WO2023109445A1 - 一种基于时间触发以太网的业务调度方法 - Google Patents

一种基于时间触发以太网的业务调度方法 Download PDF

Info

Publication number
WO2023109445A1
WO2023109445A1 PCT/CN2022/133710 CN2022133710W WO2023109445A1 WO 2023109445 A1 WO2023109445 A1 WO 2023109445A1 CN 2022133710 W CN2022133710 W CN 2022133710W WO 2023109445 A1 WO2023109445 A1 WO 2023109445A1
Authority
WO
WIPO (PCT)
Prior art keywords
cycle
matrix
node
nodes
time
Prior art date
Application number
PCT/CN2022/133710
Other languages
English (en)
French (fr)
Inventor
刘晓宇
马国轩
刘传鹏
吕文强
和延
Original Assignee
陕西电器研究所
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 陕西电器研究所 filed Critical 陕西电器研究所
Priority to JP2023564029A priority Critical patent/JP2024516965A/ja
Publication of WO2023109445A1 publication Critical patent/WO2023109445A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/02Topology update or discovery
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/12Shortest path evaluation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/302Route determination based on requested QoS
    • H04L45/306Route determination based on the nature of the carried application
    • H04L45/3065Route determination based on the nature of the carried application for real time traffic
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling

Definitions

  • the invention belongs to the technical field of computer network communication, and in particular relates to a time-triggered Ethernet service scheduling method.
  • TTE Time Trigger Ethernet
  • TT time-triggered services
  • RC rate-limited services
  • BE ordinary Ethernet services
  • the TT service has the most stringent requirements on time determinism among all services, and has the highest priority.
  • the transmission of TT business is based on the global clock, and the business must be sent and received in strict accordance with the time schedule in the predetermined time period, so as to ensure its high real-time and low delay jitter requirements, and avoid competition between data frames for limited physical links in the network road.
  • the purpose of the present invention is to provide a time-triggered Ethernet-based service scheduling method, which can be used to realize the control of sending and receiving of TT services.
  • a service scheduling method based on time-triggered Ethernet comprising the steps of:
  • Step 1 Obtain parameters of all time-triggered services to be sent and received
  • Step 2 According to the business to be sent and received, calculate the required number of end nodes ES and switches SW to obtain the minimum system;
  • Step 3 according to the minimum system determined in step 2, establish the topology structure of the system, wherein, both the end node ES and the switch SW are called the connection nodes of the system, and the connection nodes are sequentially numbered;
  • Step 4 according to the topology of the system established in 3, the connection relationship matrix between the connection nodes, including the connection matrix of the connection port of the switch SW and other switches SW or end nodes ES;
  • Step 5 According to the topological structure and connection matrix of connected nodes in 3 and 4, set the distance length between two directly connected nodes to 1, the connection distance length of the same node to 0, and set the distance length between nodes not directly connected to Infinity, represented by X; calculate the shortest transmission path between any two nodes, including the total distance of the shortest transmission path and the number of intermediate connection nodes;
  • Step 6 obtaining network parameters
  • Step 7 Calculate the basic cycle BC and matrix cycle MC: Calculate the basic cycle BC and matrix cycle MC according to the service flow parameters in 1, where the matrix cycle MC contains multiple basic cycle BCs, which are used to send all services in one pass ;
  • Step 8 According to the cycle of the business, each business is allocated to each basic cycle BC in a matrix cycle MC, and a business allocation table in a matrix cycle MC is established;
  • Step 9 For all the services allocated in each basic period BC, group them according to the different generation times of the services, sort the services in each group according to the priority, traverse each basic period BC in a matrix period MC, and divide the business Sorting is done according to priority;
  • Step 10 For the business in a matrix cycle MC, according to the source number and destination number of the business, use the shortest transmission path in step 5 to determine the sending and receiving path, and then determine the sending and receiving time according to the priority of the business and the sending and receiving path, and finally form The overall schedule within a matrix cycle MC;
  • Step 11 identify each connection node according to the overall schedule in step 10, obtain the sending and receiving schedule of each connection node, and generate a schedule file;
  • Step 12 According to the schedule file in step 11, send and receive services are scheduled.
  • step 8 after all services are allocated to each basic cycle BC, services with the same cycle are allocated to different basic cycles in an interleaved manner to obtain a service allocation table.
  • a shortest transmission path table is finally established, and the specific method is:
  • the first intermediate node z between the connection node x and the connection node y it is located in the xth row, the yth column; the second intermediate node t is located in the zth row, the yth column, in the tth row, the yth column, so that By analogy, until the last intermediate node; the two connected nodes are traversed to obtain the shortest transmission path table; among them,
  • each switch SW includes 4 full-duplex ports.
  • the two switches SW are directly connected, and the systems ES at both ends need to be connected through the switch SW.
  • the parameters of the time-triggered service include the ID number, frame length, period, source-end system number, destination-end system number and service generation time point of each service.
