Multilateral Collaborative Control Method and System Centered on Cloudified Services

Abstract

The present invention discloses a multi - party collaborative control method and system centered on cloud - based services. The method includes: obtaining calculation task data to be allocated, server information, and historical task records of multiple edge servers to be controlled; based on the historical task records and a prediction algorithm, predicting cloud service requirement parameters corresponding to each of the edge servers; determining a control requirement function according to the cloud service requirement parameters corresponding to each of the edge servers and the calculation requirements corresponding to the calculation task data; and based on the control requirement function and the server information, performing iterative calculation using a dynamic programming algorithm to obtain the allocated calculation task data and working parameters of each of the edge servers. It can be seen that the present invention can fully combine the cloud service requirements of edge servers to coordinate and allocate multi - party calculations, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a multi - party collaborative control method and system centered on cloud services. Background Art

[0002] With the development of Internet technology and data servers, the data - processing technology of "Internet +" has begun to combine with the data - processing requirements of various industries to improve the degree of intelligence of various industries. Among them, cloud service is a data center located in a remote cloud and provides dynamically scalable and often virtualized resources in a demand - processing mode through the Internet. The massive computing task data and storage resources enable the cloud to provide strong background support for the complex calculations involved in intelligent energy use. Edge computing is a new type of computing mode after cloud computing. It provides IT and cloud computing capabilities on the wireless access network side to localize computing, aiming to reduce latency, improve network operation efficiency, improve service distribution capabilities, and optimize the quality of the terminal experience. However, in the prior art, when it comes to the collaborative control of multiple edge servers, the computing tasks are generally allocated only by considering the resource requirements of the current task and the computing capabilities of each edge server, without fully considering the service quality and service efficiency of the core cloud services corresponding to different edge servers to correct the control strategy. Therefore, the collaborative control effect is not balanced enough, and it is easy to affect the service quality and service efficiency of some core cloud services. It can be seen that the prior art has defects and urgent solutions are needed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a multi - party collaborative control method and system centered on cloud services, which can fully combine the cloud service requirements of edge servers to coordinate and allocate multi - party calculations, so as to improve the collaborative control effect and ensure the service quality of cloud services.

[0004] To solve the above - mentioned technical problem, in the first aspect of the present invention, a multi - party collaborative control method centered on cloud services is disclosed. The method includes:

[0005] Obtain the calculation task data to be allocated, the server information of multiple edge servers to be controlled, and the historical task records;

[0006] Based on the historical task records and a prediction algorithm, predict the cloud service requirement parameters corresponding to each edge server;

[0007] Determine a control requirement function according to the cloud service requirement parameters corresponding to each edge server and the calculation requirements corresponding to the calculation task data;

[0008] Based on the control requirement function and the server information, iterative calculation is performed based on the dynamic programming algorithm to obtain the allocated calculation task data and working parameters of each edge server.

[0009] As an optional implementation manner, in the first aspect of the present invention, the server information includes hardware information, software information, communication performance information, and computing performance information.

[0010] As an optional implementation manner, in the first aspect of the present invention, the historical task record includes the execution calculation task records and communication records of the edge server in multiple historical time periods.

[0011] As an optional implementation manner, in the first aspect of the present invention, based on the historical task record and the prediction algorithm, predicting the cloud service requirement parameters corresponding to each edge server includes:

[0012] For each edge server, input the historical task record corresponding to the edge server into the trained cloud service prediction neural network to obtain the cloud service node corresponding to the edge server;

[0013] Obtain the preset cloud service requirements of the cloud service node; the preset cloud service requirements include the preset computing efficiency requirements and the preset communication accuracy rate;

[0014] According to all the records of completing the calculation tasks corresponding to the cloud service node in the historical task record corresponding to the edge server, calculate the historical average completion requirement corresponding to the edge server;

[0015] Calculate the average value of the preset cloud service requirements and the historical average completion requirements, and calculate the cloud service requirement parameters corresponding to the edge server; the cloud service requirement parameters include cloud service type, cloud service computing efficiency requirements, and cloud service communication accuracy requirements.

[0016] As an optional implementation manner, in the first aspect of the present invention, the cloud service prediction neural network is a CNN network, which is trained by a training data set including multiple training server task records and corresponding cloud service node annotations.

