Method, device, and equipment for determining routing scheduling strategy for edge computing network

Abstract

The present invention provides a method, apparatus, and device for determining a routing scheduling strategy for an edge computing network. The method includes: determining a source host set formed by source hosts that send data streams and a destination host set formed by destination hosts that receive data streams; determining a switch set formed by switches between the source hosts and the destination hosts; determining a data stream set formed by data streams that need to be sent by each source host in the source host set within a time period and a time period set formed by time periods within the time period; determining the priority of each data stream in the data stream set; determining a data stream transmission network topology; determining a corresponding link matrix; constructing an integer linear programming model; and solving the integer linear programming model to obtain a network routing scheduling strategy. The present invention can reduce the transmission delay of data streams.

Description

Technical Field

[0001] The present invention relates to the field of data transmission technology, and in particular to a method, device, and equipment for determining a routing scheduling strategy for an edge computing network. Background Art

[0002] With the continuous development of the Industrial Internet and artificial intelligence technologies, industrial intelligence, informatization, and dataization are gaining increasing attention. The edge computing network architecture of industrial sites can be roughly divided into three layers: industrial infrastructure devices, edge computing resources, and cloud computing resources. Because different industrial devices and computing resources use different manufacturers, operating systems, and data formats, unified communication between these devices is difficult. Even for devices from the same manufacturer, the complex structure of network transmission links often results in long transmission latency and significant uncertainty, making them unable to meet the real-time data transmission requirements of industrial edge computing networks. Summary of the Invention

[0003] In response to at least one of the above technical problems, embodiments of the present invention provide a method, apparatus, and device for determining a routing scheduling strategy for an edge computing network.

[0004] According to a first aspect, an embodiment of the present invention provides a method for determining a routing scheduling strategy for an edge computing network, including:

[0005] Determine a source host set formed by each source host sending a data stream and a destination host set formed by each destination host receiving a data stream; wherein the source host is an industrial underlying device in the edge computing network, and the destination host is an edge computing node or a cloud computing node in the edge computing network;

[0006] Determine a switch set formed by switches between the source host and the destination host;

[0007] Determine a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period;

[0008] Determining the priority of each data flow in the data flow set;

[0009] Determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, the vertices being hosts in the source host set, hosts in the destination host set, or switches in the switch set, and the edges between two vertices being data stream transmission links between the two vertices;

[0010] Determine a corresponding link matrix according to the data stream transmission network topology structure; wherein each element in the link matrix indicates whether there is a directly connected edge between the corresponding two vertices;

[0011] An integer linear programming model is constructed based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set;

[0012] The integer linear programming model is solved to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize the switches that each data flow needs to pass through during the transmission process from the corresponding source host to the corresponding destination host.

[0013] In one embodiment, the objective function includes:

[0014]

[0015] Wherein, T is the time period set, k is the time period; m is the data flow number, TS is the data flow set; i and j are the device numbers in the device set, V is the device set, and the device set includes the source host set, the destination host set, and the switch set, and the device is a source host, a destination host, or a switch; p m is the priority of the mth data stream; t ij Characterizes the path length between the i-th device and the j-th device in the device set; x mijk is the decision variable corresponding to the mth data flow between the i-th device and the j-th device in the k-th time period.

[0016] In one embodiment, the decision variable x mijk The determination method is: if the mth data stream is transmitted from the ith device to the jth device in the kth time period, then x mijk is 1, otherwise x mijk is 0.

[0017] In one embodiment, the path length t corresponding to the i-th device and the j-th device is ij The determination method is: if the edge formed by the i-th device and the j-th device belongs to the edge set formed by the multiple edges, then t ij is 1, otherwise t ij Is positive infinity.

[0018] In one embodiment, the constraints of the integer linear programming model include:

[0019]

[0020] Where q is the number of the switch, Q is the set of switches, V d is the host set, V s is the source host set, d m is the number of the destination host corresponding to the mth data stream, s m The number of the source host corresponding to the mth data flow.

[0021] In one embodiment, the data flow is a delay-sensitive data flow; the acquisition process of the delay-sensitive data flow includes: for the data flow collected by the open platform unified architecture, using the delay-sensitive network protocol to identify the delay-sensitive data flow as the delay-sensitive data flow.

[0022] In one embodiment, the method is implemented by a control plane, and the process of transmitting data streams according to a network routing scheduling policy is implemented in a data transmission plane. The separation of the control plane and the transmission plane is based on software-defined networking.