  • the invention discloses a service scheduling method based on time-triggered Ethernet, which calculates the number of end systems and switches according to service flow parameters, determines the topology, establishes a port connection matrix, and plans the shortest path; Allocation, sorting the services in each basic cycle, establishing an overall scheduling table in a matrix cycle, and then generating a business scheduling table for each end node and switch.
  • the invention realizes the scheduling of TT services, so that each end node and switch can transmit TT tasks orderly and without conflict; meanwhile, the network bandwidth is saved, and the utilization rate of network links is improved.
  • Fig. 1 is the realization flowchart of the present invention
  • Fig. 2 is a network topology diagram in a specific embodiment of the present invention.
  • Obtain service flow parameters obtain all time-triggered (TT) services to be sent and received, the ID number, frame length, period, source system number, destination system number, and service generation time point of each service, as shown in Table 1 Show.
  • Business ID frame length period(ms) source Destination generation time 1 64 1 1 2 0 2 1518 1 1 3 1 3 678 3 1 5 0 4 722 2 1 7 1 5 1168 2 3 8 1 6 120 2 4 5 0 7 865 3 2 6 0 8 147 4 2 8 0 9 530 1 5 7 0 10 654 2 6 3 0 11 30 3 7 1 0 12 48 1 7 4 0 13 600 1 8 2 0
  • each switch SW contains 4 full-duplex ports, two switches SW can be directly connected, and the two systems ES need to be connected through a switch SW.
  • step 2 establish a topology structure.
  • both the end system ES and the switch SW are called the connection nodes of the system, and the connection nodes are sequentially numbered, and the number 1-8 represents the end Nodes ES1-ES8, numbered 9-13 correspond to switches SW1-SW5.
  • Connection node number Connection node number Port number of switch SW 9 10 1 9 11 2 9 12 3 9 13 4 10 1 1 10 2 3
  • Connection node number Connection node number Port number of switch SW 10 9 4 10 11 2 11 7 4 11 8 2 11 9 3 11 10 1 12 3 1 12 4 3 12 9 2 13 5 4 13 6 2 13 9 1
  • the matrix has three columns, the first column and the second column represent the connection nodes, and the third column represents the SW port numbers connected to the two connection nodes.
  • the two interconnected connection nodes are 9 and 10, and the port number is 1, indicating that node 9 is connected to node 10 through its own port 1.
  • Planning the shortest path According to the topological structure and node connection matrix in 3 and 4, establish a distance matrix. Between every two nodes, the distance between two directly connected nodes is set to 1, and the connection distance of the same node is 0, the distance between nodes that are not directly connected is set to infinity, represented by X, as shown in Table 3.
  • the first column in the first row indicates that the distance between node 1 and itself is 0; the second column in the first row indicates that the distance between node 1 and node 2 is infinite, that is, they are not directly connected; the tenth column in the first row indicates that node 1 and node 10 The distance is 1.
  • the distance matrix calculate the shortest transmission path between any two nodes, including the total distance and intermediate node numbers, as shown in Table 4 and Table 5, respectively.
  • the seventh column in the first row indicates that the total transmission distance from node 1 to node 7 is 3.
  • Calculation of basic cycle BC and matrix cycle MC Calculate the basic cycle BC and matrix cycle MC according to the service flow parameters in 1.
  • the matrix cycle MC contains multiple basic cycle BCs, and all services are sent once.
  • the basic cycle BC takes the greatest common divisor of each business cycle MC 1ms, and the matrix cycle MC takes the least common multiple of each business cycle 12ms.
  • Table 6 TT service allocation table within a matrix cycle MC
  • Allocation table processing in each BC process the TT services allocated in each basic period, group them according to different generation times of TT services, and prioritize the services of each group according to the amount of sending and receiving of ports.
  • the first BC is processed, as shown in Table 7 before processing, and as shown in Table 8 after processing.
  • Establish an overall scheduling table in a matrix cycle MC perform the same processing on each basic cycle BC in 9, until all the basic cycle BC business processing in a matrix cycle MC is completed.
  • time scheduling is performed on the TT business processed in a matrix cycle MC.
  • the shortest transmission path table is used to determine the sending and receiving path, and the sending and receiving path is determined according to the priority of the business and the sending and receiving path. time, finally forming an overall schedule within a matrix cycle MC.
  • the first column is the ID number
  • the second column is the basic cycle number
  • the third to sixth columns represent the source node sending, which are the source node number, start sending time, end sending time, and window length
  • Node sending, every 4 columns are a group, respectively represent the intermediate node number, start receiving/sending time point, complete receiving/sending time point, window length
  • the last four columns represent destination node reception, respectively, destination node number, start receiving node , complete receiving node, window length.
  • Generating the dispatch table of each node According to the overall dispatch table in 10, identify each node, obtain the sending and receiving dispatch table of each node, and generate the dispatch table file.
  • the sending table of source system 1, the receiving table of switch 2, the sending table of switch 3, and the receiving table of destination system 4 are shown in Table 9-12 respectively.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种基于时间触发以太网的业务调度方法,该方法包括:根据业务流参数,计算端系统和交换机数量,确定拓扑结构,建立端口连接矩阵,规划最短路径;对每个矩阵周期内的业务进行分配,对每个基本周期内的业务进行排序,建立一个矩阵周期内的整体调度表,进而生成各个端节点和交换机的业务调度表。实现了对TT业务的调度,使得各个端节点和交换机能够有序、无冲突地传输TT任务;同时节省了网络带宽,提高了网络链路利用率。

