondary base station unit is used for carrying out secondary base station site selection on the existing pipeline when the uplink load of the base station is higher than a threshold value.
As shown in fig. 2, the method for intelligent pipeline laying and base station site selection based on deep learning comprises the following steps:
S1, constructing an urban GIS digital model in a base station layout area, correlating the ground height, gradient and pavement type in the area with pipeline layout cost, generating a pipeline layout cost thermodynamic diagram, estimating user communication density based on historical telephone traffic data, and generating a user thermodynamic diagram;
The step S1 comprises the following steps:
S11, constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, and acquiring ground height, gradient and road surface types by semantic segmentation of satellite images, wherein the road surface types comprise roads, greenbelts, buildings and water areas;
According to the ground height, gradient and road surface type, assigning cost coefficients, calculating the cost of laying pipelines in each region in the model, marking the cost in the GIS model, and obtaining a pipeline laying cost thermodynamic diagram;
S12, estimating the density of users in each place by utilizing a nuclear density or spatial interpolation method based on historical traffic data of the existing base station before transformation, generating a user thermodynamic diagram, and regarding coordinate points (x, y) in a GIS model, wherein the density of the users is as follows:
;
Where p (x, y) is the user density at point (x, y), N represents the number of base stations serving point (x, y), ui is the number of users of the ith base station, and di is the distance of point (x, y) to the base station.
S2, extending the base station service diameter to a base station layout area from the laying starting point of the optical fiber pipeline as the center until reaching the edge of the base station layout area, and planning in an urban GIS model by taking the extended rectangular area as a service trunk area to minimize the cost of the arrangement of the human-average pipelines in the service trunk area;
the step S2 comprises the following steps:
S21, enabling a scanning line segment to pass through a pipeline laying starting point, taking the pipeline laying starting point as a scanning line segment center, enabling the length of the scanning line segment to be the service diameter of a base station, enabling the scanning line segment to extend from the pipeline laying starting point to a base station laying area until reaching the edge of the base station laying area, and enabling the area where the scanning line segment passes to be used as a service trunk area;
s22, inputting a pipeline laying cost thermodynamic diagram and a user thermodynamic diagram into simulation calculation software, calculating the pipeline laying cost by the area where the central line of the service trunk area passes, and planning a unique service trunk area in the urban GIS model so as to minimize the average pipeline laying cost in the service trunk area range.
S3, laying an optical fiber pipeline according to the central line of the service trunk area, determining the address of a communication base station on the optical fiber pipeline, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, and enabling the total installation cost of all the base stations to be minimum;
The step S3 comprises the following steps:
S31, laying an optical fiber pipeline along the central line of a service trunk area, adopting a micro trenching technology to reduce the excavation cost, arranging base stations on the laid optical fiber pipeline, and determining a base station site selection scheme meeting the following requirements that the distance between adjacent communication base stations is smaller than the service diameter, the service capacity of the base stations meets the communication requirement in the coverage area of the base stations, and the base stations are positioned on a road surface or a building with an installation space and an installation base;
S32, evaluating all base station site selection schemes, determining the total installation cost of executing each base station site selection scheme, and selecting the base station site selection scheme with the minimum total installation cost to execute.
S4, taking a base station paved on a trunk line as a starting point, taking a base station signal coverage distance as a bottom edge, extending to the edge of the area, generating a branch line candidate area, enabling the coincidence rate of the branch line candidate area and the trunk line area to be smaller than a threshold value, enabling the per-person cost and the branch line length to meet constraint conditions, dividing the coverage area of each base station, and triggering a new round of branch line expansion for an uncovered area until the coverage area meets the requirement;
the step S4 includes:
S41, taking each base station in a trunk area as a center, taking a base station signal coverage distance as a bottom edge, extending to a base station layout area again, taking a rectangular area scanned by the bottom edge as a service branch line candidate area, and ensuring that the service branch line candidate area meets the following constraint conditions that the coincidence rate of the branch line candidate area and the trunk area is smaller than a threshold value, the average cost of branch line layout is smaller than the threshold value and the length of a branch line is higher than the threshold value;
s42, taking the service branch line candidate area with the lowest layout cost in a unit area as a service branch line area, after base station site selection is carried out on the service branch line area, dividing the actual coverage range of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion on an uncovered area until the coverage rate of the area meets the preset requirement.
S5, after the base station is installed, analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model, predicting uplink load, and determining secondary base station site selection on a laid pipeline when the uplink load is higher than a threshold value, so that the base station installation cost is the lowest.