[0023] According to a second aspect, an embodiment of the present invention provides an edge computing network routing scheduling strategy determination device including:

[0024] A first determination module is configured to determine a source host set formed by each source host sending a data stream and a destination host set formed by each destination host receiving a data stream; wherein the source host is an industrial underlying device in the edge computing network, and the destination host is an edge computing node or a cloud computing node in the edge computing network;

[0025] A second determining module is configured to determine a switch set formed by switches between the source host and the destination host;

[0026] A third determining module is used to determine a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period;

[0027] A fourth determining module, configured to determine the priority of each data flow in the data flow set;

[0028] a fifth determining module, configured to determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, wherein the vertices are hosts in the source host set, hosts in the destination host set, or switches in the switch set, and an edge between two vertices is a data stream transmission link between the two vertices;

[0029] a sixth determining module, configured to determine a corresponding link matrix according to the data stream transmission network topology; wherein each element in the link matrix indicates whether there is a directly connected edge between corresponding two vertices;

[0030] a model construction module, configured to construct an integer linear programming model based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set;

[0031] A model solving module is used to solve the integer linear programming model to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize the switches that each data flow needs to pass through during the transmission process from the corresponding source host to the corresponding destination host.

[0032] According to a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method provided in the first aspect.

[0033] According to a fourth aspect, an embodiment of the present invention provides a computing device, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method provided in the first aspect is implemented.

[0034] The embodiments of the present invention provide a method, apparatus, and device for determining a routing scheduling strategy for an edge computing network. These methods determine a set of source hosts, a set of destination hosts, a set of switches, a set of data flows, a set of time periods, and the priorities of each data flow. The method then determines a data flow transmission network topology, determines a corresponding link matrix based on the data flow transmission network topology, and constructs an integer linear programming model based on the aforementioned sets and link matrices. Finally, the integer linear programming model is solved to obtain a network routing scheduling strategy. It can be seen that in the above process, by comprehensively considering the complex network topology of the source hosts, destination hosts, and switches, the priorities of the data flows, and the like, the transmission delay of the data flows can be reduced. Furthermore, an integer linear programming model is established based on the data flow transmission network topology, and the integer linear programming model is solved to ultimately determine a network routing scheduling scheme. Since the objective function is to minimize the sum of the transmission delays of all data flows in the data flow set, this process solves the edge computing data flow transmission problem in the industrial Internet field, reducing the transmission delay and queuing delay of the data flows, thereby improving the efficiency of data transmission and reducing data transmission jitter. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Schematic diagram of a flow chart of a method for determining a routing scheduling strategy for an edge computing network in one embodiment of the present invention;

[0036] Figure 2 Schematic diagram of separation of the control plane and the data transmission plane in one embodiment of the present invention;

[0037] Figure 3 A schematic diagram of a scheduling solution in the prior art;

[0038] Figure 4 Schematic diagram of a scheduling solution in one embodiment of the present invention;

[0039] Figure 5 Schematic diagram of another scheduling solution according to an embodiment of the present invention;

[0040] Figure 6 This is a structural block diagram of a device for determining a routing scheduling strategy for an edge computing network in one embodiment of the present invention. DETAILED DESCRIPTION

[0041] In a first aspect, an embodiment of the present invention provides a method for determining a routing scheduling strategy for an edge computing network, see Figure 1 The method includes the following steps S110 to S180:

[0042] S110. Determine a source host set formed by each source host sending a data stream and a destination host set formed by each destination host receiving a data stream; wherein the source host is an industrial underlying device in the edge computing network, and the destination host is an edge computing node or a cloud computing node in the edge computing network;

[0043] The source host sending the data stream is an industrial infrastructure device, while the destination host receiving the data stream can be an edge computing node or a cloud computing node. Multiple switches are located between the source and destination hosts. The source and destination hosts of a data stream are both known, and the embodiment of the present invention determines which switch the data stream will pass through.

[0044] S120: Determine a switch set formed by switches between the source host and the destination host;

[0045] It can be seen that a device set can be formed at this time, and the device set includes the source host set, the destination host set and the switch set.

[0046] S130, determining a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period;

[0047] That is, the data flows within a time period form a data flow set, and the time periods within the time period form a time period set.

[0048] S140, determining the priority of each data flow in the data flow set;

[0049] Among them, each data flow has its own priority. The higher the priority, the lower the delay required.

