[go: up one dir, main page]

CN100391195C - A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service - Google Patents

A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service Download PDF

Info

Publication number
CN100391195C
CN100391195C CNB2003101094296A CN200310109429A CN100391195C CN 100391195 C CN100391195 C CN 100391195C CN B2003101094296 A CNB2003101094296 A CN B2003101094296A CN 200310109429 A CN200310109429 A CN 200310109429A CN 100391195 C CN100391195 C CN 100391195C
Authority
CN
China
Prior art keywords
data packet
length
request
packet length
packet
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.)
Expired - Lifetime
Application number
CNB2003101094296A
Other languages
Chinese (zh)
Other versions
CN1630270A (en
Inventor
张凯宾
沈钢
金珊
刘儿兀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nokia Shanghai Bell Co Ltd
Original Assignee
Alcatel Lucent Shanghai Bell Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Alcatel Lucent Shanghai Bell Co Ltd filed Critical Alcatel Lucent Shanghai Bell Co Ltd
Priority to CNB2003101094296A priority Critical patent/CN100391195C/en
Publication of CN1630270A publication Critical patent/CN1630270A/en
Application granted granted Critical
Publication of CN100391195C publication Critical patent/CN100391195C/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本发明提供一种动态调整数据分组长度的方法,包括步骤:源端向目的端发送含有时间戳信息的时间戳分组;目的端收到所述时间戳分组后,判断是否需要改变数据分组长度;如果需要改变数据分组长度,则所述目的端计算新的数据分组长度,并向所述源端发送请求改变数据分组长度的请求分组;所述源端根据所述请求分组的内容,或者将数据分组长度改为新的数据分组长度或使其保持不变,并向所述目的端发送响应分组;所述目的端根据所述响应分组的内容,对数据分组长度做相应处理。根据本发明的方法,可以动态监测网络服务质量的变化,动态调整数据分组长度,最大限度地减小网络服务质量变化对用户业务质量的影响。另外,本发明的方法提高了网络带宽利用率。

Figure 200310109429

The present invention provides a method for dynamically adjusting the length of a data packet, comprising the steps of: a source end sends a time stamp packet containing time stamp information to a destination end; after receiving the time stamp packet, the destination end judges whether the length of the data packet needs to be changed; If it is necessary to change the length of the data packet, the destination calculates a new data packet length, and sends a request packet requesting to change the length of the data packet to the source; The packet length is changed to a new data packet length or kept unchanged, and a response packet is sent to the destination; the destination performs corresponding processing on the data packet length according to the content of the response packet. According to the method of the invention, the change of the network service quality can be dynamically monitored, the length of the data packet can be dynamically adjusted, and the influence of the change of the network service quality on the service quality of the user can be minimized. In addition, the method of the invention improves the utilization rate of network bandwidth.

Figure 200310109429

Description

基于网络服务质量动态调整数据分组长度的方法 A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service

技术领域 technical field

本发明涉及分组交换网络,尤其涉及分组交换网络中传输时分复用业务时根据网络服务质量动态调整数据分组长度的方法。The invention relates to a packet switching network, in particular to a method for dynamically adjusting the length of a data packet according to network service quality when transmitting time division multiplexing services in the packet switching network.

背景技术 Background technique

传统的时分复用(TDM)电路交换业务具有传输延迟小、实时响应能力高等特点,适于传输语音、视频等实时性业务,在现代电信网中具有极为重要的作用和极大市场份额。但是TDM交换业务采用信道独享,所以资源利用率低。如果能将TDM业务通过分组交换网络进行传输,则可在很大程度上提高线路利用率,降低传输成本。The traditional time-division multiplexing (TDM) circuit switching service has the characteristics of small transmission delay and high real-time response capability, and is suitable for transmitting real-time services such as voice and video. It plays an extremely important role and has a huge market share in modern telecommunication networks. However, the TDM switching service uses an exclusive channel, so the resource utilization rate is low. If the TDM business can be transmitted through the packet switching network, the line utilization can be greatly improved and the transmission cost can be reduced.

在异步的分组交换网络中传输同步或准同步的TDM电路仿真业务,需要解决两个主要问题:一是如何解决发送端与接收端的时钟同步,即时钟恢复问题;二是如何尽可能地减小延时,更好地保证业务特性。To transmit synchronous or quasi-synchronous TDM circuit emulation services in an asynchronous packet-switching network, two main problems need to be solved: one is how to solve the clock synchronization between the sending end and the receiving end, that is, the clock recovery problem; the other is how to minimize the Delay, to better guarantee business characteristics.