The step S5 comprises the following steps:
S51, after the base station is installed, setting a multi-source sensor at the base station to collect environmental characteristics, wherein the environmental characteristics comprise urban geography, communication requirements, building structures and people flow density data, the multi-source sensor comprises a Wi-Fi probe, a camera, BIM data and a meteorological sensor, the environmental characteristics are modeled and analyzed by a deep learning model, and the uplink load of each base station receiver is predicted based on historical communication data;
And S52, when the predicted uplink load in the next period is higher than the base station service capacity threshold, selecting an address with the lowest cost, through which a pipeline passes, from the base station service range to additionally construct a secondary base station, so that the total service capacity of the base station after the secondary base station is put into use is higher than the predicted uplink load.
In the embodiment, an urban GIS model is built for a base station service area of 100km multiplied by 100km, a pipeline laying starting point is a right lower edge point of an city, the service radius of the base station is 5km, a service trunk line area is selected to pass through the urban area, so that the average laying cost of people in a coverage area is minimum, after base station site selection is carried out in the trunk line, branch line areas are outwards extended by all base stations until the coverage rate of users reaches the communication requirement.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the above-mentioned embodiments are merely preferred embodiments of the present invention, and the present invention is not limited thereto, but may be modified or substituted for some of the technical features thereof by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An intelligent pipeline laying and base station site selection method based on deep learning is characterized by comprising the following steps:
S1, constructing an urban GIS digital model in a base station layout area, correlating the ground height, gradient and pavement type in the area with pipeline layout cost, generating a pipeline layout cost thermodynamic diagram, estimating user communication density based on historical telephone traffic data, and generating a user thermodynamic diagram;
S2, extending the base station service diameter to a base station layout area from the laying starting point of the optical fiber pipeline as the center until reaching the edge of the base station layout area, and planning in an urban GIS model by taking the extended rectangular area as a service trunk area to minimize the cost of the arrangement of the human-average pipelines in the service trunk area;
S3, laying an optical fiber pipeline according to the central line of the service trunk area, determining the address of a communication base station on the optical fiber pipeline, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, and enabling the total installation cost of all the base stations to be minimum;
S4, taking a base station paved on a trunk line as a starting point, taking a base station signal coverage distance as a bottom edge, extending to the edge, generating a branch line candidate area, enabling the superposition ratio of the branch line candidate area and the trunk line area to be smaller than a threshold value, enabling the per-person cost and the branch line length to meet constraint conditions, dividing coverage areas of all base stations, and triggering a new round of branch line expansion for an uncovered area until the coverage areas meet requirements;
S5, after the base station is installed, analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model, predicting uplink load, and determining secondary base station site selection on a laid pipeline when the uplink load is higher than a threshold value, so that the base station installation cost is the lowest.
2. The intelligent pipeline laying and base station site selection method based on deep learning of claim 1, wherein the step S1 comprises the following steps:
S11, constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, and acquiring ground height, gradient and road surface types by semantic segmentation of satellite images, wherein the road surface types comprise roads, greenbelts, buildings and water areas;
According to the ground height, gradient and road surface type, assigning cost coefficients, calculating the cost of laying pipelines in each region in the model, marking the cost in the GIS model, and obtaining a pipeline laying cost thermodynamic diagram;
S12, estimating the density of users in each place by utilizing a nuclear density or spatial interpolation method based on historical traffic data of the existing base station before transformation, generating a user thermodynamic diagram, and regarding coordinate points (x, y) in a GIS model, wherein the density of the users is as follows:
;
Where p (x, y) is the user density at point (x, y), N represents the number of base stations serving point (x, y), ui is the number of users of the ith base station, and di is the distance of point (x, y) to the base station.
3. The intelligent pipeline laying and base station site selection method based on deep learning as set forth in claim 2, wherein the step S2 comprises the following steps:
S21, enabling a scanning line segment to pass through a pipeline laying starting point, taking the pipeline laying starting point as a scanning line segment center, enabling the length of the scanning line segment to be the service diameter of a base station, enabling the scanning line segment to extend from the pipeline laying starting point to a base station laying area until reaching the edge of the base station laying area, and enabling the area where the scanning line segment passes to be used as a service trunk area;
S22, inputting a pipeline laying cost thermodynamic diagram and a user thermodynamic diagram into simulation calculation software, calculating pipeline laying cost by a region through which the central line of the service trunk line region passes, and planning a unique service trunk line region in the urban GIS model so as to minimize the average pipeline laying cost in the service trunk line region;
The step S3 comprises the following steps:
S31, laying an optical fiber pipeline along the central line of a service trunk area, adopting a micro trenching technology to reduce the excavation cost, arranging base stations on the laid optical fiber pipeline, and determining a base station site selection scheme meeting the following requirements that the distance between adjacent communication base stations is smaller than the service diameter, the service capacity of the base stations meets the communication requirement in the coverage area of the base stations, and the base stations are positioned on a road surface or a building with an installation space and an installation base;
S32, evaluating all base station site selection schemes, determining the total installation cost of executing each base station site selection scheme, and selecting the base station site selection scheme with the minimum total installation cost to execute.