Description

一种基于时间触发以太网的业务调度方法 技术领域
本发明属于计算机网络通信技术领域,具体涉及一种基于时间触发以太网的业务调度方法。
背景技术
随着航空航天事业的发展,航空电子系统对高带宽、高可靠性、低延时和强容错性等方面的需求越来越大。经过长时间的研究与发展,TTE(Time Trigger Ethernet)应运而生。该技术在以太网的基础上增加了时间同步技术和时间触发技术,能够处理对实时性要求很高的时间触发业务(TT),也能处理速率受限业务(RC)和普通以太网业务(BE),即能够同时满足实时应用和非实时应用的需求。
其中,TT业务在所有业务中对时间确定性要求最为严格,具有最高的优先级。TT业务的传输基于全局时钟,须严格按照时间调度表在预定的时间段进行业务收发,从而保证其高实时性和低时延抖动的要求,避免数据帧之间互相竞争网络中有限的物理链路。
发明内容
有鉴于此,本发明的目的是提供一种基于时间触发以太网的业务调度方法,可以用以实现对TT业务的收发控制。
一种基于时间触发以太网的业务调度方法,包括如下步骤:
步骤1、获取待收发的所有的时间触发业务的参数;
步骤2、根据待收发的业务,计算所需端节点ES和交换机SW数量,获得最小的系统;
步骤3、根据步骤2确定的最小系统,建立系统的拓扑结构,其中,将端节点ES和交换机SW均称为系统的连接节点,并对连接节点进行顺序编号;
步骤4、根据3建立的系统的拓扑结构,连接节点之间的连接关系矩阵,其中包括交换机SW的连接端口与其它交换机SW或者端节点ES的连接矩阵;
步骤5、根据3和4中的拓扑结构和连接节点连接矩阵,将直接相连的两个节点间距离长度设置为1,同一节点的连接距离长度为0,不直接相连的节点间距离长度设置为无穷大,用X表示;计算任意两个节点之间的最短传输路径,包括最短传输路径总距离和中间连接节点编号;
步骤6、获取网络参数;
步骤7、计算基本周期BC和矩阵周期MC:根据1中的业务流参数,计算得到基本周期BC和矩阵周期MC,其中矩阵周期MC内包含多个基本周期BC,用于将所有业务完成一遍发送;
步骤8、根据业务的周期,在一个矩阵周期MC内将各业务分配到各个基本周期BC内,建立一个矩阵周期MC内的业务分配表;
步骤9、对于每个基本周期BC内分配的所有业务,按照业务的不同产生时刻进行分组,对每组内的业务根据优先级进行排序,遍历一个矩阵周期MC内的各个基本周期BC,将业务按照优先级完成排序;
步骤10、对一个矩阵周期MC内的业务,根据业务的源端编号和目的端编号,利用步骤5的最短传输路径确定收发路径,再根据业务的优先级和收发路径,确定收发时间,最终形成一个矩阵周期MC内的整体调度表;
步骤11、根据步骤10中的整体调度表,识别各个连接节点,得到每个连接节点的收发调度表,生成调度表文件;
步骤12、根据步骤11的调度表文件,对业务进行收发调度。
较佳的,所述步骤8中,将各业务分配到各个基本周期BC后,将周期相同的业务交错分配到不同的基本周期中,得到业务分配表。
较佳的,所述步骤5中,最后建立一个最短传输路径表,具体方法为:
将所有连接节点编号分别按行和列进行顺序排列;
对于连接节点x和连接节点y之间的第一个中间节点z,位于第x行第y列;第二个中间节点t位于第z行第y列,位于第t行第y列,以此类推,直到最后一个中间节点;两两连接节点进行遍历,得到最短传输路径表;其中,
较佳的,每个交换机SW包含4个全双工端口。
较佳的,两交换机SW之间直接相连,两端系统ES之间需要通过交换机SW相连。
较佳的,所述时间触发业务的参数包括每条业务的ID编号、帧长、周期、源端系统编号、目的端系统编号以及业务产生时间点。
本发明具有如下有益效果:
本发明公开了一种基于时间触发以太网的业务调度方法,根据业务流参数,计算端系统和交换机数量,确定拓扑结构,建立端口连接矩阵,规划最短路径;对每个矩阵周期内的业务进行分配,对每个基本周期内的业务进行排序,建立一个矩阵周期内的整体调度表,进而生成各个端节点和交换机的业务调度表。本发明实现了对TT业务的调度,使得各个端节点和交换机能够有序、无冲突地传输TT任务;同时节省的网络带宽,提高网络链路利用率。
附图说明
图1是本发明的实现流程图;
图2是本发明具体实施方案中的网络拓扑图。
具体实施方式
下面结合附图并举实施例,对本发明进行详细描述。
1、获取业务流参数:获取待收发的所有时间触发(TT)业务,每条业务的ID编号、帧长、周期、源端系统编号、目的端系统编号、业务产生时间点,如表1所示。
表1 业务流参数
业务ID 帧长 周期(ms) 源端 目的端 产生时间
1 64 1 1 2 0
2 1518 1 1 3 1
3 678 3 1 5 0
4 722 2 1 7 1
5 1168 2 3 8 1
6 120 2 4 5 0
7 865 3 2 6 0
8 147 4 2 8 0
9 530 1 5 7 0
10 654 2 6 3 0
11 30 3 7 1 0
12 48 1 7 4 0
13 600 1 8 2 0
2、计算所需端系统ES和交换机SW数量:每个交换机SW包含4个全双工端口,两交换机SW之间可以直接相连,两端系统ES之间需要通过交换机SW相连。