影响时钟恢复精度的主要原因是分组交换网络中数据分组的分组时延。所谓分组时延是指数据分组从发送端传到接收端所需的时间。分组时延包括以下几方面的内容:发送端封装的等待时延;信号线路传输时延;由于网路拥塞等原因造成的时延抖动。The main reason affecting the accuracy of clock recovery is the packet delay of data packets in the packet switching network. The so-called packet delay refers to the time required for a data packet to pass from the sender to the receiver. The packet delay includes the following aspects: the waiting delay of the sending end encapsulation; the transmission delay of the signal line; the delay jitter caused by network congestion and other reasons.

目前,消除时延抖动的主要方法是通过在接收端设置一定大小的抖动缓冲区,以牺牲时延特性来减小抖动,换取恢复时钟精度的提升。为了便于处理,现有的解决方案是将TDM流中的字节封装在固定长度的数据分组中,而一个数据分组中封装的TDM字节数由用户根据实际网络状况决定。At present, the main method to eliminate delay jitter is to set a certain size jitter buffer at the receiving end to reduce the jitter by sacrificing the delay characteristics in exchange for improving the accuracy of the recovered clock. In order to facilitate processing, the existing solution is to encapsulate the bytes in the TDM stream into fixed-length data packets, and the number of TDM bytes encapsulated in a data packet is determined by the user according to the actual network conditions.

当网络带宽利用率较低和用户要求TDM业务有较小的延时时,可以将数据分组长度设置为尽可能小,这样就不会因为封装时需要等待更多的TDM帧而造成时延的增大。相反,如果用户对业务实时性无严格要求或者网络环境较好,则可将封装TDM流的数据分组长度设置得大一些以节省带宽资源。When the network bandwidth utilization rate is low and the user requires a small delay for TDM services, the data packet length can be set as small as possible, so that there will be no delay due to the need to wait for more TDM frames during encapsulation increase. On the contrary, if the user does not have strict requirements on the real-time performance of the service or the network environment is good, the length of the data packet encapsulating the TDM stream can be set larger to save bandwidth resources.

但是上述方法对用户而言,不仅操作起来较为复杂,而且由于网络结构和流量特征是随着用户的需求和发展而不断变化的,用户不可能实时监控网络实际流量和结构的变化对分组长度做出必要的调整,因而这种方法可操作性不强,不能更好地为TDM仿真业务提供质量保证。However, the above method is not only complicated for users to operate, but also because the network structure and traffic characteristics are constantly changing with the needs and development of users, it is impossible for users to monitor the actual network traffic and structure changes in real time and make changes to the packet length. Therefore, the operability of this method is not strong, and it cannot better provide quality assurance for TDM simulation services.

发明内容 Contents of the invention

本发明的目的在于提供一种既便于操作又能动态调整数据分组长度的方法,从而更好地为时分复用业务提供质量保证。The purpose of the present invention is to provide a method that is convenient for operation and can dynamically adjust the length of data packets, so as to better provide quality assurance for time-division multiplexing services.

为实现上述目的,本发明提供一种动态调整数据分组长度的方法,其特征在于包括以下步骤:To achieve the above object, the present invention provides a method for dynamically adjusting the length of a data packet, which is characterized in that it comprises the following steps:

源端向目的端发送含有时间戳信息的时间戳分组;The source sends a timestamp packet containing timestamp information to the destination;

目的端收到所述时间戳分组后,判断是否需要改变数据分组长度;After the destination terminal receives the timestamp packet, it judges whether the length of the data packet needs to be changed;

如果需要改变数据分组长度,则所述目的端计算新的数据分组长度,并向所述源端发送请求改变数据分组长度的请求分组;If it is necessary to change the length of the data packet, the destination calculates a new length of the data packet, and sends a request packet requesting to change the length of the data packet to the source;

所述源端根据所述请求分组的内容,对数据分组长度做相应处理,并向所述目的端发送响应分组。The source end performs corresponding processing on the length of the data packet according to the content of the request packet, and sends a response packet to the destination end.

本发明的方法还包括一个步骤:所述目的端根据所述响应分组的内容,对数据分组长度做相应处理。The method of the present invention also includes a step: the destination terminal performs corresponding processing on the length of the data packet according to the content of the response packet.

根据本发明的方法,可以动态监测网络服务质量的变化,动态调整数据分组长度,使数据分组长度根据网络实时流量状况和用户的业务质量的要求,作动态改变,从而最大限度地减小网络服务质量变化对用户TDM业务质量的影响。另外,本发明的方法更加有效地利用了网络带宽。According to the method of the present invention, the change of network service quality can be dynamically monitored, and the length of data packets can be dynamically adjusted, so that the length of data packets can be dynamically changed according to the real-time traffic conditions of the network and the requirements of the user's service quality, thereby reducing network service quality to the greatest extent. Impact of quality changes on user TDM service quality. In addition, the method of the present invention utilizes the network bandwidth more effectively.

