Data communication method, system, electronic device and storage medium

Abstract

The present invention relates to the field of communication technology, and discloses a data communication method, system, electronic device and storage medium, including: obtaining communication condition information of multiple data streams to be transmitted and the current reward matrix of a preset deterministic network; for any data stream, according to the communication condition information of the data stream and the current comprehensive communication performance between each communication node in the preset deterministic network represented by the current reward matrix, screening a target communication path from the preset deterministic network; iteratively updating the current reward matrix according to the communication requirements of the data stream for the target communication path; and transmitting the data stream based on the target communication path. By determining the current reward matrix of the preset deterministic network, screening the target communication path for the data stream according to the current reward matrix, while ensuring the accuracy of the target communication path screening result, the determination efficiency of the target communication path is improved, laying a foundation for improving the communication efficiency of the deterministic network for the data stream.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a data communication method, system, electronic device and storage medium. Background Art

[0002] With the rapid development of technologies such as cloud computing, artificial intelligence, and communications, deterministic networks have become one of the important technologies supporting the high-quality development of various industries. Deterministic networks are used to provide deterministic services for deterministic data streams, so as to transmit the data streams with high quality through the communication paths in the deterministic networks. Therefore, how to select the communication paths of data streams in deterministic networks has become a key research topic in deterministic network data communication.

[0003] In related technologies, an integer linear programming model is usually used to search the global solution space according to constraints such as the delay and bandwidth of data stream transmission to select the best routing path.

[0004] However, when the deterministic network topology is complex, the integer linear programming model will take a lot of time to search the global solution space, which reduces the efficiency of determining the communication path and is not conducive to ensuring the communication efficiency of the deterministic network for data flow. Summary of the invention

[0005] The present application provides a data communication method, system, electronic device and storage medium to solve the defects of related technologies, such as reducing the determination efficiency of communication paths, which is not conducive to ensuring the communication efficiency of deterministic networks for data flows.

[0006] The first aspect of the present application provides a data communication method, comprising:

[0007] Acquire communication condition information of multiple data streams to be transmitted and a current reward matrix of a preset deterministic network;

[0008] For any of the data flows, according to the communication condition information of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix, a target communication path is selected from the preset deterministic network;

[0009] Iteratively updating the current reward matrix according to the communication demand of the data flow for the target communication path;

[0010] The data stream is transmitted based on the target communication path.

[0011] In an optional implementation, the communication condition information includes priorities, flow sizes, target delays, source nodes, and destination nodes of multiple data flows to be transmitted.

[0012] In an optional implementation, the obtaining of communication condition information of the plurality of data streams to be transmitted and a current reward matrix of the preset deterministic network includes:

[0013] Acquire an initial reward matrix of the preset deterministic network, where the initial reward matrix is ​​used to characterize the connectivity between communication nodes of the preset deterministic network;

[0014] According to the communication delay between each communication node in the preset deterministic network, the reward value in the initial reward matrix is ​​adjusted to obtain the current reward matrix of the preset deterministic network.

[0015] In an optional implementation, the communication requirement includes a bandwidth occupation requirement, and the iterative updating of the current reward matrix according to the communication requirement of the data flow for the target communication path includes:

[0016] Determining a communication bandwidth threshold between each communication node according to the communication bandwidth between each communication node in the target communication path;

[0017] For any of the data flows, determine a target reward value between the communication nodes according to the bandwidth occupation requirement of the data flow for the target communication path represented by the communication condition information of the data flow and a communication bandwidth threshold between the communication nodes;

[0018] The current reward matrix is ​​iteratively updated according to the target reward value between each of the communication nodes.

[0019] In an optional implementation, determining the target reward value between each of the communication nodes based on the bandwidth occupation requirement of the data flow for the target communication path and the communication bandwidth threshold between each of the communication nodes represented by the communication condition information of the data flow includes:

[0020] Determining the bandwidth occupation requirement of the data flow on the target communication path according to the flow size of the data flow represented by the communication condition information of the data flow;

[0021] According to the bandwidth occupation requirement of the data flow on the target communication path and the communication bandwidth threshold between the communication nodes, the target reward value between the communication nodes is determined.

[0022] In an optional implementation, determining the target reward value between each of the communication nodes according to the bandwidth occupation requirement of the data flow on the target communication path and the communication bandwidth threshold between each of the communication nodes includes:

[0023] Based on the following formula, the first target reward value between each of the communication nodes is determined:

[0024]

[0025] in, Represents a communication node With communication node The target reward value between The communication node representing the current reward matrix before the update With communication node The current reward value between Represents a communication node With communication node The communication bandwidth between Represents a communication node With communication node The communication bandwidth threshold between Indicates the preset communication bandwidth utilization threshold. Representing data flow The bandwidth occupation requirement of the target communication path, Indicates the total number of data streams to be transmitted, Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between.