业务流中包含的端系统数量为8,则系统中所需的ES数量最少为8,所需的SW数量最少为m=8/2-1=5,即得到最小的系统,包含8个端节点和5个交换机。
3、根据步骤2确定的最小系统,建立拓扑结构,如图2所示,将端系统ES和交换机SW均称为系统的连接节点,并对连接节点进行顺序编号,其中编号1-8表示端节点ES1-ES8,编号为9-13对应交换机SW1-SW5。
4、建立端口连接矩阵:根据3中的拓扑结构,建立端口矩阵,如表2所示。
表2 端口连接表
连接节点编号 连接节点编号 交换机SW的端口号
9 10 1
9 11 2
9 12 3
9 13 4
10 1 1
10 2 3
连接节点编号 连接节点编号 交换机SW的端口号
10 9 4
10 11 2
11 7 4
11 8 2
11 9 3
11 10 1
12 3 1
12 4 3
12 9 2
13 5 4
13 6 2
13 9 1
矩阵为三列,第一列和第二列表示连接节点,第三列表示两个连接节点相连的SW端口号。比如第一行中,两个互相连接的连接节点为9和10,端口号为1,表示节点9通过自身的端口1与节点10连接。
5、规划最短路径:根据3和4中的拓扑结构和节点连接矩阵,建立距离矩阵,每两个节点之间,直接相连的两个节点间距离长度设置为1,同一节点的连接距离长度为0,不直接相连的节点间距离长度设置为无穷大,用X表示,如表3所示。
表3 连接距离表
节点编号 1 2 3 4 5 6 7 8 9 10 11 12 13
1 0 X X X X X X X X 1 X X X
2 X 0 X X X X X X X 1 X X X
3 X X 0 X X X X X X X X 1 X
4 X X X 0 X X X X X X X 1 X
5 X X X X 0 X X X X X X X 1
6 X X X X X 0 X X X X X X 1
7 X X X X X X 0 X X X 1 X X
8 X X X X X X X 0 X X 1 X X
9 X X X X X X X X 0 1 1 1 1
10 1 1 X X X X X X 1 0 1 X X
11 X X X X X X 1 1 1 1 0 X X
12 X X 1 1 X X X X 1 X X 0 X
13 X X X X 1 1 X X 1 X X X 0
如第一行第一列表示节点1与自身的距离为0;第一行第二列表示节点1与节点2距离为无穷大,即未直接连接;第一行第十列表示节点1与节点10的距离为1。
根据该距离矩阵,计算任意两个节点之间的最短传输路径,包括总距离和中间节点编号,分别如表4和表5所示。
表4 传输距离表
Figure PCTCN2022133710-appb-000001
Figure PCTCN2022133710-appb-000002
比如其中第一行第七列表示从节点1到节点7的传输总距离为3。
表5 最短传输路径表
  1 2 3 4 5 6 7 8 9 10 11 12 13
1 1 10 10 10 10 10 10 10 10 10 10 10 10
2 10 2 10 10 10 10 10 10 10 10 10 10 10
3 12 12 3 12 12 12 12 12 12 12 12 12 12
4 12 12 12 4 12 12 12 12 12 12 12 12 12
5 13 13 13 13 5 13 13 13 13 13 13 13 13
6 13 13 13 13 13 6 13 13 13 13 13 13 13
7 11 11 11 11 11 11 7 11 11 11 11 11 11
8 11 11 11 11 11 11 11 8 11 11 11 11 11
9 10 10 12 12 13 13 11 11 9 10 11 12 13
10 1 2 9 9 9 9 11 11 9 10 11 9 9
11 10 10 9 9 9 9 7 8 9 10 11 9 9
12 9 9 3 4 9 9 9 9 9 9 9 12 9
13 9 9 9 9 5 6 9 9 9 9 9 9 13
比如想要查看节点1到节点7的传输路径,首先看第一行第七列为10,表示第一步从节点1传输到节点10;然后看第十行第七列为11,表示第二步从节点10传输到节点11,;然后看第十一行第七列为7,则表示第三步从节点11传输到节点7。即经过三步实现从节点1到节点7的传输。
6、获取网络参数:包括链路带宽(100Mbps)、同步精度(200ns)、端系统与交换机之间的时延(100ns)、端节点自身时延(20ns)、交换机自身时延(20ns)等。
7、计算基本周期BC和矩阵周期MC:根据1中的业务流参数,计算得到基本周期BC和矩阵周期MC,其中矩阵周期MC内包含多个基本周期BC,将所有业务完成一遍发送。基本周期BC取各业务周期MC的最大公约数1ms,矩阵周期MC取各业务周期的最小公倍数12ms。
8、建立一个矩阵周期MC内的TT业务分配表:根据TT业务情况,在一个矩阵周期MC内将TT业务分配到各个基本周期BC内,再将周期相同的TT业务进行基本周期BC交错处理,得到优化的分配方案,避免TT业务的冲突,如表6所示。
表6 一个矩阵周期MC内的TT业务分配表