[0050] S150. Determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, wherein the vertices are hosts in the source host set, hosts in the destination host set, or switches in the switch set, and an edge between two vertices is a data stream transmission link between the two vertices;

[0051] For example, the topology of a data stream transmission network is G = (V, E), where V is a set of vertices, representing transmission nodes in the network; and E is a set of edges, representing transmission links in the network.

[0052] S160. Determine a corresponding link matrix according to the data stream transmission network topology structure; wherein each element in the link matrix indicates whether there is a directly connected edge between corresponding two vertices;

[0053] Among them, the element t in the i-th row and j-th column of the link matrix t ij Indicates whether there is a directly connected edge between the two corresponding vertices. In one embodiment, the path length t corresponding to the i-th device and the j-th device ij The determination method can be: if the edge formed by the i-th device and the j-th device belongs to the edge set formed by the multiple edges, then t ij is 1, otherwise t ij is positive infinity. It can be expressed as the following formula:

[0054]

[0055] S170: Construct an integer linear programming model based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set;

[0056] The objective function may include:

[0057]

[0058] Wherein, T is the time period set, k is the time period; m is the data flow number, TS is the data flow set; i and j are the device numbers in the device set, V is the device set, and the device set includes the source host set, the destination host set, and the switch set, and the device is a source host, a destination host, or a switch; p m is the priority of the mth data stream; t ij Characterizes the path length between the i-th device and the j-th device in the device set; x mijk is the decision variable corresponding to the mth data flow between the i-th device and the j-th device in the k-th time period.

[0059] It can be seen that the objective function is to minimize the weighted sum of the transmission path lengths of all data flows.

[0060] Among them, the decision variable x mijk The determination method can be: if the mth data stream is transmitted from the ith device to the jth device in the kth time period, then x mijk is 1, otherwise x mijk is 0. It can be expressed as the following formula:

[0061]

[0062] The constraints of the integer linear programming model may include:

[0063]

[0064] Where q is the number of the switch, Q is the set of switches, V d is the host set, V s is the source host set, d m is the number of the destination host corresponding to the mth data stream, s m The number of the source host corresponding to the mth data flow.

[0065] It can be seen that the first constraint is the switch node constraint in the network path, which ensures that the in-degree and out-degree of all switch nodes are the same for any data flow in any time period. The second constraint is the source host node constraint. For any data flow in all time periods, the out-degree of the source host of the data flow is 1, that is, the source host only sends one data flow in one time period. The third constraint is the destination host node constraint. For any data flow in all time periods, the in-degree of the destination host of the data flow is 1, that is, the destination host only receives one data flow in one time period. The combined constraints of the first to third constraints can ensure that each data flow is transmitted within a time period and the transmission path is connected. Among them, V s ={s m|m∈TS},V d ={d m |m∈TS}. The fourth constraint states that any link can transmit at most one data stream in a single direction within any time period. The fifth constraint is the value range of the decision variable.

[0066] S180. Solve the integer linear programming model to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize switches that each data flow needs to pass through during transmission from a corresponding source host to a corresponding destination host.

[0067] It can be understood that the time period for the source host of the data stream to send data to the destination host is fixed; the transmission speed of the data stream from the source host to the destination host is a fixed bit rate; all devices synchronize the clocks through the precision time protocol; and the minimum time slot of the time period can complete the transmission of a single transmission unit.

[0068] For example, the number of data flows is 5, the number of source hosts is 5, the number of destination hosts is 5, and the number of switches is 7.

[0069] In one embodiment, the data flow is a delay-sensitive data flow; the acquisition process of the delay-sensitive data flow may include: for the data flow collected by the open platform unified architecture, using the delay-sensitive network protocol to identify the delay-sensitive data flow as the delay-sensitive data flow.

[0070] As can be seen, the embodiments of the present invention target latency-sensitive data flows, i.e., data flows that are sensitive to latency. Specifically, data flows are collected based on an open platform unified architecture, then identified based on a latency-sensitive network protocol, and then the above steps S110 to S180 are executed on the latency-sensitive data flows. The latency-sensitive data flows can be transferred from the source host to the destination host via a complex network topology through a publish-subscribe mechanism.

[0071] In one embodiment, see Figure 2 The method can be implemented by the control plane, and the process of transmitting data streams according to the network routing scheduling strategy is implemented in the data transmission plane. The separation of the control plane and the transmission plane is based on software-defined networking.

[0072] As can be seen, the control plane executes S110 to S180, and the transport plane performs data transmission. The control plane and the transport plane are separate and implemented based on software-defined networking. That is, the embodiment of the present invention separates the control plane that implements the network routing scheduling algorithm from the transport plane of the data flow.