[0026] In an optional implementation, the selecting a target communication path from the preset deterministic network according to the communication condition information of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix includes:

[0027] Determining the communication order of each of the data flows according to the priority represented by the communication condition information of the data flows;

[0028] Determining the communication constraint conditions of the data flows according to the communication times of each of the data flows and the flow size, target delay, source node and destination node represented by the communication condition information of the data flows;

[0029] A target communication path is selected from the preset deterministic network according to the communication constraints of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix.

[0030] In an optional implementation, the selecting a target communication path from the preset deterministic network according to the communication constraint of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix includes:

[0031] According to the communication constraint condition of the data flow, selecting a plurality of candidate communication paths satisfying the communication constraint condition in the preset deterministic network;

[0032] Determining the current comprehensive communication performance of each of the candidate communication paths according to the cumulative reward value of each of the candidate communication paths in the current reward matrix;

[0033] A target communication path is screened from the candidate communication paths according to the current comprehensive communication performance of each of the candidate communication paths.

[0034] In an optional implementation, the communication requirement includes the communication nodes included in the target communication path, and the method for iteratively updating the current reward matrix according to the communication requirement of the data flow for the target communication path includes:

[0035] After determining the target communication path of any of the data flows, the current reward matrix is ​​first updated according to the communication nodes included in the target communication path to reduce the probability that other data flows with a lower priority than the data flow select the target communication path.

[0036] In an optional implementation, the first updating of the current reward matrix according to the communication nodes included in the target communication path includes:

[0037] Based on the following formula, the current reward matrix is ​​first updated:

[0038]

[0039] in, Represents the first updated communication node With communication node The reward value between Indicates the communication node before the first update With communication node The current reward value between Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between represents the update coefficient.

[0040] In an optional embodiment, the method further includes:

[0041] After completing the transmission of any of the data flows, the current reward matrix is ​​secondly updated according to the communication nodes included in the target communication path to increase the probability that other data flows with a lower priority than the data flow and whose target communication path has not been determined select the target communication path.

[0042] A second aspect of the present application provides a data communication device, including:

[0043] An acquisition module, used to acquire communication condition information of multiple data streams to be transmitted and a current reward matrix of a preset deterministic network;

[0044] A screening module, configured to screen a target communication path from the preset deterministic network for any of the data streams according to the communication condition information of the data stream and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix;

[0045] An updating module, configured to iteratively update the current reward matrix according to the communication demand of the data stream for the target communication path;

[0046] A communication module is used to transmit the data stream based on the target communication path.

[0047] A third aspect of the present application provides a data communication system, comprising: a preset deterministic network composed of a plurality of communication nodes and a control terminal;

[0048] Based on the data communication method described in the first aspect and various possible designs of the first aspect, the control end transmits multiple data streams to be transmitted through the preset deterministic network to transmit each of the data streams to the destination node.

[0049] A fourth aspect of the present application provides an electronic device, comprising: at least one processor and a memory;

[0050] The memory stores computer-executable instructions;

[0051] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method described in the first aspect and various possible designs of the first aspect.

[0052] A fifth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method described in the first aspect and various possible designs of the first aspect are implemented.

[0053] The sixth aspect of the present application provides a computer program product, including computer instructions, which are used to enable a computer to execute the method described in the first aspect and various possible designs of the first aspect.

[0054] The technical solution of this application has the following advantages:

[0055] The present application provides a data communication method, system, electronic device and storage medium, the method comprising: obtaining communication condition information of multiple data streams to be transmitted and the current reward matrix of a preset deterministic network; for any data stream, based on the communication condition information of the data stream and the current comprehensive communication performance between each communication node in the preset deterministic network represented by the current reward matrix, screening the target communication path from the preset deterministic network; iteratively updating the current reward matrix according to the communication requirements of the data stream for the target communication path; based on the target communication path, transmitting the data stream to transmit the data stream to the destination node. The method provided by the above scheme determines the current reward matrix of the preset deterministic network, and when the data stream to be transmitted is obtained, the target communication path is screened for the data stream according to the current reward matrix, while ensuring the accuracy of the target communication path screening result, the determination efficiency of the target communication path is improved, laying a foundation for improving the communication efficiency of the deterministic network for the data stream. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technical descriptions. Obviously, the drawings described below are some embodiments of the present application, and a person skilled in the art can also obtain other drawings based on these drawings.