Figure PCTCN2022133710-appb-000003
Figure PCTCN2022133710-appb-000004
9、每个BC内分配表处理:对每个基本周期内分配的TT业务进行处理,根据TT业务的不同产生时刻进行分组,根据端口的收发量对每一组的业务进行优先级处理,先对第一个BC进行处理,处理前如表7所示,处理后如表8所示。
表7 处理前
ID 1 3 6 8 9 12 13 2 4
产生时间 0 0 0 0 0 0 0 1 1
表8 处理后
ID 12 9 8 1 13 3 6 2 4
产生时间 0 0 0 0 0 0 0 1 1
10、建立一个矩阵周期MC内的整体调度表:对9中的每个基本周期BC进行相同处理,直到一个矩阵周期MC内所有的基本周期BC业务处理完成。接下来对一个矩阵周期MC内处理好的TT业务进行时间调度安排,根据业务的源端编号和目的端编号,利用最短传输路径表确定收发路径,在根据业务的优先级和收发路径,确定收发时间,最终形成一个矩阵周期MC内的整体调度表。
其中第1列为ID号,第2列为基本周期编号;第3到6列表示源节点发送,分别为源节点编号、开始发送时间、结束发送时间、窗口长度;之后为中间节点接收、中间节点发送,每4列为一组,分别表示中间节点编号、开始接收/发送时间点、完成接收/发送时间点、窗口长度;最后四列表示目的节点接收,分别为目的节点编号、开始接收节点、完成接收节点、窗口长度。
11、生成各个节点的调度表:根据10中的整体调度表,识别各个节点,得到每个节点的收发调度表,生成调度表文件。
其中源端系统1发送表、交换机2接收表、交换机3发送表、目的端系统4接收表分别如表9-12所示。
表9 源端系统1发送表
帧号 基本周期号 开始发送时间点 结束发送时间点 发送窗口长度
1 1 0 2 1
3 1 3 17 1
2 1 19 50 1
4 1 52 67 1
1 2 2568 2570 1
帧号 基本周期号 开始发送时间点 结束发送时间点 发送窗口长度
2 2 5072 5103 1
1 3 10104 10106 1
2 3 15108 15139 1
4 3 20141 20156 1
3 4 27657 27671 1
1 4 35172 35174 1
2 4 42676 42707 1
1 5 52708 52710 1
2 5 62712 62743 1
4 5 72745 72760 1
1 6 85261 85263 1
2 6 97765 97796 1
1 7 112797 112799 1
3 7 127800 127814 1
2 7 142816 142847 1
4 7 157849 157864 1
1 8 175365 175367 1
2 8 192869 192900 1
1 9 212901 212903 1
2 9 232905 232936 1
4 9 252938 252953 1
3 10 275454 275468 1
1 10 297969 297971 1
2 10 320473 320504 1
1 11 345505 345507 1
2 11 370509 370540 1
4 11 395542 395557 1
1 12 423058 423060 1
2 12 450562 450593 1
表10 交换机2接收表
帧号 基本周期号 开始接收时间点 结束接收时间点 上一节点 该节点 窗口长度
1 1 4 6 1 10 2
3 1 7 21 1 10 2
2 1 23 54 1 10 2
4 1 56 71 1 10 2
1 2 2572 2574 1 10 2
2 2 5076 5107 1 10 2
1 3 10108 10110 1 10 2
2 3 15112 15143 1 10 2
4 3 20145 20160 1 10 2
3 4 27661 27675 1 10 2
1 4 35176 35178 1 10 2
2 4 42680 42711 1 10 2
1 5 52712 52714 1 10 2
2 5 62716 62747 1 10 2
4 5 72749 72764 1 10 2
1 6 85265 85267 1 10 2
2 6 97769 97800 1 10 2
1 7 112801 112803 1 10 2
帧号 基本周期号 开始接收时间点 结束接收时间点 上一节点 该节点 窗口长度
3 7 127804 127818 1 10 2
2 7 142820 142851 1 10 2
4 7 157853 157868 1 10 2
1 8 175369 175371 1 10 2
2 8 192873 192904 1 10 2
1 9 212905 212907 1 10 2
2 9 232909 232940 1 10 2
4 9 252942 252957 1 10 2
3 10 275458 275472 1 10 2
1 10 297973 297975 1 10 2
2 10 320477 320508 1 10 2
1 11 345509 345511 1 10 2
