Service request processing method and device and terminal equipment

Abstract

The invention provides a service request processing method and apparatus, and a terminal device. The method comprises the steps of receiving a service request uploaded to a local edge computing terminal by a service request node in a current region, and calculating a first delay required by the local edge computing terminal to process the service request based on a first delay calculation formula; performing interaction attribute judgment on the local edge computing terminal, and distributing a processing object of the service request based on an interaction attribute judgment result; when the local edge computing terminal does not have the interaction attribute, distributing the service request to the local edge computing terminal; and when the local edge computing terminal has an interaction attribute, obtaining first service response nodes having an interaction relationship with the local edge computing terminal, calculating a second delay required for cooperating with the local edge computing terminal to process the service request based on each first service response node, and allocating the service request to the service response node with the minimum delay. According to the invention, the real-time performance and reliability of service processing of the power distribution network system can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a service request processing method, device and terminal equipment. Background Art

[0002] The distribution network is a component of the power system, responsible for further distributing the power transmitted by the high-voltage transmission network to end users. It includes distribution transformers, distribution lines, switchgear and other facilities. Its main function is to distribute the power from the high-voltage transmission network to various users after reducing the voltage to meet their electricity needs. With the continuous advancement of the construction of new power systems, modern distribution networks are increasingly using intelligent devices (such as smart meters, sensors, and automatic switches). The distribution network has become a place where massive distributed power sources, energy storage devices, flexible loads and other objects are widely connected. These devices generate a large number and types of distribution network services / data, which need to be processed and analyzed. Most of the existing distribution network business processing adopts the master-substation data processing method. The terminal equipment uses sensors or low-voltage carrier channels to transmit data to nearby substations, and the information in the substation aggregation area is then uploaded to the cloud computing center; some areas have also deployed edge computing terminals on the basis of the original substations or transformers in the substation area, and built the main station into a cloud computing center (hereinafter referred to as the cloud), and some of the business functions of the cloud computing center are transferred to the edge computing terminal. If the edge computing terminal cannot meet the needs, the business will be uploaded to the cloud computing center for processing.

[0003] However, the business processing method of the above-mentioned master-substation depends on the resources of the master station and network communication resources, which is easy to cause network resource congestion on the master station side and affect the data processing capacity of the master station; secondly, under the processing method of cloud and unilateral collaboration, the edge computing terminal at the substation only interacts with the cloud computing center, and the resource utilization method is relatively single, and the synergy of intelligent devices is not fully utilized. How to provide a more advanced distributed data processing method is of great significance to improving the real-time and reliability of data processing in the distribution network system. Summary of the invention

[0004] The present invention aims to provide a business request processing method, device and terminal equipment to solve the above technical problems and improve the real-time performance and reliability of business data processing in the distribution network system.

[0005] In order to solve the above technical problems, the present invention provides a service request processing method, comprising:

[0006] Receive a service request uploaded by a service request node in a current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula;

[0007] Performing interaction attribute judgment on the local edge computing terminal, and allocating the processing object of the service request based on the interaction attribute judgment result; wherein the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining service response nodes in the distribution network have interaction conditions;

[0008] When the local edge computing terminal does not have an interactive attribute, allocating the service request to the local edge computing terminal so that the local edge computing terminal processes the received service request;

[0009] When the local edge computing terminal has an interactive attribute, a first business response node that has an interactive relationship with the local edge computing terminal is obtained, and a second delay required for each of the first business response nodes to cooperate with the local edge computing terminal to process the business request is calculated, and the business request is allocated to the business response node with the smallest delay.

[0010] In the above scheme, by introducing local edge computing terminals, the business request processing tasks are dispersed to each edge computing node, which effectively reduces the load of the main station and the network transmission delay, so that the pressure on the network resource usage of the main station is relieved, thereby improving the processing capacity of the main station. Using edge computing terminals to perform preliminary processing of business requests and optimizing the processing path of requests in combination with delay calculation formulas can greatly reduce the overall processing delay. By allocating business requests to the most suitable processing nodes, the system can process business requests more efficiently and improve real-time response capabilities. Under the architecture of business collaborative processing, the edge computing terminal of the substation can dynamically select processing nodes according to actual conditions and interaction attributes. This flexible processing mechanism enables the system to cope with the processing requirements of different business requests and improves the robustness and elasticity of the overall system.

[0011] In one implementation, calculating the first delay required for the local edge computing terminal to process the service request based on the first delay calculation formula specifically includes:

[0012] The first delay required for the local edge computing terminal to process the service request is calculated based on a first delay calculation formula; wherein the first delay includes calculation delay and communication delay, and the expression of the first delay calculation formula is:

[0013]

[0014] w 边,e =∑ a w a x a,e ;

[0015]

[0016] Where, t边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e is the computing resource capacity of the edge computing terminal e; w a is the computing load of business a; x a,e It is the mapping relationship between service a and edge computing terminal e, and its values ​​are 0 and 1.

[0017] In one implementation, the determining of the interaction attribute of the local edge computing terminal specifically includes:

[0018] When there is a completed interactive communication network between the local edge computing terminal and other business response nodes and the business response nodes have undergone software authentication, it is determined that the local edge computing terminal has the interactive attribute.

[0019] In one implementation, obtaining a first service response node that has an interactive relationship with the local edge computing terminal, and calculating a second delay based on each of the first service response nodes cooperating with the local edge computing terminal to process the service request specifically includes:

[0020] Monitor the operation status information of the local edge computing terminal in real time and control the local edge computing terminal to send the operation status information to the first edge computing terminal; wherein the first edge computing terminal is an edge computing terminal in an adjacent area;

[0021] Acquire a first service response node that has an interactive relationship with the local edge computing terminal, and control the local edge computing terminal to forward the service requests of a preset proportion to the first service response node; wherein the first service response node includes any one or both of a cloud master station and a first edge computing terminal;

[0022] When the first service response node is the cloud master, calculating a second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on a second delay calculation formula;

[0023] When the first service response node is the first edge computing terminal, a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request is calculated based on a third delay calculation formula.