[0057] Figure 1 A schematic diagram of the network structure based on which the embodiments of the present application are based;

[0058] Figure 2 A flowchart of a data communication method provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of the structure of an exemplary preset deterministic network provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of the structure of a data communication device provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of the structure of a data communication system provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0063] The above drawings have shown clear embodiments of the present application, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the following embodiments, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0066] In related technologies, a deterministic network (DetNet) refers to a network that provides deterministic services for deterministic flows (DetFlow) in a certain network topology. Deterministic networks are proposed because current networks often have problems such as data congestion, high data transmission latency, and weak stability. For some data with special requirements, the current network cannot provide high-quality data transmission services QoS (Quality of Service). Deterministic networks propose three concepts: resource reservation, explicit routing, and service protection to ensure high-quality services for some data.

[0067] Under a certain network topology and deterministic flow, high-quality services for deterministic flows are guaranteed. Deterministic networks reserve bandwidth in the network to ensure the transmission of this part of traffic, and other flows cannot occupy it (resource reservation); the transmission path of deterministic flows is fixed and will not change (explicit routing); and the data transmission delay is guaranteed to be within a certain range (service protection).

[0068] Planning the transmission paths of multiple deterministic flows in a deterministic network is a key issue in deterministic networks. Currently proposed models include integer linear programming models, ant colony algorithm models, and gradient-based optimal models.

[0069] The integer linear programming model adds some constraints and uses the linear programming method to find the optimal transmission path for the determined flow. This method essentially searches the global solution space and is less efficient in solving the problem.

[0070] Other algorithms include ant colony algorithms and genetic algorithms. These algorithms perform well when facing a small number of flows, but as the flow increases, the complexity of the algorithm increases, and the efficiency of solving is worrying. In addition, if a new flow is added to the network, the algorithm needs to recalculate the optimal transmission path, which shows that the scalability of the algorithm is relatively poor.

[0071] In response to the above problems, the embodiments of the present application provide a data communication method, system, electronic device and storage medium, the method comprising: obtaining communication condition information of multiple data streams to be transmitted and the current reward matrix of a preset deterministic network; for any data stream, based on the communication condition information of the data stream and the current comprehensive communication performance between each communication node in the preset deterministic network represented by the current reward matrix, screening the target communication path from the preset deterministic network; iteratively updating the current reward matrix according to the communication requirements of the data stream for the target communication path; based on the target communication path, transmitting the data stream to the destination node. The method provided by the above scheme determines the current reward matrix of the preset deterministic network, and when the data stream to be transmitted is obtained, the target communication path is screened for the data stream according to the current reward matrix, while ensuring the accuracy of the target communication path screening result, the determination efficiency of the target communication path is improved, laying a foundation for improving the communication efficiency of the deterministic network for the data stream.

[0072] The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0073] First, the network structure on which this application is based is described:

[0074] The data communication method, system, electronic device and storage medium provided in the embodiments of the present application are suitable for transmitting the data stream based on a preset deterministic network after a control terminal such as a server obtains the data stream to be transmitted. Figure 1 The figure shows a schematic diagram of the network structure based on the embodiment of the present application, which mainly includes a control end and a deterministic network. The deterministic network is composed of multiple network communication devices such as routers and switches. After obtaining the data stream to be transmitted by the user, the host end determines the target communication path for transmitting the data stream in the deterministic network, transmits the data stream through the target communication path, and finally sends the data stream to the destination end through the destination communication device.

[0075] The embodiment of the present application provides a data communication method for selecting a target communication path in a preset deterministic network. The execution subject of the embodiment of the present application is an electronic device, such as a server, a desktop computer, a laptop computer, a tablet computer, and other electronic devices that can be used to select a target communication path in a preset deterministic network.

[0076] like Figure 2 FIG. 1 is a flow chart of a data communication method provided in an embodiment of the present application, the method comprising:

[0077] Step 201: Obtain communication condition information of multiple data streams to be transmitted and a current reward matrix of a preset deterministic network.

[0078] The current reward matrix of the preset deterministic network includes reward values ​​between adjacent communication nodes in the preset deterministic network, and the reward values ​​are positively correlated with the communication performance between the communication nodes.

[0079] Specifically, in one embodiment, the priority, flow size, target delay, source node and destination node of multiple data flows to be transmitted can be obtained; and the communication condition information of the data flow is determined according to the priority, flow size, target delay, source node and destination node of the data flow. The communication condition information includes the priority, flow size, target delay, source node and destination node of the multiple data flows to be transmitted.