结合附图阅读本发明实施方式的详细描述后,本发明的其他特点和优点将变得更加清楚。Other features and advantages of the present invention will become more apparent after reading the detailed description of the embodiments of the present invention in conjunction with the accompanying drawings.

附图说明 Description of drawings

图1是根据本发明的动态调整数据分组长度的方法的示意流程图;Fig. 1 is the schematic flowchart of the method for dynamically adjusting data packet length according to the present invention;

图2是图1所示方法在信令数据分组丢失情况下的示意流程图;Fig. 2 is a schematic flowchart of the method shown in Fig. 1 in the case of signaling data packet loss;

图3是根据本发明的动态调整数据分组长度的方法在接收端的示意流程图。Fig. 3 is a schematic flow chart at the receiving end of the method for dynamically adjusting the length of a data packet according to the present invention.

具体实施方式 Detailed ways

下面结合附图详细描述本发明的具体实施方式。Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

图1是根据本发明的动态调整数据分组长度的方法的示意流程图。图1中左侧所示的处理过程是在源端(发送端)执行的,右侧所示的处理过程是在目的端(接收端)执行的。图1所示的流程图实际上是源端与目的端之间,为了实现动态调整数据分组长度的目的,而进行的信令信息交互过程。Fig. 1 is a schematic flowchart of a method for dynamically adjusting the length of a data packet according to the present invention. The processing procedure shown on the left side in FIG. 1 is performed on the source side (sending side), and the processing procedure shown on the right side is performed on the destination side (receiving side). The flow chart shown in FIG. 1 is actually a signaling information interaction process between the source end and the destination end for the purpose of dynamically adjusting the length of the data packet.

首先,对包括源端和目的端的分组交换网络进行初始化,设置业务的服务质量要求q及相关系统参数。分组交换网络的初始化过程与本发明的实质无关,并且是本领域普通技术人员熟知的。First, initialize the packet switching network including the source end and the destination end, and set the service quality requirement q and related system parameters of the business. The initialization process of a packet-switched network is not relevant to the essence of the present invention and is well known to those of ordinary skill in the art.

在分组交换网络初始化之后,源端定期发送时间戳分组。即在步骤101,源端采用带内或带外的方式以频率f定时向目的端发送含有时间戳信息的时间戳分组T。After initialization of the packet-switched network, the source periodically sends time-stamped packets. That is, in step 101, the source end regularly sends a time stamp packet T containing time stamp information to the destination end at a frequency f in an in-band or out-of-band manner.

目的端收到包含有时间戳信息的时间戳分组T后,在步骤102,利用包含在时间戳分组T中的时间戳信息,并且利用时间戳分组T到达时刻对应的时间戳,计算时间戳分组T的传输时延t、时延抖动d。After the destination end receives the timestamp packet T containing timestamp information, in step 102, it uses the timestamp information contained in the timestamp packet T and uses the timestamp corresponding to the arrival time of the timestamp packet T to calculate the timestamp packet T's transmission delay t, delay jitter d.

然后,目的端在步骤103根据传输时延t、时延抖动d、原数据分组长度l和业务的服务质量要求q,应用控制策略f1(l,t,d,q),判断是否需要改变数据分组长度。Then, in step 103, the destination end applies the control strategy f1(l, t, d, q) according to the transmission delay t, the delay jitter d, the original data packet length l and the service quality requirement q, and judges whether it is necessary to change the data packet length.

传输时延t和时延抖动d属于高频变化参量,不能因为某一次数据传输过程中的传输时延或时延抖动的变化较大,就改变数据分组长度。相反,应该以某一预定时间段内的平均传输时延、平均时延抖动作为参考,结合其他参数,决定是否改变数据分组长度。否则,可能造成数据分组长度频繁改变,以致影响系统稳定性。Transmission delay t and delay jitter d are high-frequency variable parameters, and the data packet length cannot be changed because of a large change in transmission delay or delay jitter during a certain data transmission process. On the contrary, the average transmission delay and average delay jitter within a predetermined period of time should be used as a reference, combined with other parameters to determine whether to change the length of the data packet. Otherwise, the length of the data packet may change frequently, which may affect the stability of the system.

步骤103中的判断有两种结果。The judgment in step 103 has two results.

第一种判断结果是不改变数据分组长度。这种情况下,不向源端发送任何信息,返回到步骤102之前的状态,目的端等待从源湍接收新的数据分组。The first judgment result is not to change the length of the data packet. In this case, no information is sent to the source end, and the state before step 102 is returned, and the destination end waits to receive new data packets from the source end.