[0073] See Table 1 below, which lists the source host, destination host, and priority of the data flow, as well as the specific functions of different data flows.

[0074] Table 1 Data flow related information table

[0075]

[0076] like Figure 3 As shown in the figure, when multiple source hosts transmit data streams to the destination host via the same network route at the same time, the multiple data streams will be queued in the network route, which will greatly increase the transmission delay of the network route; at the same time, due to the uncertainty of the number of transmitted data streams, the transmission delay of the network data stream will also fluctuate greatly. This is the current status of scheduling. In the embodiment of the present invention, Figure 4 and Figure 5 These are two specific examples given in the examples of the present invention.

[0077] A small-scale calculation example is designed to illustrate the embodiments of the present invention, using a small production line as an example. The production line has multiple open platform unified architecture terminals that collect data. The collected data is sent to subscribing hosts via a specific network routing protocol. Table 1 shows the detailed data flow information. The mathematical model is solved using the above method, and the results are shown in Table 2.

[0078] Table 2 Data flow scheduling results

[0079] Data Flow Transmission path Transmission period 1 A-S1-S7-S6-F 1 2 B-S1-S7-S6-G 2 3 C-S1-S7-S6-H 3 4 D-S1-S2-S3-S6-I 2 5 E-S1-S4-S5-S6-J 1

[0080] The solution results show that all data streams are transmitted to the subscriber end via different paths in different time periods and are isolated in time and space, which can effectively reduce the transmission delay of the data stream and reduce the transmission delay jitter.

[0081] It can be seen that the embodiment of the present invention discloses a method for scheduling edge computing network routing based on a delay-sensitive network. The method is a technical solution that adopts an open platform unified architecture and integrates a delay-sensitive network protocol to isolate delay-sensitive data flows in time and space, thereby reducing the transmission delay and queuing delay of the data flow on the transmission link. In addition, the embodiment of the present invention solves the integer linear programming model to determine the scheduling scheme for network routing. Specifically, the embodiment of the present invention first determines the set of source hosts for sending data and the set of destination hosts for receiving information for edge computing, and then establishes an integer linear programming model based on the description of the undirected graph, and calls the solver based on the integer linear programming model to solve the mathematical model, and finally determines the scheduling scheme for network routing. In the above process, the embodiment of the present invention designs a path optimization method based on a delay-sensitive network by comprehensively considering the priority relationship of the data flow and the network path relationship, solves the edge computing data flow transmission problem in the industrial Internet field, reduces the transmission delay and queuing delay of the data flow, improves the efficiency of data transmission, and reduces the jitter of data transmission.

[0082] The fusion of an open platform unified architecture and a latency-sensitive network (LSN) is a solution proposed in this embodiment to address data transmission between different layers in an industrial edge computing network architecture. The open platform unified architecture addresses the semantic consistency issue of communication between different devices by establishing a targeted information model for industrial devices and employing publish-subscribe mechanisms. The latency-sensitive network (LSN) isolates latency-sensitive data flows in time and space by partitioning them, reducing transmission latency within the network topology.

[0083] Among them, the data flow transmission problem in the network topology is one of the key issues in the edge computing network architecture, and its scheduling algorithm is related to the transmission delay of the data flow and the delay determinism of the data transmission. However, due to the limited network path resources, delay-sensitive data flows need to queue in the links in the network switch to wait for the transmission of other data flows, which increases the transmission delay of the delay-sensitive data flow. Moreover, since the queuing time of the delay-sensitive data flow is uncertain, its transmission time often has large jitter. Based on this problem, the embodiment of the present invention separates the control plane from the data transmission plane based on the open platform unified architecture and the delay-sensitive network protocol, describes the problem as an integer linear programming model based on an undirected graph, and solves it to obtain the data flow network routing decision result, which effectively reduces the transmission delay of the data flow and reduces the transmission jitter of the data flow. Based on the delay-sensitive network, the embodiment of the present invention takes into account the priority of the data flow and the network topology structure, and provides a new research idea for the data flow network routing scheduling problem of the edge computing network architecture.

[0084] The embodiments of the present invention have the following beneficial effects:

[0085] 1. Comprehensively considering the complex network topology of the source host, destination host and switch, as well as the priority of the data flow, can reduce the transmission delay of the data flow.