[0024] In one implementation, the calculating, based on the second delay calculation formula, the second delay for the cloud master to collaborate with the local edge computing terminal to process the service request specifically includes:

[0025] The first computing delay required for the cloud master to process the business requests of a preset proportion and the first communication delay generated by the cloud master interacting with the local edge computing terminal are calculated based on the second delay calculation formula; wherein the expression of the second delay calculation formula is:

[0026]

[0027] w 云 =∑ a w a y a,云 ;

[0028]

[0029] Where, t 云 w is the first computing delay generated when the cloud master station processes the business; 云 is the total computing load of the services undertaken by the cloud master; 云 is the computing resource capacity of the cloud master station; y a,云 is the mapping relationship between business a and the cloud master station; w a is the computing load of business a; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; v 云,e It is the communication resource capacity when the cloud master station interacts with the edge computing terminal e;

[0030] The first computing delay and the first communication delay are combined to generate a second delay for the cloud master to collaborate with the local edge computing terminal to process the business request.

[0031] In one implementation, the calculating, based on the third delay calculation formula, the third delay for the first edge computing terminal to collaborate with the local edge computing terminal to process the service request specifically includes:

[0032] The second communication delay generated by the interaction between the first edge computing terminal and the local edge computing terminal is calculated based on the third delay calculation formula; wherein the expression of the third delay calculation formula is:

[0033]

[0034] In the formula, c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; v 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2;

[0035] Calculate, based on the first delay calculation formula, a fourth delay required for the first edge computing terminal to process a preset proportion of the service requests;

[0036] The second communication delay and the fourth delay are combined to generate a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request.

[0037] In one implementation, when controlling the local edge computing terminal to forward the service requests of a preset proportion to the first service response node, resource constraints and delay constraints need to be performed, specifically:

[0038] Forwarding the service requests of the preset proportion to the first service response node; wherein the resources occupied by the service requests of the preset proportion shall not exceed the resources allocated by the first service response node;

[0039] Based on the resource restriction formula, resource restriction is performed on the service request forwarded by the local edge computing terminal; wherein the expression of the resource restriction formula is:

[0040]

[0041] In the formula, s 边,max 、s 云,max are the maximum computing resource capacities of the first edge computing terminal and the cloud master station respectively; v 边,e1,e2，min is the minimum value of the communication resource capacity between edge computing terminal e1 and edge computing terminal e2; v 云,e，min is the minimum value of the communication resource capacity between the cloud master and the edge computing terminal e;

[0042] The service request received by the first service response node is subjected to a delay constraint based on a delay constraint formula; wherein the delay constraint formula is expressed as follows:

[0043] t 边,e x a,e +t 云 y a,云 +c 边,e1,e2 x a,e1 x a,e2 +c 云,e x a,e y a,云 ≤T a ;

[0044] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; x a,e is the mapping relationship between service a and edge computing terminal e; t 云The first computing delay generated when the cloud master station processes the business; y a,云 is the mapping relationship between business a and the cloud master station; c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay generated during the interaction; x a,e1 The mapping relationship between service a and edge computing terminal e1; x a,e2 The mapping relationship between service a and edge computing terminal e2; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; T a is the delay tolerance of service a.

[0045] In one implementation, the service request processing method further includes: optimizing the allocation of the service request based on a preset objective function; wherein the preset objective function aims at minimizing delay, and the expression of the preset objective function is:

[0046] min f(a)=f1(a)+f2(a);

[0047] f1(a)=∑ a (t 边,e +t 云 );

[0048] f2(a)=∑ a (c 边,e +c 边,e1,e2 +c 云,e );

[0049] Where min f(a) is the minimum delay; f1(a) is the calculation delay; f2(a) is the communication delay; t 边,e Processing business computing load w for edge computing terminal e 边,e The calculation delay generated; t 云 The first computing delay generated when the cloud master station processes the business; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay caused by the interaction; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction.

[0050] In a second aspect, the present application further provides a service request processing device, including: a request receiving module, an attribute determination module, a first allocation module, and a second allocation module;

[0051] The request receiving module is used to receive a service request uploaded by a service request node in the current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula;

[0052] The attribute judgment module is used to perform interaction attribute judgment on the local edge computing terminal, and allocate the processing object of the business request based on the interaction attribute judgment result; wherein, the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining business response nodes in the distribution network have interaction conditions;

[0053] The first allocation module allocates the service request to the local edge computing terminal when the local edge computing terminal does not have an interactive attribute so that the local edge computing terminal processes the received service request;

[0054] The second allocation module is used to obtain the first business response node that has an interactive relationship with the local edge computing terminal when the local edge computing terminal has an interactive attribute, and calculate the second delay required for each first business response node to cooperate with the local edge computing terminal to process the business request, and allocate the business request to the business response node with the smallest delay.

[0055] In the above scheme, by introducing local edge computing terminals, the business request processing tasks are dispersed to each edge computing node, which effectively reduces the load of the main station and the network transmission delay, so that the pressure on the network resource usage of the main station is relieved, thereby improving the processing capacity of the main station. Using edge computing terminals to perform preliminary processing of business requests and optimizing the processing path of requests in combination with delay calculation formulas can greatly reduce the overall processing delay. By allocating business requests to the most suitable processing nodes, the system can process business requests more efficiently and improve real-time response capabilities. Under the architecture of business collaborative processing, the edge computing terminal of the substation can dynamically select processing nodes according to actual conditions and interaction attributes. This flexible processing mechanism enables the system to cope with the processing requirements of different business requests and improves the robustness and elasticity of the overall system.

[0056] In one implementation, calculating the first delay required for the local edge computing terminal to process the service request based on the first delay calculation formula specifically includes:

[0057] The first delay required for the local edge computing terminal to process the service request is calculated based on a first delay calculation formula; wherein the first delay includes calculation delay and communication delay, and the expression of the first delay calculation formula is:

[0058]

[0059] w 边,e =∑ a w a x a,e ;

[0060]

[0061] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e is the computing resource capacity of the edge computing terminal e; w a is the computing load of business a; x a,e It is the mapping relationship between service a and edge computing terminal e, and its values ​​are 0 and 1.

[0062] In one implementation, the determining of the interaction attribute of the local edge computing terminal specifically includes:

[0063] When there is a completed interactive communication network between the local edge computing terminal and other business response nodes and the business response nodes have undergone software authentication, it is determined that the local edge computing terminal has the interactive attribute.