第二种判断结果是改变数据分组长度。这种情况下,处理过程进行到步骤104。The second judgment result is to change the data packet length. In this case, processing proceeds to step 104 .

在步骤104,即在决定改变数据分组长度的情况下,目的端确定数据分组的最佳长度lnew,然后进行到步骤105。In step 104 , that is, in the case of deciding to change the length of the data packet, the destination determines the optimal length lnew of the data packet, and then proceeds to step 105 .

在步骤105,将新的数据分组长度包含在请求改变分组长度的数据分组Req内,然后将数据分组Req发送给源端,并等待源端的应答。In step 105, include the new data packet length in the data packet Req requesting to change the packet length, then send the data packet Req to the source end, and wait for a response from the source end.

在步骤106,当源端收到目的端发来的请求改变分组长度的数据分组Req后,应用本地规则g(l,lnew),判断是否接受改变分组长度的请求。这种判断有两种结果。In step 106, after the source end receives the data packet Req requesting to change the packet length from the destination end, it applies the local rule g(l, lnew) to judge whether to accept the request for changing the packet length. This judgment has two consequences.

第一种判断结果是拒绝改变分组长度的请求。在这种情况下,在步骤107,源端向目的端发送拒绝请求的响应分组Ack。The first judgment result is to reject the request to change the packet length. In this case, in step 107, the source sends a response packet Ack to the destination to reject the request.

第二种判断结果是接受改变分组长度的请求。在这种情况下,在步骤107,源端向目的端发送接受请求的响应分组Ack,并且从该时刻起第一预定时间间隔t1之后,执行步骤109。之所以等待第一预定时间间隔t1后才执行步骤109,是为了保证目的端有足够的时间接收响应分组Ack并根据响应分组Ack的内容做相应处理。例如,为接收按新的分组长度封装的数据分组做好准备。The second judgment result is to accept the request to change the packet length. In this case, in step 107, the source end sends a response packet Ack for accepting the request to the destination end, and after the first predetermined time interval t1 from this moment, step 109 is executed. The reason why step 109 is executed after the first predetermined time interval t1 is to ensure that the destination end has enough time to receive the response packet Ack and perform corresponding processing according to the content of the response packet Ack. For example, prepare to receive data packets encapsulated with a new packet length.

如果步骤106中决定接受改变分组长度的请求,则在步骤109,源端开始发送以新的分组长度lnew封装的数据分组。在所发送的数据分组中,分组长度改变标志位被置位。If it is decided in step 106 to accept the request for changing the packet length, then in step 109, the source starts sending data packets encapsulated with the new packet length lnew. In the transmitted data packet, the packet length change flag is set.

另一方面,在步骤108,目的端收到发送端返回的响应分组后,根据响应分组内容做相应处理,如将数据分组长度设定为新长度或使其保持不变。具体地说,如果收到源端接受请求的响应,则目的端确认本地接收数据分组的分组长度将从收到第一个分组长度改变标志位被置位的数据分组(即步骤109发送的数据分组)时刻起设定为新的数据分组长度lnew。如果收到源端拒绝请求的响应,则目的端确认仍将本地接收数据分组的分组长度保持为原数据分组长度l不变。On the other hand, in step 108, after receiving the response packet returned by the sender, the destination end performs corresponding processing according to the content of the response packet, such as setting the length of the data packet to a new length or keeping it unchanged. Specifically, if the response of the source end accepting the request is received, the destination end confirms that the packet length of the locally received data packet will be changed from receiving the first packet length change flag bit to the data packet (i.e. the data sent in step 109) Packet) time is set to the new data packet length lnew. If the response of the source end rejecting the request is received, the destination end confirms that the packet length of the locally received data packet remains unchanged at the original data packet length l.

在与步骤109对应的步骤110,目的端接收到分组长度改变标志位被置位的、以新数据分组长度lnew封装的数据分组,然后将本地合法接收数据分组时使用的数据分组长度设置为新数据分组长度lnew。In step 110 corresponding to step 109, the destination end receives the data packet whose packet length change flag bit is set and encapsulated with the new data packet length lnew, then the data packet length used when the local legally received data packet is set to the new Data packet length lnew.