4. The intelligent pipeline laying and base station locating method based on deep learning of claim 3, wherein the step S4 comprises the following steps:
S41, taking each base station in a trunk area as a center, taking a base station signal coverage distance as a bottom edge, extending to a base station layout area again, taking a rectangular area scanned by the bottom edge as a service branch line candidate area, and ensuring that the service branch line candidate area meets the following constraint conditions that the coincidence rate of the branch line candidate area and the trunk area is smaller than a threshold value, the average cost of branch line layout is smaller than the threshold value and the length of a branch line is higher than the threshold value;
s42, taking the service branch line candidate area with the lowest layout cost in a unit area as a service branch line area, after base station site selection is carried out on the service branch line area, dividing the actual coverage range of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion on an uncovered area until the coverage rate of the area meets the preset requirement.
5. The intelligent pipeline laying and base station locating method based on deep learning of claim 4, wherein the step S5 comprises the following steps:
S51, after the base station is installed, setting a multi-source sensor at the base station to collect environmental characteristics, wherein the environmental characteristics comprise urban geography, communication requirements, building structures and people flow density data, the multi-source sensor comprises a Wi-Fi probe, a camera, BIM data and a meteorological sensor, the environmental characteristics are modeled and analyzed by a deep learning model, and the uplink load of each base station receiver is predicted based on historical communication data;
And S52, when the predicted uplink load in the next period is higher than the base station service capacity threshold, selecting an address with the lowest cost, through which a pipeline passes, from the base station service range to additionally construct a secondary base station, so that the total service capacity of the base station after the secondary base station is put into use is higher than the predicted uplink load.
6. An intelligent pipeline laying and base station site selection system based on deep learning is characterized by comprising a GIS construction module, a trunk planning module, a base station site selection module, a branch line coverage module and a secondary capacity expansion module;
The GIS construction module is used for constructing a high-precision urban GIS digital elevation model of a base station layout area by using LiDAR or unmanned aerial vehicle aerial survey, acquiring ground height, gradient and road surface type after satellite image semantic segmentation, correlating pipeline laying cost, generating a pipeline laying cost thermodynamic diagram, estimating the density of users in each place by using a nuclear density or spatial interpolation method based on 2G base station historical traffic data, generating a user thermodynamic diagram, and calibrating by combining demographic data;
The trunk planning module is used for taking a laying starting point of the optical fiber pipeline as an origin, forming a bottom edge by using the service diameter of the base station to outwards extend a rectangular area until the rectangular area touches the edge of the base station laying area, taking the extended rectangular area as a service trunk area, planning the service trunk area in the urban GIS model by using simulation calculation software, so that the average-person pipeline laying cost in the service trunk area is minimum, and the length of the rectangular area is higher than a threshold value;
The base station site selection module is used for laying optical fiber pipelines on a rectangular central line of a service trunk area, arranging communication base stations on the optical fiber pipelines, enabling the distance between adjacent communication base stations to be smaller than the service diameter, meeting the area communication requirement, being positioned on a road surface or a building with an installation space and an installation base, enabling the total installation cost of all the base stations to be minimum in the whole service trunk area, and determining the number of trunk base stations and the site selection of each base station;
The branch line coverage module is used for extending outwards again by taking each base station in the trunk line area as a starting point, generating a service branch line candidate area, ensuring that the coincidence rate of the branch line candidate area and the trunk line area is smaller than a threshold value, restricting the average cost of people and the length of branch lines of the branch lines, dividing the actual coverage area of each base station by using a Voronoi diagram, and triggering a new round of branch line expansion for an uncovered area until all communication service areas are covered;
And the secondary capacity expansion module is used for acquiring urban geography, communication requirements, building structures and people flow density data by utilizing a multi-source sensor after the base stations are installed, modeling and analyzing environmental characteristics by utilizing a deep learning model, calculating the uplink load of each base station receiver, and when the uplink load is higher than a threshold value, selecting an address which is passed by a pipeline and has the lowest cost in the service range of the base station to additionally construct a secondary base station so as to realize the optimal selection of a dynamic link path among communication nodes.
7. The intelligent pipeline laying and base station site selection system based on deep learning of claim 6, wherein the GIS construction module comprises a pavement cost unit, a user estimation unit and a pipeline sensing unit;
the pavement cost unit is used for building an urban GIS digital model, classifying pavement types and assigning cost coefficients, wherein the pavement types comprise roads, greenbelts, buildings and water areas;
the user estimation unit is used for acquiring communication data of the 2G base stations in the area, and comprises base station coverage rate, user connection number and flow load, and estimating communication user density;
And the pipeline sensing unit is used for returning construction data to the GIS model in real time in the pipeline laying process and updating the three-dimensional model.