2 11 370513 370544 1 10 2
4 11 395546 395561 1 10 2
1 12 423062 423064 1 10 2
2 12 450566 450597 1 10 2
8 1 4 8 2 10 2
7 2 2509 2527 2 10 2
7 5 12528 12546 2 10 2
8 5 22547 22551 2 10 2
7 8 40052 40070 2 10 2
8 9 60071 60075 2 10 2
7 11 85076 85094 2 10 2
11 3 7515 7516 11 10 2
11 6 42526 42527 11 10 2
11 9 107537 107538 11 10 2
11 12 202548 202549 11 10 2
13 1 9 22 11 10 2
13 2 2523 2536 11 10 2
13 3 7537 7550 11 10 2
13 4 15051 15064 11 10 2
13 5 25065 25078 11 10 2
13 6 37579 37592 11 10 2
13 7 52593 52606 11 10 2
13 8 70107 70120 11 10 2
13 9 90121 90134 11 10 2
13 10 112635 112648 11 10 2
13 11 137649 137662 11 10 2
13 12 165163 165176 11 10 2
表11 交换机3发送表
帧号 基本周期号 开始发送时间点 结束发送时间点 该节点 下一节点 发送窗口长度
4 1 62 77 11 7 1
4 3 20151 20166 11 7 1
4 5 72755 72770 11 7 1
4 7 157859 157874 11 7 1
4 9 252948 252963 11 7 1
4 11 395552 395567 11 7 1
8 1 10 14 11 8 1
8 5 22553 22557 11 8 1
8 9 60077 60081 11 8 1
帧号 基本周期号 开始发送时间点 结束发送时间点 该节点 下一节点 发送窗口长度
5 2 2516 2540 11 8 1
5 4 10042 10066 11 8 1
5 6 22568 22592 11 8 1
5 8 40094 40118 11 8 1
5 10 62620 62644 11 8 1
5 12 90146 90170 11 8 1
9 1 15 26 11 7 1
9 2 2527 2538 11 7 1
9 3 7539 7550 11 7 1
9 4 15051 15062 11 7 1
9 5 25063 25074 11 7 1
9 6 37575 37586 11 7 1
9 7 52587 52598 11 7 1
9 8 70099 70110 11 7 1
9 9 90111 90122 11 7 1
9 10 112623 112634 11 7 1
9 11 137635 137646 11 7 1
9 12 165147 165158 11 7 1
12 1 5 7 11 9 1
12 2 2508 2510 11 9 1
11 3 7511 7512 11 10 1
12 3 12513 12515 11 9 1
12 4 20016 20018 11 9 1
12 5 30019 30021 11 9 1
11 6 42522 42523 11 10 1
12 6 55024 55026 11 9 1
12 7 70027 70029 11 9 1
12 8 87530 87532 11 9 1
11 9 107533 107534 11 10 1
12 9 127535 127537 11 9 1
12 10 150038 150040 11 9 1
12 11 175041 175043 11 9 1
11 12 202544 202545 11 10 1
12 12 230046 230048 11 9 1
13 1 5 18 11 10 1
13 2 2519 2532 11 10 1
13 3 7533 7546 11 10 1
13 4 15047 15060 11 10 1
13 5 25061 25074 11 10 1
13 6 37575 37588 11 10 1
13 7 52589 52602 11 10 1
13 8 70103 70116 11 10 1
13 9 90117 90130 11 10 1
13 10 112631 112644 11 10 1
13 11 137645 137658 11 10 1
13 12 165159 165172 11 10 1
表12 目的端系统4接收表
Figure PCTCN2022133710-appb-000005
Figure PCTCN2022133710-appb-000006
综上所述,以上仅为本发明的较佳实施例而已,并非用于限定本发明的保护范围。凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。