图2是图1所示方法在信令数据分组丢失情况下的示意流程图。图2中的步骤与图1中的步骤大致相同,所不同的是在图2中考虑了信令数据分组丢失的情况。例如,在步骤105中发送了请求改变分组长度的请求分组Req之后,请求分组Req有可能丢失,如图2中所示。另外,在步骤107中由源端发送响应分组Ack后,响应分组Ack也有可能丢失,如图2中所示。在这两种情况下,都使得目的端在发送了请求改变分组长度的请求分组Req之后得不到响应,从而达不到动态调整数据分组长度的目的。Fig. 2 is a schematic flowchart of the method shown in Fig. 1 in the case of signaling data packet loss. The steps in Fig. 2 are roughly the same as those in Fig. 1, except that in Fig. 2 the case of signaling data packet loss is considered. For example, after the request packet Req requesting to change the packet length is sent in step 105, the request packet Req may be lost, as shown in FIG. 2 . In addition, after the source end sends the response packet Ack in step 107, the response packet Ack may also be lost, as shown in FIG. 2 . In both cases, the destination end cannot get a response after sending the request packet Req requesting to change the packet length, thus failing to achieve the purpose of dynamically adjusting the length of the data packet.

为此,在步骤105之后,所述目的端对第二预定时间间隔t2进行监视。如果在第二预定时间间隔t2内没有收到任何响应分组Ack,则在步骤1052重新发送请求改变分组长度的请求分组Req。To this end, after step 105, the destination monitors a second predetermined time interval t2. If no response packet Ack is received within the second predetermined time interval t2, then at step 1052 the request packet Req requesting to change the packet length is resent.

源端在第一次收到请求分组Req后,从步骤106开始处理。源端第一次收到的请求分组Req可能是目的端在步骤105发送的请求分组Req,也可能是目的端在步骤1052重新发送的请求分组Req。本领域内普通技术人员容易理解到,重新发送请求分组Req的步骤可以不限于一次。After the source end receives the request packet Req for the first time, it starts processing from step 106 . The request packet Req received by the source end for the first time may be the request packet Req sent by the destination end in step 105 , or the request packet Req resent by the destination end in step 1052 . Those skilled in the art can easily understand that the step of resending the request packet Req may not be limited to one time.

步骤106与107的处理与图1中相同。The processing of steps 106 and 107 is the same as that in FIG. 1 .

如果在第一预定时间间隔t1内,源端再次收到来自目的端的请求分组Req(这种情况表明响应分组Ack丢失,且目的端已执行步骤1052),则源端在步骤1072重新发送响应分组Ack。本领域内普通技术人员容易理解到,重新发送响应分组Ack的步骤可以不限于一次。If within the first predetermined time interval t1, the source end receives the request packet Req from the destination end again (this situation shows that the response packet Ack is lost, and the destination end has executed step 1052), then the source end resends the response packet in step 1072 Ack. Those skilled in the art can easily understand that the step of resending the response packet Ack may not be limited to one time.

之后的步骤108、109、110与图1中相同。Subsequent steps 108 , 109 , 110 are the same as in FIG. 1 .

图2中要求,第一预定时间间隔t1大于第二预定时间间隔t2。这一要求既保证了目的端有足够的时间接收响应分组Ack并根据响应分组Ack的内容做相应处理(例如,为接收按新的分组长度封装的数据分组做好准备),又保证了源端在收到目的端因响应分组Ack丢失而重新发送的请求分组Req之前不会改变数据分组的长度。It is required in FIG. 2 that the first predetermined time interval t1 is greater than the second predetermined time interval t2. This requirement not only ensures that the destination has enough time to receive the response packet Ack and do corresponding processing according to the content of the response packet Ack (for example, to prepare for receiving the data packet encapsulated according to the new packet length), but also ensures that the source end The length of the data packet will not be changed before receiving the request packet Req resent by the destination end due to the loss of the response packet Ack.

图3是根据本发明的动态调整数据分组长度的方法在接收端的示意流程图。如图3所示,在步骤301,处理过程开始。在步骤302,设置系统参数,包括业务的服务质量要求q和其他参数。然后在步骤303判断是否收到含有时间戳信息的时间戳分组T。如果步骤303的判断结果是“是”,则处理过程进行到步骤304;否则,在步骤303等待,直到收到含有时间戳信息的时间戳分组T。Fig. 3 is a schematic flow chart at the receiving end of the method for dynamically adjusting the length of a data packet according to the present invention. As shown in FIG. 3, at step 301, the process starts. In step 302, system parameters are set, including service quality requirement q and other parameters. Then in step 303 it is judged whether a timestamp packet T containing timestamp information is received. If the judgment result of step 303 is "yes", then the process proceeds to step 304; otherwise, it waits at step 303 until receiving a timestamp packet T containing timestamp information.

在步骤304,计算时间戳分组T的传输时延t、时延抖动d。该步骤也可以包括计算预定时间段内收到的时间戳分组的平均传输时延和平均时延抖动。In step 304, the transmission delay t and delay jitter d of the timestamp packet T are calculated. This step may also include calculating an average transmission delay and an average delay jitter of time-stamped packets received within a predetermined time period.