[0080] For example, it is assumed that 4 data streams to be transmitted are obtained this time, and it is assumed that this deterministic network needs to optimize the paths of the 4 deterministic streams (data streams). For convenience, it is assumed that the source addresses of the data streams are all 1, and the data stream numbers are DF1, DF2, DF3 and DF4 respectively. The communication condition information is shown in Table 1 below:

[0081] Table 1

[0082]

[0083] The unit of the flow size may be mega (M), and the target delay may be microsecond (μs).

[0084] Step 202 , for any data stream, based on the communication condition information of the data stream and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix, select a target communication path from the preset deterministic network.

[0085] Specifically, for any data flow, we can first determine the reachable communication path between the source node and the destination node based on the destination node represented by the communication condition information of the data flow, and then determine the communication constraints of the data flow based on the flow size and target delay of the data flow. Then, we can preliminarily screen the reachable communication paths according to the communication constraints. Finally, we can further screen the preliminary screening results based on the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix to obtain the target communication path.

[0086] Step 203, iteratively update the current reward matrix according to the communication requirements of the data flow on the target communication path.

[0087] It should be noted that after the target communication path of any data stream is determined, because the target communication path will consume certain communication resources to transmit the data stream, the communication performance will be reduced. In order to ensure the accuracy of the target communication path selection results of data streams with lower priority, each time the target communication path of a data stream is determined, the current reward matrix is ​​iteratively updated according to the communication requirements of the data stream for the target communication path to ensure that the current reward matrix matches the actual communication performance of the preset deterministic network.

[0088] Step 204: Transmit the data stream based on the target communication path.

[0089] It should be noted that the target communication path includes at least a source node and a destination node, and the data flow is sent from the source node to the destination node through the target communication path.

[0090] On the basis of the above embodiment, since the current reward matrix of the preset deterministic network will directly affect the accuracy of the determination result of the target communication path, as an implementable manner, in one embodiment, obtaining the communication condition information of the multiple data streams to be transmitted and the current reward matrix of the preset deterministic network includes:

[0091] Step 2011, obtaining an initial reward matrix of a preset deterministic network, where the initial reward matrix is ​​used to characterize the connectivity between communication nodes of the preset deterministic network;

[0092] Step 2012, adjusting the reward values ​​in the initial reward matrix according to the communication delay between each communication node in the preset deterministic network to obtain the current reward matrix of the preset deterministic network.

[0093] For example, Figure 3 As shown, a schematic diagram of the structure of an exemplary preset deterministic network provided in an embodiment of the present application shows a deterministic network with 6 nodes, and each link has a vector (a, b), where a represents the communication bandwidth of the link, and b represents the communication delay of the link. The initial reward matrix of the preset deterministic network is shown in Table 2 below:

[0094] Table 2

[0095]

[0096] Among them, -1 is used to represent the link between two communication nodes being connected, and an extremely large value (-1000) is used to represent the link between two communication nodes being disconnected, indicating that it is impossible to select the line.

[0097] It should be noted that the target delay, as part of the data flow network service quality QoS, is mainly a constraint on the data flow link selection, that is, the target delay of the data flow is only used to screen the target communication path of the data flow in the network, that is, the path that exceeds the delay should not be selected, and the path that exceeds the target delay should be eliminated from the optional path set. The greater the delay in the deterministic network link, the less likely DF will choose the line, so the link delay can be subtracted from the initial reward matrix setting. Specifically, the reward value in the initial reward matrix can be adjusted based on the following formula.

[0098]

[0099] in, Represents the communication node in the current reward matrix With communication node The current reward value between Represents a communication node With communication node The communication delay between them finally results in the current reward matrix of the preset deterministic network as shown in Table 3 below:

[0100] Table 3

[0101]

[0102] Specifically, in one embodiment, in order to further improve the reliability of the current reward matrix initially determined, a weighted fusion method of multiple path characteristics can be used to determine the reward value between each communication node. In addition to communication delay, path characteristics can also include packet loss rate, congestion status, and security.

[0103] Among them, the packet loss of a link reflects its stability. A low packet loss rate indicates that the link is more reliable and stable, and is suitable for transmitting important data. The use of more stable paths can be encouraged by reducing the reward value of links with high packet loss rates. Some links may be congested due to excessive current load, which will cause additional delays or even packet loss. Monitoring and dynamically adjusting rewards based on real-time congestion levels can help improve the reliability of reward values ​​to avoid selecting links that are already busy. In addition, security and privacy protection are particularly important in some application scenarios. Giving higher ratings to links that can provide better security measures (such as encrypted transmission, access control, etc.) is conducive to improving the security of data stream transmission.