[0017] As an optional implementation manner, in the first aspect of the present invention, according to all the records of completing the calculation tasks corresponding to the cloud service node in the historical task record corresponding to the edge server, calculating the historical average completion requirement corresponding to the edge server includes:

[0018] Screen out all the records of completing the calculation tasks corresponding to the cloud service node in the historical task record corresponding to the edge server to obtain multiple historical associated task records;

[0019] Calculate the average value of the computing efficiency in all the historical associated task records to obtain the historical average computing efficiency requirement corresponding to the edge server;

[0020] Calculate the average value of the communication accuracy rate in all the historical associated task records to obtain the historical average communication accuracy rate requirement corresponding to the edge server;

[0021] Determine the historical average computing efficiency requirement and the historical average communication accuracy rate requirement as the historical average completion requirement corresponding to the edge server.

[0022] As an optional implementation manner, in the first aspect of the present invention, the determining the control requirement function according to the cloud service requirement parameter corresponding to each edge server and the computing requirement corresponding to the computing task data includes:

[0023] Determine the objective function as minimizing the computing task data allocated to each edge server in the collaborative control scheme;

[0024] Determine the constraint conditions including that the predicted individual computing effect corresponding to each edge server in the collaborative control scheme meets the corresponding cloud service requirement parameter and the predicted parallel computing effect corresponding to the computing task data allocated to all edge servers in the collaborative control scheme meets the computing requirement corresponding to the computing task data; the collaborative control scheme includes the allocated computing task data and working parameters corresponding to each edge server;

[0025] Determine the objective function and the constraint conditions as the control requirement function.

[0026] As an optional implementation manner, in the first aspect of the present invention, the performing iterative calculation based on the dynamic programming algorithm according to the control requirement function and the server information to obtain the allocated computing task data and working parameters of each edge server includes:

[0027] For each edge server, calculate the information similarity between the historical server information in the historical application records of multiple candidate prediction neural networks and the server information of the edge server;

[0028] Determine the candidate prediction neural network with the highest information similarity as the computing effect prediction neural network corresponding to the edge server; the computing effect prediction neural network is trained by a training data set including multiple training allocated computing data and corresponding working parameter annotations and computing effect annotations;

[0029] Iteratively generate the collaborative control schemes corresponding to all the edge servers according to a preset dynamic programming algorithm, and use the calculation effect prediction neural network corresponding to each edge server to predict the allocated calculation task data and working parameters in the collaborative control scheme to obtain the corresponding predicted individual calculation effect and predicted parallel calculation effect. Retain the collaborative control schemes for which all the corresponding predicted individual calculation effects and predicted parallel calculation effects meet the constraint conditions, and perform iterative calculations until the retained collaborative control scheme meets the objective function, to obtain the optimal collaborative control scheme, and obtain the allocated calculation task data and working parameters for each edge server.

[0030] The second aspect of the embodiments of the present invention discloses a multi-party collaborative control system centered on cloud services, and the system includes:

[0031] An acquisition module, configured to acquire the calculation task data to be allocated, and the server information and historical task records of multiple edge servers to be controlled;

[0032] A prediction module, configured to predict the cloud service requirement parameters corresponding to each edge server based on a prediction algorithm according to the historical task records;

[0033] A determination module, configured to determine a control requirement function according to the cloud service requirement parameters corresponding to each edge server and the calculation requirements corresponding to the calculation task data;

[0034] A calculation module, configured to perform iterative calculations based on a dynamic programming algorithm according to the control requirement function and the server information, to obtain the allocated calculation task data and working parameters for each edge server.

[0035] As an optional implementation manner, in the second aspect of the present invention, the server information includes hardware information, software information, communication performance information, and calculation performance information.

[0036] As an optional implementation manner, in the second aspect of the present invention, the historical task records include the execution calculation task records and communication records of the edge servers in multiple historical time periods.

[0037] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module predicts the cloud service requirement parameters corresponding to each edge server based on the historical task records and a prediction algorithm includes:

[0038] For each edge server, input the historical task record corresponding to the edge server into a trained cloud service prediction neural network to obtain the cloud service node corresponding to the edge server;

[0039] Obtain the preset cloud service requirements of the cloud service node; the preset cloud service requirements include preset computing efficiency requirements and preset communication accuracy rates;

[0040] According to all the records of completing the computing tasks corresponding to the cloud service node in the historical task record corresponding to the edge server, calculate the historical average completion requirements corresponding to the edge server;

[0041] Calculate the average value of the preset cloud service requirements and the historical average completion requirements, and calculate the cloud service requirement parameters corresponding to the edge server; the cloud service requirement parameters include cloud service type, cloud service computing efficiency requirements, and cloud service communication accuracy requirements.

[0042] As an optional implementation manner, in the second aspect of the present invention, the cloud service prediction neural network is a CNN network, and is trained by a training data set including multiple training server task records and corresponding cloud service node annotations.

[0043] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module calculates the historical average completion requirements corresponding to the edge server according to all the records of completing the computing tasks corresponding to the cloud service node in the historical task record corresponding to the edge server includes:

[0044] Screen out all the records of completing the computing tasks corresponding to the cloud service node in the historical task record corresponding to the edge server to obtain multiple historical associated task records;

[0045] Calculate the average value of the computing efficiency in all the historical associated task records to obtain the historical average computing efficiency requirements corresponding to the edge server;

[0046] Calculate the average value of the communication accuracy rates in all the historical associated task records to obtain the historical average communication accuracy requirements corresponding to the edge server;

[0047] Determine the historical average computing efficiency requirements and the historical average communication accuracy requirements as the historical average completion requirements corresponding to the edge server.

[0048] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the determination module determines the control requirement function according to the cloud service requirement parameters corresponding to each edge server and the computing requirements corresponding to the computing task data includes:

[0049] Determine that the objective function is to minimize the computing task data allocated to each edge server in the collaborative control scheme;

[0050] Determining the limiting conditions includes that the predicted individual calculation effect corresponding to each edge server in the collaborative control scheme meets the corresponding cloud service requirement parameters, and the predicted parallel calculation effect corresponding to the calculation task data assigned to all edge servers in the collaborative control scheme meets the calculation requirements corresponding to the calculation task data; the collaborative control scheme includes the assigned calculation task data and working parameters corresponding to each edge server.

[0051] Determine the objective function and the limiting conditions as the control requirement function.

[0052] As an optional implementation manner, in the second aspect of the present invention, the calculation module performs iterative calculation based on the dynamic programming algorithm according to the control requirement function and the server information, and the specific manner for obtaining the assigned calculation task data and working parameters of each edge server includes:

[0053] For each edge server, calculate the information similarity between the historical server information in the historical application records of multiple candidate prediction neural networks and the server information of this edge server.

[0054] Determine the candidate prediction neural network with the highest information similarity as the calculation effect prediction neural network corresponding to this edge server; the calculation effect prediction neural network is trained by a training data set including multiple training assigned calculation data and corresponding working parameter annotations and calculation effect annotations.

[0055] Iteratively generate the collaborative control scheme corresponding to all edge servers according to the preset dynamic programming algorithm, and predict the assigned calculation task data and working parameters in the collaborative control scheme through the calculation effect prediction neural network corresponding to each edge server to obtain the corresponding predicted individual calculation effect and predicted parallel calculation effect. Retain the collaborative control scheme in which all the corresponding predicted individual calculation effects and predicted parallel calculation effects meet the limiting conditions, and perform iterative calculation until the retained collaborative control scheme meets the objective function to obtain the optimal collaborative control scheme, and obtain the assigned calculation task data and working parameters of each edge server.

[0056] The third aspect of the present invention discloses another multi - party collaborative control system centered on cloud - based services, and the system includes:

[0057] A memory storing executable program code;

[0058] A processor coupled to the memory;

[0059] The processor calls the executable program code stored in the memory and executes some or all of the steps in the multi - party collaborative control method centered on cloud - based services disclosed in the first aspect of the present invention.

[0060] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which are used to execute some or all of the steps in the multi-party collaborative control method centered on cloud services disclosed in the first aspect of the present invention when the computer instructions are called.

[0061] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0062] The present invention can predict the cloud service requirement parameters corresponding to each edge server based on the historical task records of the edge servers, and then determine the control requirement function according to the cloud service requirement parameters and the calculation requirements corresponding to the calculation task data, so as to perform iterative calculation based on the dynamic programming algorithm to obtain the allocated calculation task data and working parameters of each edge server, so as to be able to fully combine the cloud service requirements of the edge servers to coordinate the allocation of multi-party calculations, improve the effect of collaborative control, and ensure the service quality of cloud services. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0064] Figure 1 It is a schematic flow chart of a multi-party collaborative control method centered on cloud services disclosed in the embodiments of the present invention.

[0065] Figure 2 It is a schematic structural diagram of a multi-party collaborative control system centered on cloud services disclosed in the embodiments of the present invention.

[0066] Figure 3 It is a schematic structural diagram of another multi-party collaborative control system centered on cloud services disclosed in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0068] In the description, claims, and the above-mentioned drawings of the present invention, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or equipment.

[0069] Reference to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appearing at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0070] The present invention discloses a multi-party collaborative control method and system centered on cloud-based services, which can predict the cloud service requirement parameters corresponding to each edge server based on the historical task records of the edge servers, and then determine the control requirement function according to the cloud service requirement parameters and the computing requirements corresponding to the computing task data, so as to perform iterative calculations based on the dynamic programming algorithm to obtain the allocated computing task data and working parameters of each edge server, thereby being able to fully combine the cloud service requirements of the edge servers to coordinate and allocate multi-party computing, improve the effect of collaborative control, and ensure the service quality of cloud services. The following will be described in detail respectively.

[0071] Embodiment 1

[0072] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a multi-party collaborative control method centered on cloud-based services disclosed in an embodiment of the present invention. Among them, Figure 1 the described multi-party collaborative control method centered on cloud-based services can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the multi-party collaborative control method centered on cloud-based services can include the following operations:

[0073] 101. Obtain the computing task data to be allocated and the server information and historical task records of multiple edge servers to be controlled.

[0074] 102. Based on the historical task records and a prediction algorithm, predict the cloud service requirement parameters corresponding to each edge server.

[0075] 103. Determine the control requirement function according to the cloud service requirement parameters corresponding to each edge server and the computing requirements corresponding to the computing task data.

[0076] 104. Based on the control requirement function and the server information, perform iterative calculations based on the dynamic programming algorithm to obtain the allocated computing task data and working parameters of each edge server.

[0077] It can be seen that the above-mentioned invention embodiments can predict the cloud service requirement parameters corresponding to each edge server based on the historical task records of the edge servers, and then determine the control requirement function according to the cloud service requirement parameters and the computing requirements corresponding to the computing task data, so as to perform iterative calculations based on the dynamic programming algorithm to obtain the allocated computing task data and working parameters of each edge server, thereby being able to fully combine the cloud service requirements of the edge servers to coordinate and allocate multi-party computing, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0078] As an optional embodiment, in the above steps, the server information includes hardware information, software information, communication performance information, and computing performance information.

[0079] It can be seen that through the above optional embodiment, the content of the server information is defined to comprehensively characterize the characteristics of the server, and assist in realizing the coordination and allocation of multi-party computing by fully combining the cloud service requirements of the edge server, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0080] As an optional embodiment, in the above steps, the historical task records include the execution computing task records and communication records of the edge server in multiple historical time periods.

[0081] It can be seen that through the above optional embodiment, the content of the historical task records is defined to comprehensively characterize the computing records and characteristics of the server in historical time, so as to accurately predict its cloud service requirement parameters, and assist in realizing the coordination and allocation of multi-party computing by fully combining the cloud service requirements of the edge server, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0082] As an optional embodiment, in the above steps, according to the historical task records, based on the prediction algorithm, predicting the cloud service requirement parameters corresponding to each edge server includes:

[0083] For each edge server, input the historical task records corresponding to the edge server into the trained cloud service prediction neural network to obtain the cloud service node corresponding to the edge server;

[0084] Obtain the preset cloud service requirements of the cloud service node; optionally, the preset cloud service requirements include the preset computing efficiency requirements and the preset communication accuracy rate;

[0085] Based on all the records of completing the computing tasks corresponding to the cloud service nodes in the historical task records corresponding to this edge server, calculate the historical average completion requirement corresponding to this edge server;

[0086] Calculate the average value of the preset cloud service requirement and the historical average completion requirement, and calculate the cloud service requirement parameter corresponding to this edge server; The cloud service requirement parameter includes cloud service type, cloud service computing efficiency requirement, and cloud service communication accuracy requirement.

[0087] It can be seen that through the above optional embodiments, the cloud service nodes corresponding to the edge server can be predicted by the cloud service prediction neural network, and based on the preset cloud service requirements of the cloud service nodes and the historical average completion requirements corresponding to the edge server, the cloud service requirement parameters corresponding to the edge server can be accurately determined, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge server, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0088] As an optional embodiment, in the above steps, the cloud service prediction neural network is a CNN network, which is trained through a training data set including multiple training server task records and corresponding cloud service node annotations.

[0089] It can be seen that through the above optional embodiments, the network details and training details of the cloud service prediction neural network are clarified, which can be used to accurately determine the cloud service nodes corresponding to the edge server, facilitating subsequent calculations and controls, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge server, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0090] As an optional embodiment, in the above steps, based on all the records of completing the computing tasks corresponding to the cloud service nodes in the historical task records corresponding to this edge server, calculating the historical average completion requirement corresponding to this edge server includes:

[0091] Filter out all the records of completing the computing tasks corresponding to the cloud service nodes in the historical task records corresponding to this edge server to obtain multiple historical associated task records;

[0092] Calculate the average value of the computing efficiency in all historical associated task records to obtain the historical average computing efficiency requirement corresponding to this edge server;

[0093] Calculate the average value of the communication accuracy rate in all historical associated task records to obtain the historical average communication accuracy rate requirement corresponding to this edge server;

[0094] Determine the historical average computing efficiency requirement and the historical average communication accuracy rate requirement as the historical average completion requirement corresponding to this edge server.

[0095] It can be seen that through the above optional embodiments, historical task records related to the computing tasks of the cloud service nodes can be screened out, and the computing efficiency requirements and cloud service communication accuracy requirements corresponding to the edge servers can be determined through average calculation, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of cooperative control and ensure the service quality of cloud services.

[0096] As an optional embodiment, in the above steps, determining the control requirement function according to the cloud service requirement parameters corresponding to each edge server and the computing requirements corresponding to the computing task data includes:

[0097] Determine that the objective function is to minimize the computing task data allocated to each edge server in the cooperative control scheme;

[0098] Determine that the constraint conditions include that the predicted individual computing effects corresponding to each edge server in the cooperative control scheme meet the corresponding cloud service requirement parameters and the predicted parallel computing effects corresponding to the computing task data allocated to all edge servers in the cooperative control scheme meet the computing requirements corresponding to the computing task data; optionally, the cooperative control scheme includes the allocated computing task data and working parameters corresponding to each edge server.

[0099] Determine the objective function and the constraint conditions as the control requirement function.

[0100] It can be seen that through the above optional embodiments, reasonable objective functions and constraint conditions can be accurately determined, so as to obtain a more reasonable cooperative control scheme through subsequent calculations, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of cooperative control and ensure the service quality of cloud services.

[0101] As an optional embodiment, in the above steps, based on the control requirement function and the server information, iterative calculations are performed based on the dynamic programming algorithm to obtain the allocated computing task data and working parameters of each edge server, including:

[0102] For each edge server, calculate the information similarity between the historical server information in the historical application records of multiple candidate prediction neural networks and the server information of this edge server;

[0103] Determine the candidate prediction neural network with the highest information similarity as the computing effect prediction neural network corresponding to this edge server; optionally, the computing effect prediction neural network is trained through a training data set including multiple training allocated computing data and corresponding working parameter annotations and computing effect annotations.

[0104] Iteratively generate collaborative control schemes corresponding to all edge servers according to a preset dynamic programming algorithm, and use the calculation effect prediction neural network corresponding to each edge server to predict the allocated calculation task data and working parameters in the collaborative control scheme to obtain the corresponding predicted individual calculation effect and predicted parallel calculation effect. Retain the collaborative control schemes for which all the corresponding predicted individual calculation effects and predicted parallel calculation effects meet the limiting conditions, and perform iterative calculations until the retained collaborative control schemes meet the objective function, so as to obtain the optimal collaborative control scheme, and obtain the allocated calculation task data and working parameters of each edge server.

[0105] It can be seen that through the above optional embodiments, it is possible to screen out the calculation effect prediction neural network corresponding to the edge server according to the server information, and combine the dynamic programming algorithm to generate and verify the iterative scheme until the optimal collaborative control scheme is obtained, so as to realize the coordinated allocation of multi-party calculations by fully combining the cloud service requirements of the edge server, improve the effect of collaborative control, and ensure the service quality of cloud services.

[0106] Embodiment 2

[0107] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a multi-party collaborative control system centered on cloud-based services disclosed in an embodiment of the present invention. Among them, Figure 2 the described multi-party collaborative control system centered on cloud-based services can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the multi-party collaborative control system centered on cloud-based services may include:

[0108] An acquisition module 201, configured to acquire the calculation task data to be allocated, and the server information and historical task records of multiple edge servers to be controlled.

[0109] A prediction module 202, configured to predict the cloud service requirement parameters corresponding to each edge server based on the historical task records and a prediction algorithm.

[0110] A determination module 203, configured to determine a control requirement function according to the cloud service requirement parameters corresponding to each edge server and the calculation requirements corresponding to the calculation task data.

[0111] A calculation module 204, configured to perform iterative calculations based on the control requirement function and the server information using a dynamic programming algorithm to obtain the allocated calculation task data and working parameters of each edge server.

[0112] It can be seen that the above-described invention embodiments can predict the cloud service requirement parameters corresponding to each edge server based on the historical task records of the edge servers, and then determine the control requirement function according to the cloud service requirement parameters and the computing requirements corresponding to the computing task data, so as to perform iterative calculations based on the dynamic programming algorithm to obtain the allocated computing task data and working parameters of each edge server, thereby being able to fully combine the cloud service requirements of the edge servers to coordinate the allocation of multi-party computing, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0113] As an optional embodiment, the server information includes hardware information, software information, communication performance information, and computing performance information.

[0114] It can be seen that through the above optional embodiment, the content of the server information is defined to comprehensively characterize the characteristics of the server, and assist in achieving the coordination and allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0115] As an optional embodiment, the historical task record includes the execution computing task records and communication records of the edge server in multiple historical time periods.

[0116] It can be seen that through the above optional embodiment, the content of the historical task record is defined to comprehensively characterize the computing records and characteristics of the server in historical time, so as to accurately predict its cloud service requirement parameters, and assist in achieving the coordination and allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of collaborative control and ensure the service quality of cloud services.

[0117] As an optional embodiment, the specific manner in which the prediction module predicts the cloud service requirement parameters corresponding to each edge server according to the historical task record based on the prediction algorithm includes:

[0118] For each edge server, input the historical task record corresponding to the edge server into the trained cloud service prediction neural network to obtain the cloud service node corresponding to the edge server;

[0119] Obtain the preset cloud service requirements of the cloud service node; optionally, the preset cloud service requirements include the preset computing efficiency requirements and the preset communication accuracy rate;

[0120] According to all the records of completing the computing tasks corresponding to the cloud service node in the historical task record corresponding to the edge server, calculate the historical average completion requirements corresponding to the edge server;

[0121] Calculate the average value of the preset cloud service requirements and the historical average completion requirements, and calculate the cloud service requirement parameters corresponding to the edge server; the cloud service requirement parameters include cloud service type, cloud service computing efficiency requirements, and cloud service communication accuracy requirements.

[0122] It can be seen that through the above optional embodiments, the cloud service prediction neural network can predict the cloud service nodes corresponding to the edge servers, and accurately determine the cloud service requirement parameters corresponding to the edge servers based on the preset cloud service requirements of the cloud service nodes and the historical average completion requirements corresponding to the edge servers, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of cooperative control and ensure the service quality of cloud services.

[0123] As an optional embodiment, the cloud service prediction neural network is a CNN network, which is trained by a training data set including multiple training server task records and corresponding cloud service node annotations.

[0124] It can be seen that through the above optional embodiments, the network details and training details of the cloud service prediction neural network are clarified, which can be used to accurately determine the cloud service nodes corresponding to the edge servers, facilitating subsequent calculations and controls, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of cooperative control and ensure the service quality of cloud services.

[0125] As an optional embodiment, the specific method for the prediction module to calculate the historical average completion requirement corresponding to the edge server according to all records of completing the computing tasks corresponding to the cloud service nodes in the historical task records corresponding to the edge server includes:

[0126] Filter out all records of completing the computing tasks corresponding to the cloud service nodes in the historical task records corresponding to the edge server to obtain multiple historical associated task records;

[0127] Calculate the average value of the computing efficiencies in all historical associated task records to obtain the historical average computing efficiency requirement corresponding to the edge server;

[0128] Calculate the average value of the communication accuracies in all historical associated task records to obtain the historical average communication accuracy requirement corresponding to the edge server;

[0129] Determine the historical average computing efficiency requirement and the historical average communication accuracy requirement as the historical average completion requirement corresponding to the edge server.

[0130] It can be seen that through the above optional embodiments, the historical task records related to the computing tasks of the cloud service nodes can be filtered out, and the cloud service computing efficiency requirement and the cloud service communication accuracy requirement corresponding to the edge server can be determined through average calculation, assisting in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of the edge servers, so as to improve the effect of cooperative control and ensure the service quality of cloud services.

[0131] As an optional embodiment, the determining module determines the specific manner of the control requirement function according to the cloud service requirement parameters corresponding to each edge server and the computing requirements corresponding to the computing task data, including:

[0132] Determine that the objective function is to minimize the computing task data allocated to each edge server in the collaborative control scheme;

[0133] Determine that the constraints include that the predicted individual computing effects corresponding to each edge server in the collaborative control scheme meet the corresponding cloud service requirement parameters and the predicted parallel computing effects corresponding to the computing task data allocated to all edge servers in the collaborative control scheme meet the computing requirements corresponding to the computing task data; Optionally, the collaborative control scheme includes the allocated computing task data and working parameters corresponding to each edge server;

[0134] Determine the objective function and the constraints as the control requirement function.

[0135] It can be seen that through the above optional embodiments, reasonable objective functions and constraints can be accurately determined, so as to facilitate subsequent calculations to obtain a more reasonable collaborative control scheme, assist in realizing the coordinated allocation of multi-party computing by fully combining the cloud service requirements of edge servers, improve the effect of collaborative control, and ensure the service quality of cloud services.

[0136] As an optional embodiment, the calculating module performs iterative calculations based on the dynamic programming algorithm according to the control requirement function and the server information to obtain the specific manner of the allocated computing task data and working parameters of each edge server, including:

[0137] For each edge server, calculate the information similarity between the historical server information in the historical application records of multiple candidate prediction neural networks and the server information of this edge server;

[0138] Determine the candidate prediction neural network with the highest information similarity as the computing effect prediction neural network corresponding to this edge server; Optionally, the computing effect prediction neural network is trained through a training data set including multiple training allocated computing data and corresponding working parameter annotations and computing effect annotations;

[0139] Iteratively generate the collaborative control solutions corresponding to all edge servers according to the preset dynamic programming algorithm, and use the computing effect prediction neural network corresponding to each edge server to predict the allocated computing task data and working parameters in the collaborative control solution to obtain the corresponding predicted individual computing effect and predicted parallel computing effect. Retain the collaborative control solutions for which all the corresponding predicted individual computing effects and predicted parallel computing effects meet the limiting conditions, and perform iterative calculations until the retained collaborative control solutions meet the objective function, thereby obtaining the optimal collaborative control solution and the allocated computing task data and working parameters for each edge server.

[0140] It can be seen that through the above optional embodiments, it is possible to screen out the computing effect prediction neural network corresponding to the edge server based on the server information, and combine the dynamic programming algorithm to generate and verify the iterative solutions until the optimal collaborative control solution is obtained, so as to fully combine the cloud service requirements of the edge server to coordinate and allocate multi-party computing, improve the effect of collaborative control, and ensure the service quality of cloud services.

[0141] Embodiment III

[0142] Please refer to Figure 3 , Figure 3 which is another multi-party collaborative control system centered on cloud services disclosed in the embodiments of the present invention. Figure 3 The multi-party collaborative control system centered on cloud services described is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the multi-party collaborative control system centered on cloud services may include:

[0143] A memory 301 storing executable program code;

[0144] A processor 302 coupled to the memory 301;

[0145] Wherein, the processor 302 invokes the executable program code stored in the memory 301 to execute the steps of the multi-party collaborative control method centered on cloud services described in Embodiment I.

[0146] Embodiment IV

[0147] The embodiments of the present invention disclose a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the multi-party collaborative control method centered on cloud services described in Embodiment I.

[0148] Embodiment V

[0149] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the cloud service-centered multi-party collaborative control method described in Embodiment 1.

[0150] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be performed in the specific order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0152] For convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0153] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0154] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 means for the functions specified in one or more processes and / or boxes Figure 1 or multiple boxes.

[0155] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions specified in the process Figure 1 one or more processes and / or boxes Figure 1 or multiple boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one or more processes and / or boxes Figure 1 or multiple boxes.

[0157] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0158] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0159] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0160] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0161] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0162] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for relevant details.

[0163] Finally, it should be noted that: what is disclosed in an embodiment of a multi-lateral collaborative control method and system centered on cloud services according to the present invention is only a preferred embodiment of the present invention, and is only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent substitution on some of the technical features; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multilateral collaborative control method centered on cloud services, characterized in that: The method comprises: Obtain computing task data to be assigned and server information and historical task records of multiple edge servers to be controlled; According to the historical task records, based on the prediction algorithm, predict the cloud service requirement parameters corresponding to each edge server; Determining a control requirement function according to the cloud service requirement parameters corresponding to each of the edge servers and the computing requirements corresponding to the computing task data includes: Determine the objective function to minimize the computing task data assigned to each edge server in the collaborative control scheme; Determining the constraint conditions includes that the predicted individual computing effect corresponding to each edge server in the collaborative control scheme satisfies the corresponding cloud service requirement parameters and the predicted parallel computing effects corresponding to the computing task data assigned to all edge servers in the collaborative control scheme meet the computing requirements corresponding to the computing task data; the collaborative control scheme includes the assigned computing task data and working parameters corresponding to each edge server; Determining the objective function and the constraint condition as a control requirement function; According to the control requirement function and the server information, an iterative calculation is performed based on a dynamic programming algorithm to obtain the distribution computing task data and working parameters of each edge server, including: For each of the edge servers, calculating information similarity between historical server information in historical application records of multiple candidate prediction neural networks and server information of the edge server; Determine the candidate prediction neural network with the highest information similarity as the computing effect prediction neural network corresponding to the edge server; the computing effect prediction neural network is trained by a training data set including a plurality of training allocation computing data and corresponding working parameter annotations and computing effect annotations; According to the preset dynamic programming algorithm, the collaborative control schemes corresponding to all the edge servers are iteratively generated, and the distributed computing task data and working parameters in the collaborative control scheme are predicted by the computing effect prediction neural network corresponding to each edge server to obtain the corresponding predicted individual computing effect and predicted parallel computing effect. The collaborative control schemes whose corresponding predicted individual computing effects and predicted parallel computing effects meet the constraints are retained, and iterative calculations are performed until the retained collaborative control schemes meet the objective function, so as to obtain the optimal collaborative control scheme and the distributed computing task data and working parameters of each edge server.