在步骤305,根据控制策略f1(l,t,d,q),判断是否改变数据分组的长度。判断标准与图1中相同。如果步骤305的判断结果是“否”,则处理过程返回步骤303,等待接收下一个含有时间戳信息的时间戳分组T,否则处理过程进行到步骤306。In step 305, according to the control strategy f1(l, t, d, q), it is judged whether to change the length of the data packet. Judgment criteria are the same as in Figure 1. If the judgment result of step 305 is “No”, then the processing procedure returns to step 303 and waits to receive the next timestamp packet T containing timestamp information, otherwise the processing procedure proceeds to step 306 .

在步骤306,根据上述控制策略,计算新的数据分组长度lnew。In step 306, a new data packet length lnew is calculated according to the above control strategy.

在步骤307,向源端发送含有新的数据分组长度lnew的请求分组Req。In step 307, a request packet Req containing a new data packet length lnew is sent to the source.

在步骤308,判断是否收到响应分组Ack。如果步骤308的判断结果是“是”,则处理过程进行到步骤310;否则,进行到步骤309。In step 308, it is judged whether the response packet Ack is received. If the judgment result of step 308 is "Yes", then the process proceeds to step 310; otherwise, it proceeds to step 309.

在步骤309,判断是否超过预定时间段,比如图2所示的第二预定时间间隔t2。如果步骤309的判断结果是“是”,则处理过程返回到步骤307;否则返回到步骤308。In step 309, it is judged whether a predetermined period of time has elapsed, such as the second predetermined time interval t2 shown in FIG. 2 . If the judging result of step 309 is "yes", the process returns to step 307; otherwise, it returns to step 308.

在步骤310,根据响应分组Ack的内容,目的端判断源端是否接受请求,若判断结果为“否”,源端拒绝了请求,则处理过程进行到311;否则进行到步骤312。In step 310, according to the content of the response packet Ack, the destination end judges whether the source end accepts the request, if the judgment result is "no", the source end rejects the request, then the process proceeds to 311; otherwise, it proceeds to step 312.

在步骤311,目的端使数据分组长度保持不变,之后返回步骤303。In step 311 , the destination keeps the length of the data packet unchanged, and then returns to step 303 .

在步骤312,目的端将数据分组长度改变为lnew,或者确认本地接收数据分组的分组长度将从收到第一个分组长度改变标志位被置位的数据分组时刻起设定为新的数据分组长度lnew。之后,处理过程返回到步骤303。In step 312, the destination end changes the data packet length to lnew, or confirms that the packet length of the locally received data packet will be set as a new data packet from the moment of receiving the first data packet whose packet length change flag bit is set length lnew. After that, the process returns to step 303 .

图3所示的流程,尤其是步骤307至309,有效地处理了如图2所示的信令数据分组(即请求分组Req或响应分组Ack)丢失的情况。The flow shown in FIG. 3 , especially steps 307 to 309 , effectively handles the loss of the signaling data packet (ie, the request packet Req or the response packet Ack) as shown in FIG. 2 .

与图3所示的流程相应地,在源端执行相对比较简单的处理过程,即先执行图1所示的步骤101,并等待。如果收到请求改变分组长度的请求分组Req,则执行图1中的步骤106和107,以及在步骤106中决定接受改变分组长度的请求的情况下,在第一预定时间间隔t1后执行步骤109。步骤101是以频率f周期性地执行的。而步骤106和107的执行取决于目的端的请求、请求分组Req是否丢失、响应分组Ack是否丢失、是否超时等许多因素。在第一预定时间间隔t1内再次收到请求分组Req的情况下,也可以执行图2所示的步骤1072。Corresponding to the flow shown in FIG. 3 , a relatively simple processing procedure is performed at the source end, that is, step 101 shown in FIG. 1 is executed first and waits. If a request packet Req requesting to change the packet length is received, steps 106 and 107 in FIG. 1 are executed, and in case of a decision to accept the request to change the packet length in step 106, step 109 is executed after the first predetermined time interval t1 . Step 101 is performed periodically with frequency f. The execution of steps 106 and 107 depends on many factors such as the request of the destination, whether the request packet Req is lost, whether the response packet Ack is lost, or whether it times out. In the case that the request packet Req is received again within the first predetermined time interval t1, step 1072 shown in FIG. 2 may also be executed.

虽然结合附图描述了本发明的实施方式,但是本领域内熟练的技术人员可以在所附权利要求的范围内做出各种变形或修改。Although the embodiments of the present invention have been described with reference to the accompanying drawings, various variations or modifications may be made by those skilled in the art within the scope of the appended claims.