[0064] In one implementation, obtaining a first service response node that has an interactive relationship with the local edge computing terminal, and calculating a second delay based on each of the first service response nodes cooperating with the local edge computing terminal to process the service request specifically includes:

[0065] Monitor the operation status information of the local edge computing terminal in real time and control the local edge computing terminal to send the operation status information to the first edge computing terminal; wherein the first edge computing terminal is an edge computing terminal in an adjacent area;

[0066] Acquire a first service response node that has an interactive relationship with the local edge computing terminal, and control the local edge computing terminal to forward the service requests of a preset proportion to the first service response node; wherein the first service response node includes any one or both of a cloud master station and a first edge computing terminal;

[0067] When the first service response node is the cloud master, calculating a second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on a second delay calculation formula;

[0068] When the first service response node is the first edge computing terminal, a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request is calculated based on a third delay calculation formula.

[0069] In one implementation, the calculating, based on the second delay calculation formula, the second delay for the cloud master to collaborate with the local edge computing terminal to process the service request specifically includes:

[0070] The first computing delay required for the cloud master to process the business requests of a preset proportion and the first communication delay generated by the cloud master interacting with the local edge computing terminal are calculated based on the second delay calculation formula; wherein the expression of the second delay calculation formula is:

[0071]

[0072] w 云 =∑ a w a y a,云 ;

[0073]

[0074] Where, t 云 w is the first computing delay generated when the cloud master station processes the business; 云 is the total computing load of the services undertaken by the cloud master; 云 is the computing resource capacity of the cloud master station; a,云 is the mapping relationship between business a and the cloud master station; w a is the computing load of business a; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; v 云,e It is the communication resource capacity when the cloud master station interacts with the edge computing terminal e;

[0075] The first computing delay and the first communication delay are combined to generate a second delay for the cloud master to collaborate with the local edge computing terminal to process the business request.

[0076] In one implementation, the calculating, based on the third delay calculation formula, the third delay for the first edge computing terminal to collaborate with the local edge computing terminal to process the service request specifically includes:

[0077] The second communication delay generated by the interaction between the first edge computing terminal and the local edge computing terminal is calculated based on the third delay calculation formula; wherein the expression of the third delay calculation formula is:

[0078]

[0079] In the formula, c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; v 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2;

[0080] Calculate, based on the first delay calculation formula, a fourth delay required for the first edge computing terminal to process a preset proportion of the service requests;

[0081] The second communication delay and the fourth delay are combined to generate a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request.

[0082] In one implementation, when controlling the local edge computing terminal to forward the service requests of a preset proportion to the first service response node, resource constraints and delay constraints need to be performed, specifically:

[0083] Forwarding the service requests of the preset proportion to the first service response node; wherein the resources occupied by the service requests of the preset proportion shall not exceed the resources allocated by the first service response node;

[0084] Based on the resource restriction formula, resource restriction is performed on the service request forwarded by the local edge computing terminal; wherein the expression of the resource restriction formula is:

[0085]

[0086] In the formula, s 边,max 、s 云,max are the maximum computing resource capacities of the first edge computing terminal and the cloud master station respectively; v 边,e1,e2，min is the minimum value of the communication resource capacity between edge computing terminal e1 and edge computing terminal e2; v 云,e，min is the minimum value of the communication resource capacity between the cloud master and the edge computing terminal e;

[0087] The service request received by the first service response node is subjected to a delay constraint based on a delay constraint formula; wherein the delay constraint formula is expressed as follows:

[0088] t 边,e x a,e +t 云 y a,云 +c 边,e1,e2 x a,e1 x a,e2 +c 云,e x a,ey a,云 ≤T a ;

[0089] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; x a,e is the mapping relationship between service a and edge computing terminal e; t 云 The first computing delay generated when the cloud master station processes the business; y a,云 is the mapping relationship between business a and the cloud master station; c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay generated during the interaction; x a,e1 The mapping relationship between service a and edge computing terminal e1; x a,e2 The mapping relationship between service a and edge computing terminal e2; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; T a is the delay tolerance of service a.

[0090] In one implementation, the service request processing device further includes: optimizing the allocation of the service request based on a preset objective function; wherein the preset objective function aims at minimizing delay, and the expression of the preset objective function is:

[0091] min f(a)=f1(a)+f2(a);

[0092] f1(a)=∑ a (t 边,e +t 云 );

[0093] f2(a)=∑ a (c 边,e +c 边,e1,e2 +c 云,e );

[0094] Where min f(a) is the minimum delay; f1(a) is the calculation delay; f2(a) is the communication delay; t 边,e Processing business computing load w for edge computing terminal e 边,e The calculation delay generated; t 云 The first computing delay generated when the cloud master station processes the business; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2边,e1,e2 The communication delay caused by the interaction; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction.

[0095] In a third aspect, the present application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the service request method as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 A flowchart of a method for processing a service request provided in one embodiment of the present invention;

[0097] Figure 2 A cloud-edge multi-agent collaborative distribution network business processing architecture provided in one embodiment of the present invention;

[0098] Figure 3 A flowchart of a feasible embodiment of a service request processing method provided in an embodiment of the present invention;

[0099] Figure 4 A module diagram of a service request processing method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0100] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0101] The terms "first" and "second" and the like in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0102] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0103] First, some terms in this application are explained to facilitate understanding by those skilled in the art.

[0104] (1) Edge computing terminals: They are key components in the edge computing architecture and refer to computing devices or systems that process and analyze data near the data source. By processing data close to the data source, they can reduce data transmission delays, reduce the burden on the central cloud computing platform, and provide faster response speeds.

[0105] Example 1

[0106] See also Figure 1 , Figure 1 The flowchart of a service request processing method provided in an embodiment of the present invention is as follows. The embodiment of the present invention provides a service request processing method, including steps 101 to 104, and each step is specifically as follows:

[0107] Step 101: Receive a service request uploaded by a service request node in the current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula.

[0108] In an embodiment of the present invention, a service request processing method is provided, which receives a service request uploaded by a service request node in a current distribution network area to a local edge computing terminal, and the local edge computing terminal is used to undertake the service requested by the service request node in the current area. Figure 2 , Figure 2A cloud-edge multi-agent collaborative distribution network business processing architecture provided in one embodiment of the present invention. In the distribution network business processing architecture, the business request node is a data source node, which is used to generate business data to be processed in the distribution network, generally an electric power user or electric power equipment. Business response nodes, also known as resource supply nodes, include edge computing terminals and cloud master stations. Among them, in the traditional master-substation distribution network business processing architecture, the edge computing terminal is deployed at the substation, and the cloud master station is deployed at the distribution master station. Among them, the communication link is a data channel for communicating business request nodes (data source nodes), edge computing terminals, and cloud master stations, and the uploading and sending of data are completed by the communication link; the power line is the path for system power transmission, completing the transmission of electric energy. The local edge computing terminal undertakes the business requested by the data source node in the area, and is the only intelligent device for the data source node to interact, that is, an edge computing terminal will be deployed in each area as a local edge computing terminal. Due to the differences in the types and data of data source nodes in different areas, the types and quantities of business requested to the local edge computing terminal are different. Generally, the service type requested by the service request node is determined according to the object monitored by the service request node. If the service request node represents a reactive power regulation device, the service request sent to the local edge computing terminal generally includes the status of the reactive power regulation device, the adjustable capacity, the voltage and current of the current node, etc.; in addition, the service request node can also send service requests such as switch status, current direction, protection device action information, equipment event information, photovoltaic or wind turbine processing size, and charging and discharging status of energy storage devices to the service response node.

[0109] In one embodiment, the calculating, based on the first delay calculation formula, the first delay required for the local edge computing terminal to process the service request specifically includes:

[0110] The first delay required for the local edge computing terminal to process the service request is calculated based on a first delay calculation formula; wherein the first delay includes calculation delay and communication delay, and the expression of the first delay calculation formula is:

[0111]

[0112] w 边,e =∑ a w a x a,e ;

[0113]

[0114] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; c 边,e Processing transmission data volume u for edge computing terminal e 边,eThe communication delay caused by the data 边,e is the computing resource capacity of the edge computing terminal e; w a is the computing load of business a; x a,e It is the mapping relationship between service a and edge computing terminal e, and its values ​​are 0 and 1.

[0115] In the embodiment of the present invention, the first delay calculation formula is used to calculate the first delay required for a single edge computing terminal to process a service request; wherein the first delay includes calculation delay and communication delay. 边,e The size of is related to the type and quantity of services undertaken by the edge computing terminal e. The mapping relationship between services and edge computing terminals means that if the edge computing terminal e undertakes to process service a, the mapping relationship between the two is 1, and if service a is not processed by the edge computing terminal e, the mapping relationship between the two is 0.

[0116] Step 102: Perform interaction attribute judgment on the local edge computing terminal, and allocate the processing object of the business request based on the interaction attribute judgment result; the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining business response nodes in the distribution network have interaction conditions.

[0117] In one embodiment, the interactive attribute judgment of the local edge computing terminal specifically includes: when there is a completed interactive communication network between the local edge computing terminal and other business response nodes and the business response nodes have undergone software authentication, it is determined that the local edge computing terminal has the interactive attribute.

[0118] In the implementation of the present invention, what kind of business processing method / what processing object is assigned to the business request uploaded by the business request node depends on whether the local edge computing terminal has interactive attributes. Whether the local edge computing terminal and the remaining business response nodes have the conditions for interaction: one is to determine whether the two parties to the interaction have built an interactive communication network; the other is to determine whether the two parties to the interaction have passed the software certification. Ensure that the network connection between the edge computing terminal and other edge terminals or cloud master stations is stable and available. This includes physical networks (such as wired or wireless connections) and network configurations (such as IP address allocation, network protocol support). The interactive communication network is used to achieve the integration of different devices and systems, enabling them to work together and share resources and information. Ensure that data can be transmitted smoothly between the edge terminal and the cloud master station, and support data synchronization, backup and sharing. Software certification is used to confirm that the communication software of the local edge computing terminal and other business response nodes is certified and compatible with each other. This includes API interface compatibility, data format matching, etc. It can ensure that the data transmission and processing results between different systems are consistent, avoiding data errors caused by software compatibility issues. Judging whether the local edge computing terminal is capable of interacting with other response nodes involves ensuring the stability of network connections and communication protocols, as well as the compatibility and security of software. These criteria help ensure that the system can operate normally, avoid service interruptions caused by network or software problems, optimize data transmission and processing, improve the performance and response speed of the overall system, prevent data leakage or tampering, and protect the data privacy of the system and users.

[0119] Step 103: When the local edge computing terminal does not have an interactive attribute, the service request is allocated to the local edge computing terminal so that the local edge computing terminal processes the received service request.

[0120] In an embodiment of the present invention, if the local edge computing terminal does not have the conditions to interact with other business response nodes, the business request uploaded by the business request node can only be processed by the local edge computing terminal, that is, the local edge computing terminal.

[0121] Step 104: When the local edge computing terminal has an interactive attribute, obtain the first business response node that has an interactive relationship with the local edge computing terminal, and calculate the second delay required for each of the first business response nodes to cooperate with the local edge computing terminal to process the business request, and allocate the business request to the business response node with the smallest delay.

[0122] In an embodiment of the present invention, when the local edge computing terminal has interactive attributes, it is necessary to calculate the first delay required for the local edge computing terminal to process the business request, and the second delay generated by each first business response node cooperating with the local edge computing terminal to process the business request, select the processing object with smaller delay, and allocate the business request.

[0123] In one embodiment, the obtaining of the first business response node that has an interactive relationship with the local edge computing terminal, and the calculation of the second delay based on each first business response node cooperating with the local edge computing terminal to process the business request, specifically includes: real-time monitoring of the operating status information of the local edge computing terminal and controlling the local edge computing terminal to send the operating status information to the first edge computing terminal; wherein the first edge computing terminal is an edge computing terminal in an adjacent area; obtaining the first business response node that has an interactive relationship with the local edge computing terminal, and controlling the local edge computing terminal to forward a preset proportion of the business requests to the first business response node; wherein the first business response node includes any one or both of a cloud master station and a first edge computing terminal; when the first business response node is the cloud master station, the second delay of the cloud master station cooperating with the local edge computing terminal to process the business request is calculated based on a second delay calculation formula; when the first business response node is the first edge computing terminal, the third delay of the first edge computing terminal cooperating with the local edge computing terminal to process the business request is calculated based on a third delay calculation formula.

[0124] In an embodiment of the present invention, the operation status information of the local edge computing terminal is monitored in real time, wherein the operation status information includes the current idle resource capacity and the terminal operation status, and the local edge computing terminal is controlled to send its own operation status information to the edge computing terminal in the adjacent area, so that the edge computing terminals can undertake the services forwarded by other edge computing terminals according to their own idle resource capacity. When the local edge computing terminal has interactive attributes, the delay required for the local edge computing terminal and each first service response node to collaboratively process the service request is calculated respectively, and the collaborative processing scheme with the smallest delay is selected.

[0125] In one embodiment, the second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on the second delay calculation formula specifically includes:

[0126] The first computing delay required for the cloud master to process the business requests of a preset proportion and the first communication delay generated by the cloud master interacting with the local edge computing terminal are calculated based on the second delay calculation formula; wherein the expression of the second delay calculation formula is:

[0127]

[0128] w 云 =∑ a w a y a,云 ;

[0129]

[0130] Where, t 云 w is the first computing delay generated when the cloud master station processes the business; 云 is the total computing load of the services undertaken by the cloud master; 云 is the computing resource capacity of the cloud master station; a,云 is the mapping relationship between business a and the cloud master station; w a is the computing load of business a; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; v 云,e It is the communication resource capacity when the cloud master station interacts with the edge computing terminal e;

[0131] The first computing delay and the first communication delay are combined to generate a second delay for the cloud master to collaborate with the local edge computing terminal to process the business request.

[0132] When the first service response node is the cloud master, it is necessary to calculate the first computing delay required by the cloud master to process the service forwarded by the local edge computing terminal, and the first communication delay generated by the interaction between the local edge computing terminal and the cloud master is used as the total delay, that is, the second delay. a,云 It means that when business a is processed by the cloud master, business a is mapped to the cloud master. a,云 =1"; if service a is not processed by the cloud master, then "y a,云 =0".w 云 is the total computing load of the services undertaken by the cloud master, which is a cumulative amount. For example, the cloud master only processes service 1 (computational load is w1) and service 2 (computational load is w2), then “w 云 =w1+w2”; the cloud master station processes business 1 (computing load is w1), business 2 (computing load is w2), and business 3 (computing load is w3), then “w 云 =w1+w2+w3". And so on, we can get the total computing load of the cloud master station. 云 The computing resource capacity of the cloud master station depends on multiple aspects such as business needs, technical architecture, hardware resources, network bandwidth, security and reliability requirements, and cost budget, and is obtained based on specific actual conditions.

[0133] In one embodiment, the calculating, based on the third delay calculation formula, the third delay for the first edge computing terminal to collaborate with the local edge computing terminal to process the service request specifically includes:

[0134] The second communication delay generated by the interaction between the first edge computing terminal and the local edge computing terminal is calculated based on the third delay calculation formula; wherein the expression of the third delay calculation formula is:

[0135]

[0136] In the formula, c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; v 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2;

[0137] Based on the first delay calculation formula, the fourth delay required for the first edge computing terminal to process a preset proportion of the business requests is calculated; and the second delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the business requests is generated by combining the second communication delay and the fourth delay.

[0138] In the embodiment of the present invention, the third delay calculation formula is used to calculate the communication delay generated when two edge computing terminals perform data interaction, and the communication delay is equal to the data volume divided by the communication resource capacity. 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2, and it is the resource allocated to the service by the edge computing terminal, and its size is affected by the total amount of data transmitted by the edge computing terminal. Furthermore, it is necessary to calculate the fourth delay required for the first edge computing terminal to process the received service request according to the first delay calculation formula, wherein the delay includes calculation delay and communication delay. Combined with the second communication delay between the two edge computing terminals and the fourth delay required for the first edge computing terminal to process the service request, the third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request is generated.

[0139] In one embodiment, when controlling the local edge computing terminal to forward the service requests of a preset proportion to the first service response node, resource constraints and delay constraints need to be performed, specifically:

[0140] Forwarding the service requests of the preset proportion to the first service response node; wherein the resources occupied by the service requests of the preset proportion shall not exceed the resources allocated by the first service response node;

[0141] Based on the resource restriction formula, resource restriction is performed on the service request forwarded by the local edge computing terminal; wherein the expression of the resource restriction formula is:

[0142]

[0143] In the formula, s 边,max 、s 云,max are the maximum computing resource capacities of the first edge computing terminal and the cloud master station respectively; v 边,e1,e2，min is the minimum value of the communication resource capacity between edge computing terminal e1 and edge computing terminal e2; v 云,e，min is the minimum value of the communication resource capacity between the cloud master and the edge computing terminal e;

[0144] The service request received by the first service response node is subjected to a delay constraint based on a delay constraint formula; wherein the delay constraint formula is expressed as follows:

[0145] t 边,e x a,e +t 云 y a,云 +c 边,e1,e2 x a,e1 x a,e2 +c 云,e x a,e y a,云 ≤T a ;

[0146] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; x a,e is the mapping relationship between service a and edge computing terminal e; t 云 The first computing delay generated when the cloud master station processes the business; y a,云 is the mapping relationship between business a and the cloud master station; c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay generated during the interaction; x a,e1 The mapping relationship between service a and edge computing terminal e1; x a,e2 The mapping relationship between service a and edge computing terminal e2; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; T a is the delay tolerance of service a.

[0147] When using multiple topics for collaborative processing of distribution network services, certain constraints need to be imposed, including resource constraints and delay constraints. Resource constraints refer to the fact that when edge computing terminals or cloud master stations are used to process distribution services, the computing resources and communication resources that can be used by the services do not exceed the resources allocated by the edge computing terminals and cloud master stations. For example, the cloud master station interacts with the e-th edge computing terminal, and the amount of data interacted is 10MB. Then the “data volume u 云,e =10MB”; at the same time, the communication resources that can be used by the cloud master station and the e-th edge computing terminal for data exchange are 100MB / s, so the “communication resource capacity v 云,e =100MB / s", when the cloud master station and the e-th edge computing terminal interact with each other and transmit 10MB of data, the communication delay generated is 0.1s. The upper limit of the communication resource capacity depends on the bandwidth of the edge computing terminal. If the bandwidths of the two communicating parties are not equal, the smaller value of the two bandwidths is taken. Because the one with larger bandwidth completes data transmission first, its data transmission delay is smaller; while the one with smaller bandwidth takes a longer delay to fully receive the data. In the communication process, the delay generated from data transmission to reception is based on the delay of data being completely received. The lower limit is generally not less than 0, but considering that the processing delay of actual business is about The delay tolerance of service a refers to the maximum delay time that the distribution network can accept when processing services or responding to requests. This delay tolerance is crucial to ensuring the stability and efficient operation of the power system, and depends on multiple factors such as service type and demand, system architecture, network delay, system load, fault tolerance and redundancy design, service continuity requirements, and application design.

[0148] As an optimization scheme of an embodiment of the present invention, the service request processing method further includes: optimizing the allocation of the service request based on a preset objective function; wherein the preset objective function aims at minimizing the delay, and the expression of the preset objective function is:

[0149] min f(a)=f1(a)+f2(a);

[0150] f1(a)=∑ a (t 边,e +t 云 );

[0151] f2(a)=∑ a (c 边,e +c 边,e1,e2 +c 云,e );

[0152] Where min f(a) is the minimum delay; f1(a) is the calculation delay; f2(a) is the communication delay; t 边,e Processing business computing load w for edge computing terminal e 边,e The calculation delay generated; t 云 The first computing delay generated when the cloud master station processes the business; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction.

[0153] In the embodiment of the present invention, an objective function is established with the goal of minimizing delay, and the allocation of service requests is optimized. The following three aspects are mainly considered: first, after receiving the service request from the data source node, that is, the service request node, the edge computing terminal in each area calculates the required computing resources and forwards the information to other edge computing terminals. Second, the types and quantities of services undertaken by the edge computing terminal are optimized; third, the service scheduling between the cloud master station and the edge computing terminal is optimized. For the objective function, it is mainly divided into two parts: computing delay f1(a) and communication delay f2(a), and both are only related to the mapping relationship between the service in the edge computing terminal and the cloud master station. If the resources of the edge computing terminal are sufficient, each service can be completed by the local edge computing terminal, which can meet the delay constraint formula. If the resources of the edge computing terminal are insufficient, in order to meet the requirements of the delay constraint formula, the available resources in the distribution network system need to be called; if the total processing delay of the service is minimized, part of the communication delay can be sacrificed in exchange for a lower computing delay.

[0154] See also Figure 3 , Figure 3 A flowchart of a feasible embodiment of a service request processing method provided in one embodiment of the present invention. The local edge computing terminal receives the service request information uploaded by the data source node in the region, that is, the service request node; then calculates the first delay required for the local edge computing terminal to process the service, and the first delay includes the calculation delay and the communication delay; sends the idle resource capacity and the terminal operation status to the first edge computing terminal in the adjacent area; the local edge computing terminal decides to transfer part of the service to the edge computing terminal with more idle resource capacity, and analyzes the reduced calculation delay and increased communication delay; analyzes the increased communication delay and reduced calculation delay when transferring the edge computing terminal's service to the cloud master station; and then selects the service scheduling result with the smallest delay according to different delay calculation results.

[0155] In an embodiment of the present invention, a service request processing device is also provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above service request processing method is implemented.

[0156] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored computer program. When the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned service request processing method.

[0157] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the service request processing device.

[0158] The service request processing device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The service request processing device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art will appreciate that the above components are merely examples of the service request processing device and do not constitute a limitation on the service request processing device. The service request processing device may include more or fewer components than the components, or may combine certain components, or different components. For example, the service request processing device may also include input and output devices, network access devices, buses, and the like.

[0159] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the service request processing device, and uses various interfaces and lines to connect various parts of the entire service request processing device.

[0160] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the multi-device access platform processing device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0161] Wherein, if the service request processing module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0162] The embodiment of the present invention provides a method for processing business requests. By introducing a local edge computing terminal, the business request processing tasks are dispersed to each edge computing node, which effectively reduces the load of the main station and the network transmission delay, so that the pressure on the use of network resources of the main station is alleviated, thereby improving the processing capacity of the main station. The edge computing terminal is used to perform preliminary processing of the business request, and the processing path of the request is optimized in combination with the delay calculation formula, which can greatly reduce the overall processing delay. By allocating business requests to the most suitable processing node, the system can process business requests more efficiently and improve real-time response capabilities. Under the architecture of business collaborative processing, the edge computing terminal of the substation can dynamically select the processing node according to the actual situation and interaction attributes. This flexible processing mechanism enables the system to cope with the processing requirements of different business requests and improves the robustness and elasticity of the overall system.

[0163] Example 2

[0164] See also Figure 4 , Figure 4 The module diagram of a service request processing method provided in an embodiment of the present invention is as follows. The embodiment of the present invention provides a service request processing device, including: a request receiving module 201, an attribute judgment module 202, a first allocation module 203 and a second allocation module 204;

[0165] The request receiving module 201 is used to receive a service request uploaded by a service request node in the current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula;

[0166] The attribute judgment module 202 is used to perform interaction attribute judgment on the local edge computing terminal, and allocate the processing object of the business request based on the interaction attribute judgment result; wherein the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining business response nodes in the distribution network have interaction conditions;

[0167] When the local edge computing terminal does not have an interactive attribute, the first allocation module 203 allocates the service request to the local edge computing terminal so that the local edge computing terminal processes the received service request;

[0168] The second allocation module 204 is used to obtain the first business response node that has an interactive relationship with the local edge computing terminal when the local edge computing terminal has an interactive attribute, and calculate the second delay required for each first business response node to cooperate with the local edge computing terminal to process the business request, and allocate the business request to the business response node with the smallest delay.

[0169] In one embodiment, the calculating, based on the first delay calculation formula, the first delay required for the local edge computing terminal to process the service request specifically includes:

[0170] The first delay required for the local edge computing terminal to process the service request is calculated based on a first delay calculation formula; wherein the first delay includes calculation delay and communication delay, and the expression of the first delay calculation formula is:

[0171]

[0172] w 边,e =∑ a w a x a,e ;

[0173]

[0174] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e is the computing resource capacity of the edge computing terminal e; w a is the computing load of business a; x a,e It is the mapping relationship between service a and edge computing terminal e, and its values ​​are 0 and 1.

[0175] In one embodiment, the determining of the interaction attribute of the local edge computing terminal specifically includes:

[0176] When there is a completed interactive communication network between the local edge computing terminal and other business response nodes and the business response nodes have undergone software authentication, it is determined that the local edge computing terminal has the interactive attribute.

[0177] In one embodiment, obtaining a first service response node that has an interactive relationship with the local edge computing terminal, and calculating a second delay based on each first service response node cooperating with the local edge computing terminal to process the service request specifically includes:

[0178] Monitor the operation status information of the local edge computing terminal in real time and control the local edge computing terminal to send the operation status information to the first edge computing terminal; wherein the first edge computing terminal is an edge computing terminal in an adjacent area;

[0179] Acquire a first service response node that has an interactive relationship with the local edge computing terminal, and control the local edge computing terminal to forward the service requests of a preset proportion to the first service response node; wherein the first service response node includes any one or both of a cloud master station and a first edge computing terminal;

[0180] When the first service response node is the cloud master, calculating a second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on a second delay calculation formula;

[0181] When the first service response node is the first edge computing terminal, a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request is calculated based on a third delay calculation formula.

[0182] In one embodiment, the second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on the second delay calculation formula specifically includes:

[0183] The first computing delay required for the cloud master to process the business requests of a preset proportion and the first communication delay generated by the cloud master interacting with the local edge computing terminal are calculated based on the second delay calculation formula; wherein the expression of the second delay calculation formula is:

[0184]

[0185] w 云 =∑ a w a y a,云 ;

[0186]

[0187] Where, t 云 w is the first computing delay generated when the cloud master station processes the business; 云 is the total computing load of the services undertaken by the cloud master; 云 is the computing resource capacity of the cloud master station; a,云 is the mapping relationship between business a and the cloud master station; w a is the computing load of business a; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; v 云,e It is the communication resource capacity when the cloud master station interacts with the edge computing terminal e;

[0188] The first computing delay and the first communication delay are combined to generate a second delay for the cloud master to collaborate with the local edge computing terminal to process the business request.

[0189] In one embodiment, the calculating, based on the third delay calculation formula, the third delay for the first edge computing terminal to collaborate with the local edge computing terminal to process the service request specifically includes:

[0190] The second communication delay generated by the interaction between the first edge computing terminal and the local edge computing terminal is calculated based on the third delay calculation formula; wherein the expression of the third delay calculation formula is:

[0191]

[0192] In the formula, c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; v 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2;

[0193] Calculate, based on the first delay calculation formula, a fourth delay required for the first edge computing terminal to process a preset proportion of the service requests;

[0194] The second communication delay and the fourth delay are combined to generate a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request.

[0195] In one embodiment, when controlling the local edge computing terminal to forward the service requests of a preset proportion to the first service response node, resource constraints and delay constraints need to be performed, specifically:

[0196] Forwarding the service requests of the preset proportion to the first service response node; wherein the resources occupied by the service requests of the preset proportion shall not exceed the resources allocated by the first service response node;

[0197] Based on the resource restriction formula, resource restriction is performed on the service request forwarded by the local edge computing terminal; wherein the expression of the resource restriction formula is:

[0198]

[0199] In the formula, s 边,max 、s 云,max are the maximum computing resource capacities of the first edge computing terminal and the cloud master station respectively; v 边,e1,e2，min is the minimum value of the communication resource capacity between edge computing terminal e1 and edge computing terminal e2; v 云,e，minis the minimum value of the communication resource capacity between the cloud master and the edge computing terminal e;

[0200] The service request received by the first service response node is subjected to a delay constraint based on a delay constraint formula; wherein the delay constraint formula is expressed as follows:

[0201] t 边,e x a,e +t 云 y a,云 +c 边,e1,e2 x a,e1 x a,e2 +c 云,e x a,e y a,云 ≤T a ;

[0202] Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; x a,e is the mapping relationship between service a and edge computing terminal e; t 云 The first computing delay generated when the cloud master station processes the business; y a,云 is the mapping relationship between business a and the cloud master station; c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay generated during the interaction; x a,e1 The mapping relationship between service a and edge computing terminal e1; x a,e2 The mapping relationship between service a and edge computing terminal e2; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; T a is the delay tolerance of service a.

[0203] In one embodiment, the service request processing device further includes: optimizing the allocation of the service request based on a preset objective function; wherein the preset objective function aims at minimizing delay, and the expression of the preset objective function is:

[0204] min f(a)=f1(a)+f2(a);

[0205] f1(a)=∑ a (t 边,e +t 云 );

[0206] f2(a)=∑ a (c 边,e +c 边,e1,e2 +c 云,e);

[0207] Where min f(a) is the minimum delay; f1(a) is the calculation delay; f2(a) is the communication delay; t 边,e Processing business computing load w for edge computing terminal e 边,e The calculation delay generated; t 云 The first computing delay generated when the cloud master station processes the business; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay caused by the interaction; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction.

[0208] Those skilled in the art can clearly understand that, for the convenience and brevity of description, 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.

[0209] An embodiment of the present invention provides a service request processing device, which introduces a local edge computing terminal to distribute the service request processing tasks to each edge computing node, effectively reducing the load of the main station and the network transmission delay, so that the pressure on the network resource usage of the main station is alleviated, thereby improving the processing capacity of the main station. Using the edge computing terminal to perform preliminary processing of the service request and optimizing the processing path of the request in combination with the delay calculation formula can greatly reduce the overall processing delay. By allocating service requests to the most suitable processing node, the system can process service requests more efficiently and improve real-time response capabilities. Under the architecture of business collaborative processing, the edge computing terminal of the substation can dynamically select the processing node according to the actual situation and interaction attributes. This flexible processing mechanism enables the system to cope with the processing requirements of different service requests and improves the robustness and elasticity of the overall system.

[0210] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing a business request, characterized in that: include: Receive a service request uploaded by a service request node in a current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula; Performing interaction attribute judgment on the local edge computing terminal, and allocating the processing object of the service request based on the interaction attribute judgment result; wherein the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining service response nodes in the distribution network have interaction conditions; When the local edge computing terminal does not have an interactive attribute, allocating the service request to the local edge computing terminal so that the local edge computing terminal processes the received service request; When the local edge computing terminal has an interactive attribute, a first business response node that has an interactive relationship with the local edge computing terminal is obtained, and a second delay required for each of the first business response nodes to cooperate with the local edge computing terminal to process the business request is calculated, and the business request is allocated to the business response node with the smallest delay.

2. A service request processing method according to claim 1, characterized in that: The calculating, based on the first delay calculation formula, the first delay required for the local edge computing terminal to process the service request specifically includes: The first delay required for the local edge computing terminal to process the service request is calculated based on a first delay calculation formula; wherein the first delay includes calculation delay and communication delay, and the expression of the first delay calculation formula is: w 边,e =∑ a w a x a,e ; Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data; 边,e is the computing resource capacity of the edge computing terminal e; w a is the computing load of business a; x a,e It is the mapping relationship between service a and edge computing terminal e, and its values ​​are 0 and 1.

3. A service request processing method according to claim 1, characterized in that: The determining of the interaction attribute of the local edge computing terminal specifically includes: When there is a completed interactive communication network between the local edge computing terminal and other business response nodes and the business response nodes have undergone software authentication, it is determined that the local edge computing terminal has the interactive attribute.

4. A service request processing method according to claim 1, characterized in that: The obtaining of a first service response node having an interactive relationship with the local edge computing terminal, and calculating a second delay based on each of the first service response nodes cooperating with the local edge computing terminal to process the service request specifically includes: Monitor the operation status information of the local edge computing terminal in real time and control the local edge computing terminal to send the operation status information to the first edge computing terminal; wherein the first edge computing terminal is an edge computing terminal in an adjacent area; Acquire a first service response node that has an interactive relationship with the local edge computing terminal, and control the local edge computing terminal to forward the service requests of a preset proportion to the first service response node; wherein the first service response node includes any one or both of a cloud master station and a first edge computing terminal; When the first service response node is the cloud master, calculating a second delay for the cloud master to collaborate with the local edge computing terminal to process the service request based on a second delay calculation formula; When the first service response node is the first edge computing terminal, a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request is calculated based on a third delay calculation formula.

5. A service request processing method as claimed in claim 4, characterized in that: The calculating, based on the second delay calculation formula, the second delay for the cloud master station to collaborate with the local edge computing terminal to process the service request specifically includes: The first computing delay required for the cloud master to process the business requests of a preset proportion and the first communication delay generated by the cloud master interacting with the local edge computing terminal are calculated based on the second delay calculation formula; wherein the expression of the second delay calculation formula is: w 云 =∑ a w a y a,云 ; Where, t 云 w is the first computing delay generated when the cloud master station processes the business; 云 is the total computing load of the services undertaken by the cloud master; 云 is the computing resource capacity of the cloud master station; a,云 is the mapping relationship between business a and the cloud master station; w a is the computing load of business a; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; v 云,e It is the communication resource capacity when the cloud master station interacts with the edge computing terminal e; The first computing delay and the first communication delay are combined to generate a second delay for the cloud master to collaborate with the local edge computing terminal to process the business request.

6. A method for processing a service request as claimed in claim 4, characterized in that: The calculating, based on the third delay calculation formula, a third delay for the first edge computing terminal to collaborate with the local edge computing terminal to process the service request specifically includes: The second communication delay generated by the interaction between the first edge computing terminal and the local edge computing terminal is calculated based on the third delay calculation formula; wherein the expression of the third delay calculation formula is: In the formula, c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The second communication delay generated during the interaction; v 边,e1,e2 It is the communication resource capacity when the edge computing terminal e1 interacts with the edge computing terminal e2; Calculate, based on the first delay calculation formula, a fourth delay required for the first edge computing terminal to process a preset proportion of the service requests; The second communication delay and the fourth delay are combined to generate a third delay for the first edge computing terminal to cooperate with the local edge computing terminal to process the service request.

7. A method for processing a service request according to claim 1, characterized in that: When controlling the local edge computing terminal to forward the service requests of a preset proportion to the first service response node, resource constraints and delay constraints need to be performed, specifically: Forwarding the service requests of the preset proportion to the first service response node; wherein the resources occupied by the service requests of the preset proportion shall not exceed the resources allocated by the first service response node; Based on the resource restriction formula, resource restriction is performed on the service request forwarded by the local edge computing terminal; wherein the expression of the resource restriction formula is: In the formula, s 边,max 、s 云,max are the maximum computing resource capacities of the first edge computing terminal and the cloud master station respectively; v 边,e1,e2，min is the minimum value of the communication resource capacity between edge computing terminal e1 and edge computing terminal e2; v 云,e，min is the minimum value of the communication resource capacity between the cloud master station and the edge computing terminal e; The service request received by the first service response node is subjected to a delay constraint based on a delay constraint formula; wherein the delay constraint formula is expressed as follows: t 边,e x a,e +t 云 y a,云 +c 边,e1,e2 x a,e1 x a,e2 +c 云,e x a,e y a,云 ≤T a ; Where, t 边,e Processing business computing load w for edge computing terminal e 边,e The computational delay generated; x a,e is the mapping relationship between service a and edge computing terminal e; t 云 The first computing delay generated when the cloud master station processes the business; y a,云 is the mapping relationship between business a and the cloud master station; c 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay generated during the interaction; x a,e1 The mapping relationship between service a and edge computing terminal e1; x a,e2 The mapping relationship between service a and edge computing terminal e2; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction; T a is the delay tolerance of service a.

8. A service request processing method according to claim 1, characterized in that: The service request processing method further includes: The allocation of the service request is optimized based on a preset objective function; wherein the preset objective function aims at minimizing the delay, and the expression of the preset objective function is: min f(a)=f1(a)+f2(a); f1(a)=∑ a (t 边,e +t 云 ); f2(a)=∑ a (c 边,e +c 边,e1,e2 +c 云,e ); Where min f(a) is the minimum delay; f1(a) is the calculation delay; f2(a) is the communication delay; t 边,e Processing business computing load w for edge computing terminal e 边,e The calculation delay generated; t 云 The first computing delay generated when the cloud master station processes the business; c 边,e Processing transmission data volume u for edge computing terminal e 边,e The communication delay caused by the data 边,e1,e2 The data volume is u for edge computing terminal e1 and edge computing terminal e2 边,e1,e2 The communication delay caused by the interaction; c 云,e The data volume u is used for the cloud master station and the edge computing terminal e 云,e The first communication delay generated during the interaction.

9. A service request processing device, characterized in that: include: A request receiving module, an attribute judging module, a first allocating module and a second allocating module; The request receiving module is used to receive a service request uploaded by a service request node in the current area to a local edge computing terminal and calculate a first delay required for the local edge computing terminal to process the service request based on a first delay calculation formula; The attribute judgment module is used to perform interaction attribute judgment on the local edge computing terminal, and allocate the processing object of the business request based on the interaction attribute judgment result; wherein, the interaction attribute judgment is to detect whether the local edge computing terminal and the remaining business response nodes in the distribution network have interaction conditions; The first allocation module allocates the service request to the local edge computing terminal when the local edge computing terminal does not have an interactive attribute so that the local edge computing terminal processes the received service request; The second allocation module is used to obtain the first business response node that has an interactive relationship with the local edge computing terminal when the local edge computing terminal has an interactive attribute, and calculate the second delay required for each first business response node to cooperate with the local edge computing terminal to process the business request, and allocate the business request to the business response node with the smallest delay.

10. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a service request processing method as claimed in any one of claims 1 to 8 is implemented.

Images