2. The cloud-based service-centric multilateral collaborative control method according to claim 1, characterized in that: The server information includes hardware information, software information, communication performance information and computing performance information.

3. The cloud-based service-centric multilateral collaborative control method according to claim 1, characterized in that: The historical task records include the execution computing task records and communication records of the edge server in multiple historical time periods.

4. The cloud-based service-centric multilateral collaborative control method according to claim 3 is characterized in that: The predicting, based on the historical task records and a prediction algorithm, of cloud service requirement parameters corresponding to each edge server includes: For each edge server, input the historical task record corresponding to the edge server into the trained cloud service prediction neural network to obtain the cloud service node corresponding to the edge server; Obtaining preset cloud service requirements of the cloud service node; the preset cloud service requirements include preset computing efficiency requirements and preset communication accuracy; Calculate the historical average completion requirement corresponding to the edge server according to all records of completing the computing tasks corresponding to the cloud service node in the historical task records corresponding to the edge server; Calculate the average of the preset cloud service requirement and the historical average completion requirement, and calculate the cloud service requirement parameters corresponding to the edge server; the cloud service requirement parameters include cloud service type, cloud service computing efficiency requirement, and cloud service communication accuracy requirement.

5. The cloud-based service-centric multilateral collaborative control method according to claim 4 is characterized in that: The cloud service prediction neural network is a CNN network, which is trained by a training data set including multiple training server task records and corresponding cloud service node annotations.

6. The cloud service-centric multilateral collaborative control method according to claim 4, characterized in that: The calculating the historical average completion requirement corresponding to the edge server according to all records of completing the computing tasks corresponding to the cloud service node in the historical task records corresponding to the edge server includes: Filter out all records of completing the computing tasks corresponding to the cloud service node in the historical task records corresponding to the edge server to obtain multiple historical associated task records; Calculate the average value of the computing efficiency in all the historical associated task records to obtain the historical average computing efficiency requirement corresponding to the edge server; Calculate the average of the communication accuracy rates in all the historical associated task records to obtain the historical average communication accuracy rate requirement corresponding to the edge server; The historical average computing efficiency requirement and the historical average communication accuracy requirement are determined as the historical average completion requirement corresponding to the edge server.

7. A multilateral collaborative control system centered on cloud services, characterized in that: The system comprises: An acquisition module, used to acquire computing task data to be assigned and server information and historical task records of multiple edge servers to be controlled; A prediction module, configured to predict the cloud service requirement parameters corresponding to each edge server based on the historical task records and a prediction algorithm; A determination module, used to determine a control requirement function according to the cloud service requirement parameters corresponding to each of the edge servers and the computing requirements corresponding to the computing task data, including: Determine the objective function to minimize the computing task data assigned to each edge server in the collaborative control scheme; Determining the constraint conditions includes that the predicted individual computing effect corresponding to each edge server in the collaborative control scheme satisfies the corresponding cloud service requirement parameters and the predicted parallel computing effects corresponding to the computing task data assigned to all edge servers in the collaborative control scheme meet the computing requirements corresponding to the computing task data; the collaborative control scheme includes the assigned computing task data and working parameters corresponding to each edge server; Determining the objective function and the constraint condition as a control requirement function; A calculation module, used to perform iterative calculation based on the dynamic programming algorithm according to the control requirement function and the server information to obtain the distribution calculation task data and working parameters of each edge server, including: For each of the edge servers, calculating information similarity between historical server information in historical application records of multiple candidate prediction neural networks and server information of the edge server; Determine the candidate prediction neural network with the highest information similarity as the computing effect prediction neural network corresponding to the edge server; the computing effect prediction neural network is trained by a training data set including a plurality of training allocation computing data and corresponding working parameter annotations and computing effect annotations; According to the preset dynamic programming algorithm, the collaborative control schemes corresponding to all the edge servers are iteratively generated, and the distributed computing task data and working parameters in the collaborative control scheme are predicted by the computing effect prediction neural network corresponding to each edge server to obtain the corresponding predicted individual computing effect and predicted parallel computing effect. The collaborative control schemes whose corresponding predicted individual computing effects and predicted parallel computing effects meet the constraints are retained, and iterative calculations are performed until the retained collaborative control schemes meet the objective function, so as to obtain the optimal collaborative control scheme and the distributed computing task data and working parameters of each edge server.

8. A multilateral collaborative control system centered on cloud services, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the cloud service-centric multilateral collaborative control method as described in any one of claims 1-6.

Images