Cloud edge collaborative computing power allocation method and system for power dispatching

By collecting power load information in power scheduling, building power load distribution field, analyzing the complexity of load changes, optimizing the power scheduling calculation location, cloud-side collaborative computing power allocation is realized, and the intelligent and low power scheduling computing power allocation is solved. Problem, improving resource utilization.

CN119029903APending Publication Date: 2024-11-26STATE GRID JIANGSU ELECTRIC POWER CO LTD NANTONG POWER SUPPLY BRANCH +3
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411141667.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In the prior art, the computing power allocation of power dispatching is relatively low, which makes it difficult to improve the utilization rate of computing power resources.

Method used

By collecting the power load information of the power user body in multiple time windows, building the power load distribution field, analyzing the complexity of regional load changes, making computing power allocation decisions for cloud power scheduling, and combining load change complexity and timeliness optimization Power scheduling and computing location to realize cloud-edge collaborative computing power allocation.

Benefits of technology

The intelligent allocation of power scheduling computing power has been improved, the utilization rate of computing power resources has been improved, and the problem of difficult to improve the utilization rate of computing power resources has been solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119029903A_ABST
    Figure CN119029903A_ABST
Patent Text Reader

Abstract

The invention discloses a cloud-side collaborative computing power allocation method and system for power dispatching, which are applied to the technical field of data processing and are used for acquiring a plurality of power load chains by acquiring power load information of a plurality of power main bodies in a target area. And based on the plurality of electrical load chains, constructing an electrical load distribution field of the target area, and obtaining an electrical load distribution field chain. And according to the electrical load distribution field chain, analyzing the regional load change complexity of the target region, and performing a computing power allocation decision of cloud power dispatching to obtain cloud allocation computing power. And according to the power utilization load distribution field chain, analyzing load change complexity and timeliness of the plurality of power utilization main bodies. And according to the aging degrees of the plurality of main bodies, performing deployment optimization on the power dispatching calculation positions of the plurality of power utilization main bodies to obtain an optimal deployment scheme. The technical problems that in the prior art, the computing power allocation intelligence of power dispatching is low, and the computing power resource utilization rate is difficult to improve are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a cloud-edge collaborative computing power allocation method and system for power dispatching. Background Art

[0002] Power dispatching is based on the acquisition of power data by information collection equipment and the distribution of power in combination with power grid operation data, so as to ensure the safe and stable operation of the power grid. The power dispatching data is processed based on computer computing power. However, in the existing technology, the computing power allocation of power dispatching is relatively low in intelligence, and there is a problem that the utilization rate of computing power resources is difficult to improve.

[0003] Therefore, in the existing technology, the intelligent allocation of computing power in power dispatching is relatively low, and there is a technical problem that it is difficult to improve the utilization rate of computing power resources. Summary of the invention

[0004] The present application solves the technical problems in the prior art that the computing power allocation for power dispatching is less intelligent and it is difficult to improve the utilization rate of computing power resources by providing a cloud-edge collaborative computing power allocation method and system for power dispatching.

[0005] The present application provides a cloud-edge collaborative computing power allocation method for power dispatching, the method comprising: collecting power load information of multiple power users in a target area in multiple time windows to obtain multiple power load chains; constructing a power load distribution field in the target area based on the multiple power load chains to obtain a power load distribution field chain; analyzing the complexity of regional load changes in the target area according to the power load distribution field chain, and making computing power allocation decisions for cloud-based power dispatching to obtain cloud-based allocated computing power; analyzing the complexity and timeliness of load changes of the multiple power users according to the power load distribution field chain , obtain multiple subject complexities and multiple subject timeliness; according to the multiple subject timeliness, optimize the power dispatching and computing positions of the multiple power users to obtain the optimal deployment plan, wherein the power dispatching and computing positions include the cloud or the edge, and the optimal deployment plan includes multiple edge scheduling and computing positions and multiple cloud scheduling and computing positions; based on the optimal deployment plan, combined with the multiple subject complexities, make deployment decisions on the computing power of the multiple edge scheduling and computing positions, obtain multiple edge-end deployment computing powers, and deploy the power dispatching of multiple power users in combination with the cloud-end deployment computing power.