[0086] 2. It uses a fusion of open platform unified architecture and latency-sensitive network protocols, and provides a specific integer linear programming model to effectively reduce jitter in data stream transmission latency. Based on a software-defined network architecture with a separation of control and data planes, it is effectively applicable to edge computing network architecture deployments in the industrial internet sector.

[0087] Of course, in the embodiments of the present invention, the heterogeneity of on-site operation equipment manufacturers and interface protocols in the industrial Internet field can be taken into consideration, while the time and space separation of data stream transmission is taken into consideration, and specific definitions of industrial field equipment, switch nodes, and network topology structures are given. The embodiments of the present invention can be applied to edge computing network routing scheduling problems in the industrial Internet field.

[0088] In a second aspect, an embodiment of the present invention provides a device for determining a routing scheduling strategy for an edge computing network, see Figure 6 , the apparatus 100 comprises:

[0089] A first determining module 110 is configured to determine a source host set formed by source hosts that send data streams and a destination host set formed by destination hosts that receive data streams; wherein the source hosts are industrial infrastructure devices in the edge computing network, and the destination hosts are edge computing nodes or cloud computing nodes in the edge computing network;

[0090] A second determining module 120 is configured to determine a switch set formed by switches between the source host and the destination host;

[0091] The third determining module 130 is configured to determine a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period;

[0092] A fourth determining module 140 is configured to determine the priority of each data flow in the data flow set;

[0093] a fifth determining module 150 configured to determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, wherein the vertices are hosts in the source host set, hosts in the destination host set, or switches in the switch set, and an edge between two vertices is a data stream transmission link between the two vertices;

[0094] A sixth determining module 160 is configured to determine a corresponding link matrix according to the data stream transmission network topology structure; wherein each element in the link matrix indicates whether there is a directly connected edge between corresponding two vertices;

[0095] A model construction module 170 is configured to construct an integer linear programming model based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set;

[0096] The model solving module 180 is used to solve the integer linear programming model to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize the switches that each data flow needs to pass through during the transmission process from the corresponding source host to the corresponding destination host.

[0097] In one embodiment, the objective function includes:

[0098]

[0099] Wherein, T is the time period set, k is the time period; m is the data flow number, TS is the data flow set; i and j are the device numbers in the device set, V is the device set, and the device set includes the source host set, the destination host set, and the switch set, and the device is a source host, a destination host, or a switch; p m is the priority of the mth data stream; t ij Characterizes the path length between the i-th device and the j-th device in the device set; x mijk is the decision variable corresponding to the mth data flow between the i-th device and the j-th device in the k-th time period.

[0100] In one embodiment, the decision variable x mijk The determination method is: if the mth data stream is transmitted from the ith device to the jth device in the kth time period, then x mijk is 1, otherwise x mijk is 0.

[0101] In one embodiment, the path length t corresponding to the i-th device and the j-th device is ij The determination method is: if the edge formed by the i-th device and the j-th device belongs to the edge set formed by the multiple edges, then t ij is 1, otherwise t ij Is positive infinity.

[0102] In one embodiment, the constraints of the integer linear programming model include:

[0103]

[0104]

[0105] Where q is the number of the switch, Q is the set of switches, V d is the host set, V s is the source host set, d m is the number of the destination host corresponding to the mth data stream, s m The number of the source host corresponding to the mth data flow.

[0106] In one embodiment, the data flow is a delay-sensitive data flow; the acquisition process of the delay-sensitive data flow includes: for the data flow collected by the open platform unified architecture, using the delay-sensitive network protocol to identify the delay-sensitive data flow as the delay-sensitive data flow.

[0107] In one embodiment, the device is implemented by a control plane, and the process of transmitting data streams according to the network routing scheduling strategy is implemented in the data transmission plane. The separation of the control plane and the transmission plane is based on software-defined networking.

[0108] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the device provided by the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0109] In a third aspect, an embodiment of the present invention provides a computer-readable medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0110] Specifically, a system or device equipped with a storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program codes stored in the storage medium.

[0111] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0112] Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0113] In addition, it should be clear that the functions of any of the above embodiments can be achieved not only by executing the program code read by the computer, but also by enabling the operating system operating on the computer to complete part or all of the actual operations based on the instructions of the program code.

[0114] In addition, it can be understood that the program code read from the storage medium is written into a memory provided in an expansion board inserted into the computer or into a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above embodiments.

[0115] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0116] In a fourth aspect, an embodiment of this specification provides a computing device, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method in any one of the embodiments in the specification.