[0104] On the basis of the above embodiment, in order to further improve the reliability of the current reward matrix of the preset determined network, as an implementable manner, in one embodiment, the communication demand includes a bandwidth occupation demand, and the current reward matrix is ​​iteratively updated according to the communication demand of the data flow for the target communication path, including:

[0105] Step 2031, determining a communication bandwidth threshold between each communication node according to the communication bandwidth between each communication node in the target communication path;

[0106] Step 2032, for any data flow, according to the bandwidth occupation requirement of the data flow for the target communication path represented by the communication condition information of the data flow and the communication bandwidth threshold between each communication node, determine the target reward value between each communication node;

[0107] Step 2033, iteratively update the current reward matrix according to the target reward value between each communication node.

[0108] It should be noted that the path selection in the related art often only considers whether the delay and bandwidth meet the data flow requirements, but ignores the factor that excessive communication bandwidth occupancy of the communication node will affect the communication performance. In order to further improve the accuracy of the target communication path determination result, this application considers the bandwidth occupancy requirement of the data flow for the target communication path represented by the communication condition information of the data flow and the communication bandwidth threshold between each communication node, and iteratively updates the current reward matrix.

[0109] Among them, for any two adjacent communication nodes, if the communication bandwidth occupancy between the two communication nodes exceeds the communication bandwidth threshold, the communication performance of the link between the two communication nodes will be reduced, and the link should be avoided in the future to avoid overload.

[0110] Specifically, in one embodiment, the bandwidth occupancy requirement of the data flow for the target communication path can be determined based on the flow size of the data flow represented by the communication condition information of the data flow; the target reward value between each communication node is determined based on the bandwidth occupancy requirement of the data flow for the target communication path and the communication bandwidth threshold between each communication node.

[0111] The bandwidth occupation requirement of the data flow for the target communication path can be specifically quantified by its flow size, that is, the flow size of the data flow is equal to the bandwidth occupation requirement of the data flow for the target communication path.

[0112] Specifically, in one embodiment, the first target reward value between each communication node may be determined based on the following formula:

[0113]

[0114] in, Represents a communication node With communication node The target reward value between The communication node representing the current reward matrix before the update With communication node The current reward value between Represents a communication node With communication node The communication bandwidth between Represents a communication node With communication node The communication bandwidth threshold between Indicates the preset communication bandwidth utilization threshold. Representing data flow The bandwidth requirement of the target communication path, Indicates the total number of data streams to be transmitted. Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between.

[0115] in, , that is, when the link<i,j> When the total flow exceeds 80% of the link, the reward function will increase the negative value appropriately after each iteration to improve the link congestion by reducing DF's choice of this path.

[0116] On the basis of the above embodiments, in order to further improve the accuracy of the target communication path determination result, as an implementable manner, in one embodiment, according to the communication condition information of the data flow and the current comprehensive communication performance between each communication node in the preset deterministic network represented by the current reward matrix, the target communication path is screened from the preset deterministic network, including:

[0117] Step 2021, determining the communication order of each data stream according to the priority represented by the communication condition information of the data stream;

[0118] Step 2022, according to the communication times of each data flow, and according to the flow size, target delay, source node and destination node represented by the communication condition information of the data flow, determine the communication constraint condition of the data flow;

[0119] Step 2023, based on the communication constraints of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix, select the target communication path from the preset deterministic network.

[0120] It should be noted that the communication constraints of data flow in terms of delay can be abstracted into the following expression, that is, for M deterministic flows, the total delay of any flow m is within the target delay, that is:

[0121]

[0122] in, is the communication path to be selected, Indicates the target delay of data flow m.

[0123] The communication constraints of data flow in terms of bandwidth can be abstracted into the following expression, that is, for each link, the total flow number should not exceed its bandwidth, that is:

[0124]

[0125] in, Represents a communication node With communication node The communication bandwidth between Representing data flow The bandwidth occupation requirement of the target communication path is Representing data flow The stream size.

[0126] Specifically, in one example, according to the communication constraints of the data flow, several candidate communication paths that meet the communication constraints can be screened in the preset deterministic network; according to the cumulative value of the rewards of each candidate communication path in the current reward matrix, the current comprehensive communication performance of each candidate communication path can be determined; according to the current comprehensive communication performance of each candidate communication path, the target communication path can be screened among the candidate communication paths.