Claims (6)

  1. 一种基于时间触发以太网的业务调度方法,其特征在于,包括如下步骤:
    步骤1、获取待收发的所有的时间触发业务的参数;
    步骤2、根据待收发的业务,计算所需端节点ES和交换机SW数量,获得最小的系统;
    步骤3、根据步骤2确定的最小系统,建立系统的拓扑结构,其中,将端节点ES和交换机SW均称为系统的连接节点,并对连接节点进行顺序编号;
    步骤4、根据3建立的系统的拓扑结构,连接节点之间的连接关系矩阵,其中包括交换机SW的连接端口与其它交换机SW或者端节点ES的连接矩阵;
    步骤5、根据3和4中的拓扑结构和连接节点连接矩阵,将直接相连的两个节点间距离长度设置为1,同一节点的连接距离长度为0,不直接相连的节点间距离长度设置为无穷大,用X表示;计算任意两个节点之间的最短传输路径,包括最短传输路径总距离和中间连接节点编号;
    步骤6、获取网络参数;
    步骤7、计算基本周期BC和矩阵周期MC:根据1中的业务流参数,计算得到基本周期BC和矩阵周期MC,其中矩阵周期MC内包含多个基本周期BC,用于将所有业务完成一遍发送;
    步骤8、根据业务的周期,在一个矩阵周期MC内将各业务分配到各个基本周期BC内,建立一个矩阵周期MC内的业务分配表;
    步骤9、对于每个基本周期BC内分配的所有业务,按照业务的不同产生时刻进行分组,对每组内的业务根据优先级进行排序,遍历一个矩阵周期MC内的各个基本周期BC,将业务按照优先级完成排序;
    步骤10、对一个矩阵周期MC内的业务,根据业务的源端编号和目的端编号,利用步骤5的最短传输路径确定收发路径,再根据业务的优先级和收发路径,确定收发时间,最终形成一个矩阵周期MC内的整体调度表;
    步骤11、根据步骤10中的整体调度表,识别各个连接节点,得到每个连接节点的收发调度表,生成调度表文件;
    步骤12、根据步骤11的调度表文件,对业务进行收发调度。
  2. 如权利要求1所述的一种基于时间触发以太网的业务调度方法,其特征在于,所述步骤8中,将各业务分配到各个基本周期BC后,将周期相同的业务交错分配到不同的基本周期中,得到业务分配表。
  3. 如权利要求1所述的一种基于时间触发以太网的业务调度方法,其特征在于,所述步骤5中,最后建立一个最短传输路径表,具体方法为:
    将所有连接节点编号分别按行和列进行顺序排列;
    对于连接节点x和连接节点y之间的第一个中间节点z,位于第x行第y列;第二个中间节点t位于第z行第y列,位于第t行第y列,以此类推,直到最后一个中间节点;两两连接节点进行遍历,得到最短传输路径表;其中,
  4. 如权利要求1所述的一种基于时间触发以太网的业务调度方法,其特征在于,每个交换机SW包含4个全双工端口。
  5. 如权利要求1所述的一种基于时间触发以太网的业务调度方法,其特征在于,两交换机SW之间直接相连,两端系统ES之间需要通过交换机SW相连。
  6. 如权利要求1所述的一种基于时间触发以太网的业务调度方法,其特征在于,所述时间触发业务的参数包括每条业务的ID编号、帧长、周期、源端系统编号、目的端系统编号以及业务产生时间点。
PCT/CN2022/133710 2021-12-15 2022-11-23 一种基于时间触发以太网的业务调度方法 WO2023109445A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2023564029A JP2024516965A (ja) 2021-12-15 2022-11-23 タイムトリガイーサネットに基づくサービススケジューリング方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111536553.5A CN114374640A (zh) 2021-12-15 2021-12-15 一种基于时间触发以太网的业务调度方法
CN202111536553.5 2021-12-15

Publications (1)

Publication Number Publication Date
WO2023109445A1 true WO2023109445A1 (zh) 2023-06-22