Claims (12)

1. the method for a dynamic adjusting data block length is characterized in that may further comprise the steps:
The source end sends the timestamp grouping that contains timestamp information to destination;
After destination is received described timestamp grouping, judge whether to need to change data packet length;
Change data packet length if desired, then described destination calculates new data packet length, and sends the request grouping that request changes data packet length to described source end;
Described source end is done respective handling according to the content of described request grouping to the data block length.
2. according to the method for claim 1, it is characterized in that the described step of needs change data packet length that judges whether may further comprise the steps:
Calculate described timestamp transmission packets time delay and delay variation;
At least according to QoS requirement, described propagation delay time, described delay variation, judge whether to need to change data packet length.
3. according to the method for claim 1, it is characterized in that the step that described transmission contains the timestamp grouping of timestamp information undertaken by described source end with preset frequency.
4. according to the method for claim 3, it is characterized in that the described step of needs change data packet length that judges whether may further comprise the steps:
Calculate described timestamp transmission packets time delay and delay variation;
Calculate the mean transit delay and the average delay variation of the timestamp grouping of receiving in the predetermined amount of time;
At least according to QoS requirement, described mean transit delay, the shake of described average delay, judge whether to need to change data packet length.
5. according to the method for claim 1, it is characterized in that in the described step that described new data packet length is added in the described request grouping that before described source end sends the step of request grouping that request changes data packet length, comprises.
6. according to the method for claim 1, it is characterized in that the described step that the data block length is done respective handling may further comprise the steps:
At least according to former data packet length, described new data packet length, judge whether to accept the described request grouping;
If accept the described request grouping, then send and accept the described request response packet to described destination; And
Behind first predetermined time interval, the data packet length that this locality sends is set to described new data packet length.
7. according to the method for claim 6, it is characterized in that further comprising the steps of:
Described destination receive described accept described request response packet grouping after, the length of the legal packet of local reception is set to described new data packet length.
8. according to the method for claim 6, it is characterized in that further comprising the steps of:
In second predetermined time interval of described destination after the request that the request that sends to described source end changes data packet length is divided into groups, monitor whether receive the described respond packet of sending from described source end; And
Do not receive under the situation of described respond packet that in described second predetermined time interval described destination resends the request grouping that described request changes data packet length to described source end.
9. method according to Claim 8 is characterized in that described first predetermined time interval is greater than described second predetermined time interval.
10. according to the method for claim 1, it is characterized in that the described step that the data block length is done respective handling may further comprise the steps:
At least according to former data packet length, described new data packet length, judge whether to accept the described request grouping;
If the rejecting said request grouping then sends the grouping of rejecting said request response packet to described destination.
11., it is characterized in that further comprising the steps of according to the method for claim 10:
Described destination remains unchanged the length of the packet of local reception after receiving described rejecting said request response packet grouping.
12., it is characterized in that further comprising the steps of according to the method for claim 10:
In second predetermined time interval of described destination after the request that the request that sends to described source end changes data packet length is divided into groups, monitor whether receive the described respond packet of sending from described source end; And
Do not receive under the situation of described respond packet that in described second predetermined time interval described destination resends the request grouping that described request changes data packet length to described source end.
CNB2003101094296A 2003-12-15 2003-12-15 A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service Expired - Lifetime CN100391195C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNB2003101094296A CN100391195C (en) 2003-12-15 2003-12-15 A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNB2003101094296A CN100391195C (en) 2003-12-15 2003-12-15 A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service

Publications (2)

Publication Number Publication Date
CN1630270A CN1630270A (en) 2005-06-22
CN100391195C true CN100391195C (en) 2008-05-28

Family

ID=34843056

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB2003101094296A Expired - Lifetime CN100391195C (en) 2003-12-15 2003-12-15 A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service

Country Status (1)

Country Link
CN (1) CN100391195C (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100388693C (en) * 2005-12-28 2008-05-14 华为技术有限公司 Method and system for monitoring service quality according to service level agreement
CN100442730C (en) * 2007-05-11 2008-12-10 北京邮电大学 Measuring Method of Network Link Bandwidth Based on Hop-by-Hop Timestamp Label
CN101471873A (en) * 2007-12-29 2009-07-01 华为技术有限公司 Method, equipment and system for controlling medium transmission packet size
CN101789852B (en) * 2010-01-12 2012-12-26 浙江大学 Method for dynamic control of data packet length in wireless sensor network
CN102801690B (en) * 2011-05-25 2015-09-30 华为技术有限公司 The processing method of Streaming Media, Distributor, client and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10126430A (en) * 1996-10-18 1998-05-15 Toshiba Corp Cable network system
EP1225736A2 (en) * 2001-01-18 2002-07-24 Texas Instruments Incorporated Adaptive fragmentation for wireless network communications
CN1398094A (en) * 2001-07-12 2003-02-19 Lg电子株式会社 Data communication method
WO2003015355A2 (en) * 2001-08-06 2003-02-20 Koninklijke Philips Electronics N.V. Method for supporting non-linear, highly scalable increase-decrease congestion control scheme
US20030076850A1 (en) * 2001-10-22 2003-04-24 Jason James L. Determining packet size in networking