[0127] Specifically, a reward function can be formulated for each link based on the above two expressions: , that is, determine the current reward matrix of the preset deterministic network, and the optimization goal of the target communication path is as follows:

[0128]

[0129] That is, the candidate communication path with the largest cumulative reward value in the current reward matrix has better current comprehensive communication performance, so the candidate communication path with the highest cumulative reward value is used as the target communication path.

[0130] Further, in one embodiment, the communication requirements include the communication nodes included in the target communication path. After determining the target communication path of any data flow, the current reward matrix is ​​first updated according to the communication nodes included in the target communication path to reduce the probability that other data flows with a lower priority than the data flow select the target communication path.

[0131] It should be noted that the obtained data streams are transmitted in order of priority. In one iteration, after the deterministic stream m selects the transmission path, the negative value of the reward function of the transmission path taken by the stream m can be appropriately increased in this iteration, that is, the first update of the current reward matrix is ​​performed. The purpose of this is to reduce the probability of other flows choosing this line, so as to reduce the congestion of the transmission path selected by the high-priority flow and increase network stability.

[0132] Specifically, in one embodiment, the current reward matrix may be first updated based on the following formula:

[0133]

[0134] in, Represents the first updated communication node With communication node The reward value between Indicates the communication node before the first update With communication node The current reward value between Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between represents the update coefficient, for example, .

[0135] Accordingly, in one embodiment, after the transmission of any data stream is completed, the current reward matrix can be secondly updated according to the communication nodes included in the target communication path to increase the probability that other data streams with a lower priority than the data stream and for which the target communication path has not been determined select the target communication path.

[0136] Specifically, performing a second update on the current reward matrix is ​​to restore the effect of the first update on the current reward matrix. The implementation principle is the same and will not be repeated here.

[0137] In order to facilitate those skilled in the art to better understand the method provided in the embodiments of the present application, the embodiments of the present application provide the following examples. Figure 3 Taking the deterministic network structure shown in the figure as an example, the starting reward matrix (current reward matrix) of the deterministic network is determined as shown in Table 4 below:

[0138] Table 4

[0139]

[0140] Nodes 1 to 2,3 are directly connected, and the maximum reward function sum is -1.2, -1.2. Nodes 4 are connected to 2,3, and the reward function between 4 and 2 is small. It can be obtained that the node path 1-2-4 is feasible, and the reward function is -2.35. Nodes 5 and 3,4 are connected, and similarly, 1-3-5 is obtained, and the reward function is -2.5. Nodes 6 and 4,5 are connected, and 1-2-4-6 is obtained, and the reward function is -3.65, as shown in Table 5. Among them, the reward function and the reward function sum both represent the cumulative reward value of the path (Note: the data flow DF with a lower priority should find its maximum reward function sum when it selects the path. Here, it is convenient to introduce the calculation of the maximum reward function sum and the path selection method).

[0141] Table 5

[0142]

[0143] According to the priority DF1, line 1-2 is selected, and the reward function of 1-2 is updated to -0.1. For the convenience of understanding by those skilled in the art, this example only considers the first update of the current reward matrix, that is, the update table is shown in Table 6 below:

[0144] Table 6

[0145]

[0146] Further, DF2 selects line 1-2-4, links <1,2> ​​and <2,4> increase by -0.1, and the updated table is shown in Table 7 below:

[0147] Table 7

[0148]

[0149] Furthermore, it is determined that the reward cumulative value of selecting path 1-3-4 to destination node 4 is 2.6. If the destination node of the subsequent data flow is node 4, path 1-3-4 is selected. DF3 selects line 1-3-5, and links <1,3> and <3,5> increase by 0.1. That is, if after DF3, the destination communication path of the destination node 4 is changed to 1-2-4, the updated table is shown in Table 8 below:

[0150] Table 8

[0151]

[0152] Furthermore, according to the updated table, it is determined that the path 1-2-4-6 corresponding to the destination node 6 is still the path with the smallest reward cumulative value, that is, DF4 is determined to select the route 1-2-4-6.

[0153] Specifically, in practical applications, the update of the first target reward value between each communication node will also be considered. DF1 passes through <1,2>, the total flow of DF1 is 4, and <1-2> increases the negative value of the reward function by (6-0.8×6) / 6=0.02, that is, Similarly, <1,3>, <2.4>, <5,6> increase the reward function negative value by 0, and <3,5> increases by 0.009. This table is updated as shown in Table 9 below, and one iteration is completed.