8. The intelligent pipeline laying and base station site selection system based on deep learning of claim 7, wherein the trunk planning module comprises an area extending unit and a cost constraint unit;
The area extending unit is used for extending the service range of the base station and determining the service trunk area;
The cost constraint unit is used for verifying the pipeline laying cost of each service trunk area and selecting a trunk laying scheme with the minimum cost;
The base station site selection module comprises a communication demand unit and a site selection planning unit;
the communication demand unit is used for reducing the excavation cost by adopting a micro trenching technology and analyzing the communication density in the service trunk area;
The addressing planning unit is used for determining the distribution position of the base stations on the pipeline, so that the total installation cost of all the base stations is minimized.
9. The intelligent pipeline laying and base station site selection system based on deep learning of claim 8, wherein the branch line coverage module comprises a branch line expansion unit and a coverage verification unit;
The branch line expansion unit is used for taking a trunk line base station as a starting point, taking a base station signal coverage distance as a radius to extend to the edge of the area, generating a branch line candidate area, and determining a pipeline to lay a branch line;
and the coverage verification unit is used for verifying the coincidence rate of the branch line and the trunk line, judging the coverage condition of the regional pipeline, and triggering a new round of branch line expansion for the uncovered region until the coverage rate reaches the requirement.
10. The intelligent pipeline laying and base station site selection system based on deep learning of claim 9, wherein the secondary capacity expansion module comprises a demand monitoring unit, a deep learning unit and a secondary base station unit;
The demand monitoring unit is used for dividing the actual coverage range of each base station by using the Voronoi diagram and acquiring the communication data of the base station in real time;
the deep learning unit is used for analyzing urban geography, communication requirements, building structures and people flow density data by using a deep learning model and carrying out uplink load prediction;
The secondary base station unit is used for carrying out secondary base station site selection on the existing pipeline when the uplink load of the base station is higher than a threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510810742.9A CN120746319A (en) | 2025-06-17 | 2025-06-17 | A method and system for intelligent pipeline laying and base station site selection based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510810742.9A CN120746319A (en) | 2025-06-17 | 2025-06-17 | A method and system for intelligent pipeline laying and base station site selection based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120746319A true CN120746319A (en) | 2025-10-03 |
Family
ID=97197037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510810742.9A Pending CN120746319A (en) | 2025-06-17 | 2025-06-17 | A method and system for intelligent pipeline laying and base station site selection based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120746319A (en) |
-
2025
- 2025-06-17 CN CN202510810742.9A patent/CN120746319A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10542330B2 (en) | Automatic adaptive network planning | |
| CN106056247B (en) | A method for selecting optimal traffic routes in urban waterlogging scenarios | |
| US6771932B2 (en) | Method and system for automatically determining lines of sight between nodes | |
| KR102798882B1 (en) | Method for determining river zone using river topology information structure and boundary of inundation range, and recording medium thereof | |
| US20180121576A1 (en) | Network planning using mobile data collection devices and machine learning | |
| JPWO2010067560A1 (en) | Radio wave environment data correction system, method and program | |
| US20100103868A1 (en) | Method for modeling wireless network coverage under line-of-sight conditions | |
| CN108230482B (en) | Underground space patrol inspection point setting method and device based on software definition | |
| JPWO2010113379A1 (en) | Radio wave condition measurement system, radio wave condition measurement method, and radio wave condition measurement program | |
| US8942956B1 (en) | Method and apparatus for building and presenting network designs | |
| CN119047337A (en) | Road engineering design modeling method and system based on BIM three-dimensional visualization technology | |
| Sousa et al. | How to evaluate the quality of coarse‐resolution DEM‐derived drainage networks | |
| Fakhrmoosavi et al. | An iterative learning approach for network contraction: Path finding problem in stochastic time‐varying networks | |
| KR101988040B1 (en) | Method for managing water feed pipelines, computer readable medium for performing the method | |
| CN120746319A (en) | A method and system for intelligent pipeline laying and base station site selection based on deep learning | |
| CN119294017A (en) | A method and system for selecting a site for connection of a drainage network | |
| CN108536934B (en) | Underground Power Pipeline Planning Method with Geological Judgment | |
| Brown et al. | Large-scale geospatial planning of wireless backhaul links | |
| Kunapo et al. | Drainage network modelling for water‐sensitive urban design | |
| CN115130264B (en) | Urban waterlogging prediction method and system based on runoff coupling simulation | |
| CN115291304B (en) | Deployment method of omnidirectional antenna hub-and-spoke microwave intensive rainfall monitoring network | |
| CN114090147B (en) | Data processing method based on geographic information platform | |
| CN110109152B (en) | A GNSS Local Positioning Error Spatial Modeling Method | |
| JP3894547B2 (en) | Shape matching database and shape matching device | |
| CN113645633B (en) | Backbone network planning method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |