A resource collaboration service system based on cloud platform

Abstract

The present invention discloses a resource collaboration service system based on a cloud platform, comprising a request collection module, a resource collaboration module and a service processing module, characterized in that: the request collection module is used to collect service request data input by a user or generate a service request based on a user service request, the resource collaboration module is used to determine whether an edge computing node is overloaded or is in an overloaded state, and adjust the processing method of the service request according to the load status of the edge computing node, the service processing module is used to extract user service requests from the edge computing node, transmit the user service requests to a cloud computing center, and respond to the processed service requests, the request collection module, the resource collaboration module and the service processing module are communicated with each other, and the request collection module includes a request information entry module and a request generation module. The present invention has the characteristics of reducing response delay and improving system efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and in particular to a resource collaboration service system based on a cloud platform. Background Art

[0002] With the continuous development of network technology, in today's highly developed science and technology and network, people's daily lives are increasingly inseparable from the Internet. With the convenience provided by the Internet, people have higher requirements for the response speed of the Internet. In view of the unpredictable communication delays when cloud computing centers respond to services, the response waiting time of services is also uncertain. The low latency characteristics of edge computing nodes make them widely used, but the computing resources of edge computing nodes are limited. When faced with the explosive growth of user service requests, the service quality of edge computing nodes cannot be guaranteed. If a large number of edge computing nodes are added, although the service response speed and service quality can be guaranteed, the subsequent management and service quality will be affected. Maintenance costs will increase significantly, and adding a large number of edge computing nodes will not always be fully loaded, resulting in some edge computing nodes being idle, causing resource waste. At present, the cloud-edge collaboration model is an effective way to solve the above problems. However, the existing technology cannot effectively calculate whether the current client's service request will overload the current edge computing node, and when the edge computing node is overloaded, it cannot process service requests from other clients, resulting in service request congestion, which greatly prolongs the waiting time for service response. Moreover, since the overload of edge computing nodes affects the user experience, it is very necessary to design a resource collaboration service system based on a cloud platform to reduce response delay and improve system efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a resource collaboration service system based on a cloud platform to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a resource collaboration service system based on a cloud platform, comprising a request collection module, a resource collaboration module and a service processing module, characterized in that: the request collection module is used to collect service request data input by a user or generate a service request based on a user service request, the resource collaboration module is used to determine whether an edge computing node is overloaded or is in an overload state, and adjust the processing method of the service request according to the load status of the edge computing node, the service processing module is used to extract the user service request from the edge computing node, transmit the user service request to the cloud computing center, and respond to the processed service request, and the request collection module, resource collaboration module and service processing module are communicatively connected to each other;

[0005] The resource adjustment module includes a collaborative task allocation submodule, a load calculation submodule and a service transfer submodule. The collaborative task allocation module is used to allocate the processing method of the current service request according to the analyzed service request preloading model. The load calculation submodule is used to calculate the load status of the current edge computing node. The service transfer submodule is used to judge the load status of the current edge node and select the corresponding processing method according to the load status.

[0006] According to the above technical solution, the request collection module includes a request information entry module and a request generation module. The request information entry module is used for users to enter service request processing data into the system, and the request generation module is used to generate service requests according to user operations on the client.

[0007] According to the above technical solution, the resource collaboration module includes a request receiving module and a resource adjustment module. The request receiving module is used to receive and identify the service request processing method selected by the user, and the resource adjustment node is used to adjust the service request processing method according to the user's selection and the load status of the edge computing node.

[0008] According to the above technical solution, the resource collaboration module also includes a request preloading module, and the request is expected to be used in the module to preload service requests processed by the edge computing node to determine whether the current edge computing node is overloaded.

[0009] According to the above technical solution, the service processing module includes a request extraction module and a service response module. The request extraction module is used to extract service request data from the overloaded edge computing node, and the service response module is used to respond to the processed service request.

[0010] According to the above technical solution, the operation method of the resource collaboration system mainly includes the following steps:

[0011] Step S1: The data that the user wants to process is entered into the system through the information entry module. The user's operations on the client are collected through the request generation module, and a service request is generated based on the user's operations and selections.

[0012] Step S2: When the system receives a service request, the system activates the request preloading module through an electrical signal and begins to analyze the service request to determine whether the service request will cause an excessive load on the current edge computing node;

[0013] Step S3: When the system processes the service request, the system starts the resource adjustment module to analyze the load of each edge computing node in real time and adjust the processing method of the service request according to the load status of the edge node;

[0014] Step S4: When the service request is transferred to the cloud computing center for processing, the cloud computing center receives the service request transmitted by the system and processes the service request. The cloud computing center and the edge computing node respond to the service requests they process.

[0015] According to the above technical solution, step S2 further includes the following steps:

[0016] Step S21: Retrieve the received user service request, scan and identify the processing method tag selected by the user in the service request and the number of bytes of the data to be calculated. If the processing method is cloud computing center processing, the system retrieves a pre-set transmission line based on the number of bytes of the data to be calculated;

[0017] Step S22: When the processing mode is edge computing node processing or the processing mode is not indicated, scan and identify the data structure and data size of the data to be calculated in the service request, and use the formula to predict the occupancy rate of the data size under the current data structure in the processor of the current edge computing node Where S represents the occupancy rate of the data size under the current data structure in the processor of the current edge computing node, M represents the maximum data size that the current edge computing node can process under the current data structure, m represents the data size of the current data to be processed, and α represents the influence coefficient of the residual efficiency of the current edge computing node processor on the occupancy rate. If the predicted occupancy rate is greater than the current residual efficiency of the edge node, the data to be calculated will be transmitted to the cloud computing center for calculation through the set transmission route. Otherwise, the calculation will be performed by the edge computing node.

[0018] According to the above technical solution, step S3 further includes the following steps:

[0019] Step S31: When allocating an edge computing node to a service request, scan and identify all clients that issue service requests, classify the service requests according to the client, calculate the total processor occupancy required for the service requests issued by the current client, and compare the remaining efficiency of all edge computing nodes. If there is an edge computing node with a remaining efficiency greater than the total processor occupancy required for the service requests issued by the current client, the service request is allocated to the edge computing node. Otherwise, all service requests from the current client are packaged and sent to the cloud computing center for processing.

[0020] Step S32: retrieve the data change between units and the data reduction per unit time in the current edge computing node processor, and calculate the actual load rate of the edge computing node processor by the formula Where F represents the actual load rate of the current edge node, Q represents the amount of data change in the current edge computing node per unit time, q represents the amount of data reduction in the edge computing node per unit time, W represents the amount of data that the current edge server can process, and β represents the influence coefficient of the processor occupancy rate of the current edge computing node.

[0021] Step S33: retrieve the load rates of all current edge computing nodes, compare them with the threshold set by the system, and transfer the service request to the cloud computing center or the adjacent edge computing node for processing based on the judgment result.

[0022] According to the above technical solution, in step S33, when the load rate of the edge computing node is greater than the first threshold and less than the second threshold, the system encapsulates the current edge node, packages the service requests in the transmission route of the current edge computing node, and calls the load rate of other edge computing nodes. The efficiency of the edge computing node processing is calculated by the formula In the formula, K represents the efficiency of edge computing node proxy processing, F represents the actual load rate of the current edge node, L represents the transmission distance between edge computing nodes, and λ represents the influence coefficient of distance L on the efficiency of edge computing node proxy processing. The nodes are sorted in descending order, and the edge computing node with the highest proxy processing efficiency is selected as the proxy processing node. When the load rate of the edge computing node is greater than the second threshold, the system intercepts the service request of the current edge computing node and encapsulates it, and sends the encapsulated service request to the cloud computing center for processing.

[0023] According to the above technical solution, in step S4, when responding to the user service request, if the service request processing method is edge computing node processing, the edge computing node transmits the calculation result to the user client through the transmission line for response, or the edge computing node participating in the proxy processing transmits the calculation result to the user client through the current edge computing node for response. If the service request processing method is cloud computing center processing, the cloud computing center transmits the calculation result to the user client through the transmission route for response. If the user request is jointly processed by the edge computing node and the cloud computing center, the cloud computing center transmits the calculation result to the edge computing node, integrates the calculation result through the edge computing node, and sends the integrated calculation to the client for response.

[0024] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by judging whether the remaining efficiency of the processor of the current edge computing node can calculate the data to be calculated, can avoid the data to be calculated without marking the processing method from entering the edge computing node, avoid the edge computing node from being overloaded and causing the remaining service requests to block the edge computing node, thereby improving the processing speed of the edge computing node; by classifying the service requests according to the client and allocating computing nodes according to the classified service requests, it can avoid the user splitting the overall service request into small service requests and causing the edge computing node to be blocked, further reducing the processing time of the service request, thereby reducing the service response delay; by calculating the load rate of the edge computing node, it can quickly judge the current The processing efficiency of the front edge computing node is improved, which avoids adjusting the service request to the fully loaded edge computing node, resulting in a decrease in the computing accuracy of the edge computing node, thereby improving the computing accuracy of the service request. By calculating the actual processing efficiency of the target edge computing node to transfer the service request, it is possible to find the target edge computing node with the fastest processing speed for the service request, and transfer the service request to the adjacent edge computing node or cloud computing center for processing, thereby avoiding service request congestion and edge computing node overload, greatly improving the efficiency of the system in processing service requests. By having the edge computing node responsible for the current client respond to the calculation results, it can prevent the calculation results from being disordered during the transmission process, thereby improving the accuracy and completeness of the calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0026] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0028] See also Figure 1The present invention provides a technical solution: a resource collaboration service system based on a cloud platform, comprising a request collection module, a resource collaboration module and a service processing module, characterized in that: the request collection module is used to collect service request data input by a user or generate a service request according to a user service request, the resource collaboration module is used to determine whether an edge computing node is overloaded or is in an overload state, and adjust the processing method of the service request according to the load status of the edge computing node, the service processing module is used to extract the user service request from the edge computing node, transmit the user service request to the cloud computing center, and respond to the processed service request, and the request collection module, the resource collaboration module and the service processing module are communicatively connected to each other;

[0029] The resource adjustment module includes a collaborative task allocation submodule, a load calculation submodule and a service transfer submodule. The collaborative task allocation module is used to allocate the processing method of the current service request based on the analyzed service request preloading model. The load calculation submodule is used to calculate the load status of the current edge computing node. The service transfer submodule is used to judge the load status of the current edge node and select the corresponding processing method according to the load status.

[0030] The request collection module includes a request information entry module and a request generation module. The request information entry module is used for users to enter service request processing data into the system, and the request generation module is used to generate service requests according to user operations on the client.

[0031] The resource collaboration module includes a request receiving module and a resource adjustment module. The request receiving module is used to receive and identify the service request processing method selected by the user, and the resource adjustment node is used to adjust the service request processing method according to the user's selection and the load status of the edge computing node.

[0032] The resource collaboration module also includes a request preloading module, which is used to preload service requests processed by the edge computing node to determine whether the current edge computing node is overloaded.

[0033] The service processing module includes a request extraction module and a service response module. The request extraction module is used to extract service request data from the overloaded edge computing node, and the service response module is used to respond to the processed service request.

[0034] The operation method of the resource collaboration system mainly includes the following steps:

[0035] Step S1: The data that the user wants to process is entered into the system through the information entry module. The user's operations on the client are collected through the request generation module, and a service request is generated based on the user's operations and selections.

[0036] Step S2: When the system receives a service request, the system activates the request preloading module through an electrical signal and begins to analyze the service request to determine whether the service request will cause an excessive load on the current edge computing node;

[0037] Step S3: When the system processes the service request, the system starts the resource adjustment module to analyze the load of each edge computing node in real time and adjust the processing method of the service request according to the load status of the edge node;

[0038] Step S4: When the service request is transferred to the cloud computing center for processing, the cloud computing center receives the service request transmitted by the system and processes the service request. The cloud computing center and the edge computing node respond to the service requests they process.

[0039] Step S2 further includes the following steps:

[0040] Step S21: Retrieve the received user service request, scan and identify the processing method tag selected by the user in the service request and the number of bytes of the data to be calculated. If the processing method is cloud computing center processing, the system retrieves a pre-set transmission line based on the number of bytes of the data to be calculated. By identifying the number of bytes of the data to be calculated and selecting the corresponding transmission line, the data to be calculated can be quickly transmitted to the cloud computing center, reducing data transmission time.

[0041] Step S22: When the processing mode is edge computing node processing or the processing mode is not indicated, scan and identify the data structure and data size of the data to be calculated in the service request, and use the formula to predict the occupancy rate of the data size under the current data structure in the processor of the current edge computing node Where S represents the occupancy rate of the data size under the current data structure in the processor of the current edge computing node, M represents the maximum data size that the current edge computing node can process under the current data structure, m represents the data size of the current data to be processed, and α represents the influence coefficient of the current edge computing node processor surplus efficiency on the occupancy rate. If the predicted occupancy rate is greater than the current edge node surplus efficiency, it means that the current edge computing node cannot calculate the current service request. The data to be calculated is transmitted to the cloud computing center for calculation through the set transmission route. Otherwise, the edge computing node performs the calculation. By judging whether the surplus efficiency of the processor of the current edge computing node can calculate the data to be calculated, it is possible to prevent the data to be calculated without marking the processing method from entering the edge computing node, avoid the overload of the edge computing node, and prevent the remaining service requests from blocking the edge computing node, thereby improving the processing speed of the edge computing node.

[0042] Step S3 further includes the following steps:

[0043] Step S31: When allocating an edge computing node to a service request, scan and identify all clients that issue service requests, classify the service requests according to the client, calculate the total processor occupancy required for the service requests issued by the current client, and compare the remaining efficiencies of all edge computing nodes. If there is an edge computing node with a remaining efficiency greater than the total processor occupancy required for the service requests issued by the current client, the service request is allocated to the edge computing node. Otherwise, all service requests of the current client are packaged and sent to the cloud computing center for processing. By classifying the service requests according to the client and allocating computing nodes according to the classified service requests, it is possible to avoid the situation where the user splits the overall service request into small service requests, causing congestion in the edge computing node, further reducing the processing time of the service request, and thus reducing the service response delay.

[0044] Step S32: retrieve the data change between units and the data reduction per unit time in the current edge computing node processor, and calculate the actual load rate of the edge computing node processor by the formula Where F represents the actual load rate of the current edge node, Q represents the amount of data change in the current edge computing node per unit time, q represents the amount of data reduction in the edge computing node per unit time, W represents the amount of data that the current edge server can process, and β represents the influence coefficient of the processor occupancy rate of the current edge computing node. By calculating the load rate of the edge computing node, the processing efficiency of the current edge computing node can be quickly judged, avoiding the reduction of the calculation accuracy of the edge computing node due to adjusting the service request to a fully loaded edge computing node, thereby improving the calculation accuracy of the service request;

[0045] Step S33: retrieve the load rates of all current edge computing nodes, compare them with the threshold set by the system, and transfer the service request to the cloud computing center or the adjacent edge computing node for processing based on the judgment result.

[0046] In step S33, when the load rate of the edge computing node is greater than the first threshold and less than the second threshold, the system encapsulates the current edge node, packages the service requests in the transmission route of the current edge computing node, calls the load rate of other edge computing nodes, and calculates the efficiency of the edge computing node's processing by the formula In the formula, K represents the efficiency of edge computing node proxy processing, F represents the actual load rate of the current edge node, L represents the transmission distance between edge computing nodes, and λ represents the influence coefficient of distance L on the efficiency of edge computing node proxy processing. The nodes are sorted in descending order, and the edge computing node with the largest proxy processing efficiency is selected as the proxy processing node. When the load rate of the edge computing node is greater than the second threshold, the system intercepts the service request of the current edge computing node and encapsulates it, and sends the encapsulated service request to the cloud computing center for processing. By calculating the actual proxy processing efficiency of the target edge computing node to transfer the service request, the target edge computing node with the fastest processing speed can be found for the service request, and the service request can be transferred to the adjacent edge computing node or cloud computing center for processing, thereby avoiding service request congestion and edge computing node overload, greatly improving the efficiency of the system in processing service requests.

[0047] In step S4, when responding to the user service request, if the service request processing method is edge computing node processing, the edge computing node transmits the calculation result to the user client through the transmission line for response, or the edge computing node participating in the processing transmits the calculation result to the user client through the current edge computing node for response. If the service request processing method is cloud computing center processing, the cloud computing center transmits the calculation result to the user client through the transmission route for response. If the user request is jointly processed by the edge computing node and the cloud computing center, the cloud computing center transmits the calculation result to the edge computing node, integrates the calculation result through the edge computing node, and sends the integrated calculation to the client for response. By having the edge computing node responsible for the current client respond to the calculation results, it is possible to prevent the calculation results from being disordered during the transmission process, thereby improving the accuracy and completeness of the calculation results.

[0048] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0049] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A resource collaboration service system based on a cloud platform, comprising a request collection module, a resource collaboration module, and a service processing module, characterized in that: The request collection module is used to collect service request data input by users or generate service requests based on user service requests. The resource collaboration module is used to determine whether the edge computing node is overloaded or is in overload, and adjust the processing method of the service request according to the load status of the edge computing node. The service processing module is used to extract user service requests from the edge computing node, transmit the user service requests to the cloud computing center, and respond to the processed service requests. The request collection module, resource collaboration module and service processing module are in communication with each other; The resource adjustment module includes a collaborative task allocation submodule, a load calculation submodule, and a service transfer submodule. The collaborative task allocation module is used to allocate the processing method of the current service request according to the analyzed service request preloading model. The load calculation submodule is used to calculate the load status of the current edge computing node. The service transfer submodule is used to determine the load status of the current edge node and select the corresponding processing method according to the load status. The operation method of the resource collaboration system mainly includes the following steps: Step S1: The data that the user wants to process is entered into the system through the information entry module. The request generation module collects the user's operations on the client and generates a service request based on the user's operations and selections. Step S2: When the system receives a service request, the system starts the request preloading module through an electrical signal and begins to analyze the service request to determine whether the service request will cause an excessive load on the current edge computing node; Step S3: When the system processes the service request, the system starts the resource adjustment module to analyze the load of each edge computing node in real time and adjust the processing method of the service request according to the load status of the edge node; Step S4: When the service request is transferred to the cloud computing center for processing, the cloud computing center receives the service request transmitted by the system and processes the service request. The cloud computing center and the edge computing node respond to the service requests they have processed. The step S3 further comprises the following steps: Step S31: When allocating an edge computing node to a service request, scan and identify all clients that issue service requests, classify the service requests according to the client, calculate the total processor occupancy required for the service requests issued by the current client, and compare the remaining efficiency of all edge computing nodes. If there is an edge computing node with a remaining efficiency greater than the total processor occupancy required for the service requests issued by the current client, the service request is allocated to the edge computing node. Otherwise, all service requests from the current client are packaged and sent to the cloud computing center for processing. Step S32: Retrieve the amount of data per unit time and the amount of data change per unit time in the current edge computing node processor, and calculate the actual load rate F of the edge computing node processor using a formula; Step S33: Retrieve the load rates of all current edge computing nodes, compare them with the threshold set by the system, and transfer the service request to the cloud computing center or a neighboring edge computing node for processing based on the judgment result; In step S33, when the load rate of the edge computing node is greater than the first threshold and less than the second threshold, the system encapsulates the current edge node, packages the service requests in the transmission route of the current edge computing node, retrieves the load rate of other edge computing nodes, and calculates the efficiency of the edge computing node's processing by the formula , where Indicates the efficiency of edge computing node processing, Indicates the actual load rate of the current edge node, Indicates the transmission distance between edge computing nodes, Indicates distance The influence coefficients of the efficiency of edge computing node proxy processing are sorted in descending order, and the edge computing node with the highest proxy processing efficiency is selected as the proxy processing node. When the load rate of the edge computing node is greater than the second threshold, the system intercepts the service request of the current edge computing node and encapsulates it, and sends the encapsulated service request to the cloud computing center for processing.

2. A cloud platform-based resource collaboration service system according to claim 1, characterized in that: The request collection module includes a request information entry module and a request generation module. The request information entry module is used for the user to enter the service request processing data into the system, and the request generation module is used to generate a service request according to the user's operation on the client.

3. The cloud platform-based resource collaboration service system according to claim 2, characterized in that: The resource collaboration module includes a request receiving module and a resource adjustment module. The request receiving module is used to receive and identify the service request processing method selected by the user, and the resource adjustment node is used to adjust the service request processing method according to the user's selection and the load status of the edge computing node.

4. The cloud platform-based resource collaboration service system according to claim 3, characterized in that: The resource collaboration module further includes a request preloading module, wherein the request is expected to be used in the module to preload service requests processed by the edge computing node to determine whether the current edge computing node is overloaded.

5. The cloud platform-based resource collaboration service system according to claim 4, characterized in that: The service processing module includes a request extraction module and a service response module. The request extraction module is used to extract service request data from the overloaded edge computing node, and the service response module is used to respond to the processed service request.

6. The cloud platform-based resource collaboration service system according to claim 1, characterized in that: The step S2 further comprises the following steps: Step S21: Retrieve the received user service request, scan and identify the processing method tag selected by the user in the service request and the number of bytes of the data to be calculated. If the processing method is cloud computing center processing, the system retrieves a pre-set transmission line based on the number of bytes of the data to be calculated; Step S22: When the processing mode is edge computing node processing or the processing mode is not indicated, scan and identify the data structure and data size of the data to be calculated in the service request, and use the formula to predict the occupancy rate of the data size under the current data structure in the processor of the current edge computing node , where Indicates the occupancy rate of the data size in the processor of the current edge computing node under the current data structure, Indicates the maximum data size that the current edge computing node can process under the current data structure. Indicates the size of the data currently to be processed. It represents the influence coefficient of the current edge computing node processor surplus efficiency on the occupancy rate. If the predicted occupancy rate is greater than the current edge node surplus efficiency, the data to be calculated will be transmitted to the cloud computing center for calculation through the set transmission route. Otherwise, the edge computing node will perform the calculation.

7. The cloud platform-based resource collaboration service system according to claim 1, characterized in that: In step S4, when responding to the user service request, if the service request processing method is edge computing node processing, the edge computing node transmits the calculation result to the user client through the transmission line for response, or the edge computing node participating in the proxy processing transmits the calculation result to the user client through the current edge computing node for response. If the service request processing method is cloud computing center processing, the cloud computing center transmits the calculation result to the user client through the transmission route for response. If the user request is jointly processed by the edge computing node and the cloud computing center, the cloud computing center transmits the calculation result to the edge computing node, integrates the calculation result through the edge computing node, and sends the integrated calculation to the client for response.

Images