[0117] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the computing device provided by the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0118] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0119] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention may be implemented using hardware, software, widgets, or any combination thereof. When implemented using software, these functions may be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0120] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for determining a routing scheduling strategy for an edge computing network, characterized in that: include: Determine a source host set formed by each source host sending a data stream and a destination host set formed by each destination host receiving a data stream; wherein the source host is an industrial underlying device in the edge computing network, and the destination host is an edge computing node or a cloud computing node in the edge computing network; Determine a switch set formed by switches between the source host and the destination host; Determine a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period; Determining the priority of each data flow in the data flow set; Determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, the vertices being hosts in the source host set, hosts in the destination host set, or switches in the switch set, and the edges between two vertices being data stream transmission links between the two vertices; Determine a corresponding link matrix according to the data stream transmission network topology structure; wherein each element in the link matrix indicates whether there is a directly connected edge between the corresponding two vertices; An integer linear programming model is constructed based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set; The integer linear programming model is solved to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize the switches that each data flow needs to pass through during the transmission process from the corresponding source host to the corresponding destination host.

2. The method according to claim 1, characterized in that The objective function includes: Wherein, T is the time period set, k is the time period; m is the data flow number, TS is the data flow set; i and j are the device numbers in the device set, V is the device set, and the device set includes the source host set, the destination host set, and the switch set, and the device is a source host, a destination host, or a switch; p m is the priority of the mth data stream; t ij Characterizes the path length between the i-th device and the j-th device in the device set; x mijk is the decision variable corresponding to the mth data flow between the i-th device and the j-th device in the k-th time period.

3. The method according to claim 2, characterized in that The decision variable x mijk The determination method is: if the mth data stream is transmitted from the ith device to the jth device in the kth time period, then x mijk is 1, otherwise x mijk is 0.

4. The method according to claim 2, characterized in that The path length t between the i-th device and the j-th device ij The determination method is: if the edge formed by the i-th device and the j-th device belongs to the edge set formed by the multiple edges, then t ij is 1, otherwise t ij Is positive infinity.

5. The method according to claim 2, characterized in that The constraints of the integer linear programming model include: Where q is the number of the switch, Q is the set of switches, V d is the host set, V s is the source host set, d m is the number of the destination host corresponding to the mth data stream, s m The number of the source host corresponding to the mth data flow.

6. The method according to claim 1, characterized in that The data stream is a delay-sensitive data stream; The acquisition process of the delay-sensitive data flow includes: for the data flow collected by the open platform unified architecture, using the delay-sensitive network protocol to identify the delay-sensitive data flow as the delay-sensitive data flow.

7. The method according to claim 1, characterized in that The method is implemented by the control plane, and the process of transmitting data streams according to the network routing scheduling strategy is implemented in the data transmission plane. The separation of the control plane and the transmission plane is based on software-defined networking.

8. A device for determining a routing scheduling strategy for an edge computing network, characterized in that: include: A first determination module is configured to determine a source host set formed by each source host sending a data stream and a destination host set formed by each destination host receiving a data stream; wherein the source host is an industrial underlying device in the edge computing network, and the destination host is an edge computing node or a cloud computing node in the edge computing network; A second determining module is configured to determine a switch set formed by switches between the source host and the destination host; A third determining module is used to determine a data flow set formed by each data flow that each source host in the source host set needs to send within a time period and a time period set formed by each time period within the time period; A fourth determining module, configured to determine the priority of each data flow in the data flow set; a fifth determining module, configured to determine a data stream transmission network topology structure; wherein the data stream transmission network topology structure includes a plurality of vertices and a plurality of edges, wherein the vertices are hosts in the source host set, hosts in the destination host set, or switches in the switch set, and an edge between two vertices is a data stream transmission link between the two vertices; a sixth determining module, configured to determine a corresponding link matrix according to the data stream transmission network topology; wherein each element in the link matrix indicates whether there is a directly connected edge between corresponding two vertices; a model construction module, configured to construct an integer linear programming model based on the source host set, the destination host set, the switch set, the data flow set, the time period set, the priority of each data flow in the data flow set, and the link matrix; wherein the objective function of the integer linear programming model is to minimize the sum of the transmission delays of all data flows in the data flow set; A model solving module is used to solve the integer linear programming model to obtain a network routing scheduling strategy; wherein the network routing scheduling strategy is used to characterize the switches that each data flow needs to pass through during the transmission process from the corresponding source host to the corresponding destination host.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

10. A computing device, characterized in that The method comprises a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method according to any one of claims 1 to 7 is implemented.

Images