[0154] Table 9

[0155]

[0156] Furthermore, in order to further improve the generalization of the method provided in the embodiment of the present application, randomness can also be added based on reinforcement learning logic, and the path with a larger cumulative reward value is more likely to be selected.

[0157] The data communication method provided by the embodiment of the present application obtains the communication condition information of multiple data streams to be transmitted and the current reward matrix of the preset deterministic network; for any data stream, according to the communication condition information of the data stream and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix, the target communication path is screened from the preset deterministic network; according to the communication requirements of the data stream for the target communication path, the current reward matrix is ​​iteratively updated; based on the target communication path, the data stream is transmitted to transmit the data stream to the destination node. The method provided by the above scheme determines the current reward matrix of the preset deterministic network, and when the data stream to be transmitted is obtained, the target communication path is screened for the data stream according to the current reward matrix, while ensuring the accuracy of the target communication path screening result, the determination efficiency of the target communication path is improved, and the foundation is laid for improving the communication efficiency of the deterministic network to the data stream. In addition, by setting the reward function according to information such as network bandwidth, traffic delay and priority, the reliability of the current reward matrix is ​​improved, thereby further improving the accuracy of the target communication path determination result.

[0158] An embodiment of the present application provides a data communication device, which is used to execute the data communication method provided in the above embodiment.

[0159] like Figure 4 , which is a schematic diagram of the structure of a data communication device provided in an embodiment of the present application. The data communication device 40 comprises: an acquisition module 401 , a screening module 402 , an update module 403 and a communication module 404 .

[0160] Among them, the acquisition module is used to obtain the communication condition information of multiple data streams to be transmitted and the current reward matrix of the preset deterministic network; the screening module is used to screen the target communication path from the preset deterministic network for any data stream according to the communication condition information of the data stream and the current comprehensive communication performance between each communication node in the preset deterministic network represented by the current reward matrix; the update module is used to iteratively update the current reward matrix according to the communication requirements of the data stream for the target communication path; the communication module is used to transmit the data stream based on the target communication path.

[0161] Regarding the data communication device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0162] The data communication device provided in the embodiment of the present application is used to execute the data communication method provided in the above embodiment. Its implementation method and principle are the same and will not be repeated here.

[0163] An embodiment of the present application provides a data communication system for executing the data communication method provided in the above embodiment.

[0164] like Figure 5 , which is a schematic diagram of the structure of a data communication system provided in an embodiment of the present application. The data communication system includes: a preset deterministic network composed of multiple communication nodes and a control terminal;

[0165] Based on the data communication method provided in the above embodiment, the control end transmits the multiple data streams to be transmitted through a preset deterministic network, so as to transmit each data stream to the destination node.

[0166] An embodiment of the present application provides an electronic device for executing the data communication method provided in the above embodiment.

[0167] like Figure 6 FIG. 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 60 includes: at least one processor 61 and a memory 62 .

[0168] The memory stores computer-executable instructions; at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the data communication method provided in the above embodiment.

[0169] The electronic device provided in the embodiment of the present application is used to execute the data communication method provided in the above embodiment. Its implementation method and principle are the same and will not be repeated here.

[0170] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the data communication method provided in any of the above embodiments is implemented.

[0171] The storage medium containing computer executable instructions provided in the embodiments of the present application can be used to store computer executable instructions of the data communication method provided in the aforementioned embodiments. The implementation method and principle are the same and will not be repeated here.

[0172] An embodiment of the present application provides a computer program product, including computer instructions, which are used to enable a computer to execute the data communication method provided in the aforementioned embodiment.

[0173] The embodiments of the present application provide a computer program product that can be used to execute computer instructions of the data communication method provided in the aforementioned embodiments. The implementation method and principle are the same and will not be repeated here.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0177] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0178] A part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0179] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A data communication method, characterized in that: include: Acquire communication condition information of multiple data streams to be transmitted and a current reward matrix of a preset deterministic network; For any of the data flows, according to the communication condition information of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix, a target communication path is selected from the preset deterministic network; Iteratively updating the current reward matrix according to the communication demand of the data flow for the target communication path; transmitting the data stream based on the target communication path; The communication requirement includes a bandwidth occupation requirement, and the iterative updating of the current reward matrix according to the communication requirement of the data flow for the target communication path includes: Determining a communication bandwidth threshold between each communication node according to the communication bandwidth between each communication node in the target communication path; For any of the data flows, determine a target reward value between the communication nodes according to the bandwidth occupation requirement of the data flow for the target communication path represented by the communication condition information of the data flow and a communication bandwidth threshold between the communication nodes; The current reward matrix is ​​iteratively updated according to the target reward value between each of the communication nodes.