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10126430A (en) * 1996-10-18 1998-05-15 Toshiba Corp Cable network system
EP1225736A2 (en) * 2001-01-18 2002-07-24 Texas Instruments Incorporated Adaptive fragmentation for wireless network communications
CN1398094A (en) * 2001-07-12 2003-02-19 Lg电子株式会社 Data communication method
WO2003015355A2 (en) * 2001-08-06 2003-02-20 Koninklijke Philips Electronics N.V. Method for supporting non-linear, highly scalable increase-decrease congestion control scheme
US20030076850A1 (en) * 2001-10-22 2003-04-24 Jason James L. Determining packet size in networking

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Adaptive Frame Length Control for Improving Wireless LinkThroughput,Range, and Energy Efficiency. Paul Lettieri and Mani B.Srivastava.IEEE. 1998 *

Also Published As

Publication number Publication date
CN1630270A (en) 2005-06-22

Similar Documents

Publication Publication Date Title
CN101803316B (en) Methods, systems and apparatus for adaptive congestion control on virtual lanes for data center Ethernet architectures
CN101558612B (en) Controlling congestion detection in hsdpa systems
US9729459B2 (en) System and method for credit-based link level flow control
EP3758409A1 (en) Data traffic processing method and related network device
CN116527584B (en) Congestion control method and device, communication network, and computer storage medium
KR20130023094A (en) Dynamic bandwidth re-allocation
JP2007506364A (en) How to empirically schedule network packets
CN112822268B (en) A method for multi-service coexistence and IP layer data packet scheduling in the Industrial Internet of Things
US7983297B2 (en) Method and apparatus for the efficient use of available communications network bandwidth
JP2004304806A (en) Method for flow control in a communication system
WO2006086691A2 (en) A network for providing a streaming service
CN116260773A (en) A congestion control method and related equipment
CN100391195C (en) A Method of Dynamically Adjusting Data Packet Length Based on Network Quality of Service
CN114979011A (en) Congestion control method applied to park network
US7321557B1 (en) Dynamic latency assignment methodology for bandwidth optimization of packet flows
CN100473047C (en) A transmission control method for asynchronous transfer mode adaptation layer 2
EP1341350B1 (en) A method for congestion detection for IP flows over a wireless network
CN113273149B (en) Data sending method and device and FlexE exchange system
US7088738B1 (en) Dynamic fragmentation of information
KR100440575B1 (en) The traffic characterization scheme for realtime video transmission
TWI817905B (en) Downlink bandwidth control method and associated network device
KR100585932B1 (en) Real-time dynamic variable bit rate transmission device and method
CN114157727B (en) Application method and device of TCP acceleration in OSU
Engan et al. Selective truncating internetwork protocol: experiments with explicit framing
Peng et al. Fast backward congestion notification mechanism for TCP congestion control

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C56 Change in the name or address of the patentee

Owner name: SHANGHAI ALCATEL-LUCENT CO., LTD.

Free format text: FORMER NAME: BEIER AERKATE CO., LTD., SHANGHAI

CP01 Change in the name or title of a patent holder

Address after: 201206 Pudong Jinqiao Export Processing Zone, Nanjing Road, No. 388, Shanghai

Patentee after: ALCATEL-LUCENT SHANGHAI BELL Co.,Ltd.

Address before: 201206 Pudong Jinqiao Export Processing Zone, Nanjing Road, No. 388, Shanghai

Patentee before: Shanghai Bell Alcatel Co.,Ltd.

CP01 Change in the name or title of a patent holder

Address after: 201206 Pudong Jinqiao Export Processing Zone, Nanjing Road, No. 388, Shanghai

Patentee after: NOKIA SHANGHAI BELL Co.,Ltd.

Address before: 201206 Pudong Jinqiao Export Processing Zone, Nanjing Road, No. 388, Shanghai

Patentee before: ALCATEL-LUCENT SHANGHAI BELL Co.,Ltd.

CP01 Change in the name or title of a patent holder
CX01 Expiry of patent term

Granted publication date: 20080528

CX01 Expiry of patent term