Family

ID=81139734

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/133710 WO2023109445A1 (zh) 2021-12-15 2022-11-23 一种基于时间触发以太网的业务调度方法

Country Status (3)

Country Link
JP (1) JP2024516965A (zh)
CN (1) CN114374640A (zh)
WO (1) WO2023109445A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114374640A (zh) * 2021-12-15 2022-04-19 陕西电器研究所 一种基于时间触发以太网的业务调度方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108712224A (zh) * 2018-05-10 2018-10-26 西安电子科技大学 最小时延最大匹配的时间触发业务调度表生成方法
CN111030942A (zh) * 2019-11-05 2020-04-17 天津大学 基于响应约束的tte网络离线调度方法
CN111049611A (zh) * 2019-12-30 2020-04-21 西安电子科技大学 多矩阵周期联合调度的时间触发业务调度表生成方法
US10887244B1 (en) * 2019-08-28 2021-01-05 Honeywell International Inc. Methods, systems and apparatuses for optimizing time-triggered ethernet (TTE) network scheduling by bin allocation, demand prediction and machine learning
CN114374640A (zh) * 2021-12-15 2022-04-19 陕西电器研究所 一种基于时间触发以太网的业务调度方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107241179B (zh) * 2017-04-19 2020-07-03 西安电子科技大学 一种时间触发业务静态调度表的生成方法
CN108768865B (zh) * 2018-05-24 2020-11-03 西安电子科技大学 支持多播业务的时间触发业务调度表生成方法
CN109743144A (zh) * 2018-12-14 2019-05-10 西安电子科技大学 基于时间触发以太网的静态调度表生成方法、航电系统
CN110545206B (zh) * 2019-09-10 2021-02-02 清华大学 一种时间触发网络中调度表生成的方法、装置及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108712224A (zh) * 2018-05-10 2018-10-26 西安电子科技大学 最小时延最大匹配的时间触发业务调度表生成方法
US10887244B1 (en) * 2019-08-28 2021-01-05 Honeywell International Inc. Methods, systems and apparatuses for optimizing time-triggered ethernet (TTE) network scheduling by bin allocation, demand prediction and machine learning
CN111030942A (zh) * 2019-11-05 2020-04-17 天津大学 基于响应约束的tte网络离线调度方法
CN111049611A (zh) * 2019-12-30 2020-04-21 西安电子科技大学 多矩阵周期联合调度的时间触发业务调度表生成方法
CN114374640A (zh) * 2021-12-15 2022-04-19 陕西电器研究所 一种基于时间触发以太网的业务调度方法

Also Published As

Publication number Publication date
JP2024516965A (ja) 2024-04-18
CN114374640A (zh) 2022-04-19

Similar Documents

Publication Publication Date Title
CN107241179B (zh) 一种时间触发业务静态调度表的生成方法
US9769082B2 (en) System and method for network bandwidth, buffers and timing management using hybrid scheduling of traffic with different priorities and guarantees
CN109818876B (zh) 全局最优化时间触发业务调度表的生成方法
CN1989738B (zh) 最低保证调度速率的传播
JP6456330B2 (ja) 工業インターネットブロードバンドフィールドバスのリアルタイム性の実現方法
CN108282415A (zh) 一种调度方法及设备
US20240098033A1 (en) Centralized network configuration entity and time-sensitive network control system comprising same
US20160294720A1 (en) Systematic hybrid network scheduling for multiple traffic classes with host timing and phase constraints
CN103036792B (zh) 一种最大化最小公平多数据流传输调度方法
CN102970247B (zh) 一种有效的时间触发网络通信时间调度方法
Suethanuwong Scheduling time-triggered traffic in TTEthernet systems
WO2023109445A1 (zh) 一种基于时间触发以太网的业务调度方法
CN110990140B (zh) 一种光电交换网络中分布式机器学习流的调度方法
CN103457881A (zh) 执行数据直通转发的系统
CN111049611B (zh) 多矩阵周期联合调度的时间触发业务调度表生成方法
US10075391B2 (en) Flexible deterministic binary scheduler
CN100593312C (zh) 使用定额和差额值进行调度
CN110661589B (zh) 基于交换式时间触发网络的时隙分配调度方法
CN113765825B (zh) 一种链式业务流调度的规划方法和系统架构
CN102448120A (zh) 多路径负荷分担方法及装置
CN104283805B (zh) 一种sdn网络报文发送方法及设备
CN114285541A (zh) 一种基于时延误差时间触发以太网调度表生成方法
EP4014448B1 (en) Scheduling transmissions through a telecommunication network
CN102594670A (zh) 多端口多流的调度方法、装置及设备
CN105099925A (zh) 用于确定性网络的分层调度器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22906197

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023564029

Country of ref document: JP