2. The method according to claim 1, characterized in that The communication condition information includes the priority, flow size, target delay, source node and destination node of multiple data flows to be transmitted.

3. The method according to claim 1, characterized in that The obtaining of communication condition information of a plurality of data streams to be transmitted and a current reward matrix of a preset deterministic network includes: Acquire an initial reward matrix of the preset deterministic network, where the initial reward matrix is ​​used to characterize the connectivity between communication nodes of the preset deterministic network; According to the communication delay between each communication node in the preset deterministic network, the reward value in the initial reward matrix is ​​adjusted to obtain the current reward matrix of the preset deterministic network.

4. The method according to claim 1, characterized in that: The step of determining the target reward value between the communication nodes based on the bandwidth occupation requirement of the data flow for the target communication path and the communication bandwidth threshold between the communication nodes represented by the communication condition information of the data flow comprises: Determining the bandwidth occupation requirement of the data flow on the target communication path according to the flow size of the data flow represented by the communication condition information of the data flow; According to the bandwidth occupation requirement of the data flow on the target communication path and the communication bandwidth threshold between the communication nodes, the target reward value between the communication nodes is determined.

5. The method according to claim 4, characterized in that Determining the target reward value between the communication nodes according to the bandwidth occupation requirement of the data flow on the target communication path and the communication bandwidth threshold between the communication nodes includes: Based on the following formula, the first target reward value between each of the communication nodes is determined: in, Represents a communication node With communication node The target reward value between The communication node representing the current reward matrix before the update With communication node The current reward value between Represents a communication node With communication node The communication bandwidth between Represents a communication node With communication node The communication bandwidth threshold between Indicates the preset communication bandwidth utilization threshold. Representing data flow The bandwidth occupation requirement of the target communication path, Indicates the total number of data streams to be transmitted, Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between.

6. The method according to claim 1, characterized in that The step of selecting a target communication path from the preset deterministic network according to the communication condition information of the data stream and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix includes: Determining the communication order of each of the data flows according to the priority represented by the communication condition information of the data flows; Determine the communication constraints of the data flows according to the communication order of each of the data flows and according to the flow size, target delay, source node and destination node represented by the communication condition information of the data flows; A target communication path is selected from the preset deterministic network according to the communication constraints of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix.

7. The method according to claim 6, characterized in that The step of selecting a target communication path from the preset deterministic network according to the communication constraint of the data flow and the current comprehensive communication performance between the communication nodes in the preset deterministic network represented by the current reward matrix includes: According to the communication constraint condition of the data flow, selecting a plurality of candidate communication paths satisfying the communication constraint condition in the preset deterministic network; Determining the current comprehensive communication performance of each of the candidate communication paths according to the cumulative reward value of each of the candidate communication paths in the current reward matrix; A target communication path is screened from the candidate communication paths according to the current comprehensive communication performance of each of the candidate communication paths.

8. The method according to claim 6, characterized in that The communication requirement includes the communication nodes included in the target communication path, and the iterative updating of the current reward matrix according to the communication requirement of the data flow for the target communication path includes: After determining the target communication path of any of the data flows, the current reward matrix is ​​first updated according to the communication nodes included in the target communication path to reduce the probability that other data flows with a lower priority than the data flow select the target communication path.

9. The method according to claim 8, characterized in that The first updating of the current reward matrix according to the communication nodes included in the target communication path includes: Based on the following formula, the current reward matrix is ​​first updated: in, Represents the first updated communication node With communication node The reward value between Indicates the communication node before the first update With communication node The current reward value between Representing data flow Whether the target communication path includes the communication node With communication node The path between Representing data flow The target communication path includes communication nodes With communication node The path between Representing data flow The target communication path does not include the communication node With communication node The path between represents the update coefficient.

10. The method according to claim 8, characterized in that The method further comprises: After completing the transmission of any of the data flows, the current reward matrix is ​​secondly updated according to the communication nodes included in the target communication path to increase the probability that other data flows with a lower priority than the data flow and whose target communication path has not been determined select the target communication path.

11. A data communication system, characterized in that: include: A preset deterministic network consisting of multiple communication nodes and a control terminal; The control end transmits the multiple data streams to be transmitted through the preset deterministic network based on the data communication method according to any one of claims 1 to 10, so as to transmit each of the data streams to the destination node.

12. An electronic device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 10.

Images