[0006] The present application also provides a cloud-edge collaborative computing power allocation system for power dispatching, the system comprising: a data acquisition module, used to collect power load information of multiple power users in a target area in multiple time windows, and obtain multiple power load chains; a load distribution acquisition module, used to construct a power load distribution field in the target area based on multiple power load chains, and obtain a power load distribution field chain; a cloud computing power allocation module, used to analyze the complexity of regional load changes in the target area according to the power load distribution field chain, and make computing power allocation decisions for cloud power dispatching, and obtain cloud-based allocated computing power; a data analysis module, used to analyze the load changes of the multiple power users according to the power load distribution field chain. The complexity and timeliness are analyzed to obtain multiple subject complexities and multiple subject timeliness; a dispatching scheme acquisition module is used to dispatch and optimize the power dispatching and computing positions of the multiple power users according to the multiple subject timeliness to obtain the optimal dispatching scheme, wherein the power dispatching and computing positions include the cloud or the edge, and the optimal dispatching scheme includes multiple edge dispatching and computing positions and multiple cloud dispatching and computing positions; a dispatching deployment module is used to make dispatching decisions on the computing power of the multiple edge dispatching and computing positions based on the optimal dispatching scheme and in combination with the multiple subject complexities, obtain multiple edge-end dispatching computing powers, and deploy the power dispatching of multiple power users in combination with the cloud-end dispatching computing power.

[0007] The present application also provides an electronic device, including:

[0008] A memory for storing executable instructions;

[0009] The processor is used to implement the cloud-edge collaborative computing power allocation method for power dispatching provided in the present application when executing the executable instructions stored in the memory.

[0010] The present application provides a computer-readable storage medium storing a computer program. When the program is executed by a processor, the cloud-edge collaborative computing power allocation method for power dispatching provided by the present application is implemented.

[0011] It is proposed that the cloud-edge collaborative computing power allocation method and system for power dispatching proposed in this application collect the power load information of multiple power users in the target area to obtain multiple power load chains. Based on the multiple power load chains, a power load distribution field of the target area is constructed to obtain a power load distribution field chain. According to the power load distribution field chain, the complexity of the regional load change of the target area is analyzed, and the computing power allocation decision of the cloud power dispatching is made to obtain the cloud-based allocated computing power. According to the power load distribution field chain, the complexity and timeliness of the load changes of the multiple power users are analyzed. According to the timeliness of the multiple subjects, the power dispatching calculation positions of the multiple power users are allocated and optimized to obtain the optimal allocation plan. The intelligent allocation of power dispatching computing power is realized, and the utilization rate of computing power resources is improved. The technical problem that the intelligence of computing power allocation for power dispatching in the prior art is low and the utilization rate of computing power resources is difficult to improve is solved.

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0014] Figure 1 A flowchart of a cloud-edge collaborative computing power allocation method for power dispatching provided in an embodiment of the present application;

[0015] Figure 2 A schematic diagram of a flow chart of generating a power load distribution field chain for a cloud-edge collaborative computing power allocation method for power dispatching provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of a process for obtaining cloud-allocated computing power by using a cloud-edge collaborative computing power allocation method for power dispatching provided in an embodiment of the present application;

[0017] Figure 4 A schematic diagram of the structure of a system for a cloud-edge collaborative computing power allocation method for power dispatching provided in an embodiment of the present application;

[0018] Figure 5 A structural diagram of the system electronic equipment of the cloud-edge collaborative computing power allocation method for power dispatching provided in an embodiment of the present invention.

[0019] Explanation of the accompanying drawings: data acquisition module 11, load distribution acquisition module 12, cloud computing power allocation module 13, data analysis module 14, allocation plan acquisition module 15, scheduling and deployment module 16, processor 31, memory 32, input device 33, output device 34. DETAILED DESCRIPTION

[0020] Embodiment 1

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0025] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, the modules are illustrative only, and different aspects of the system and method may use different modules.

[0026] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0027] like Figure 1 As shown, the embodiment of the present application provides a cloud-edge collaborative computing power allocation method for power dispatching, the method comprising:

[0028] Collect the power load information of multiple power users in the target area in multiple time windows to obtain multiple power load chains;

[0029] Based on multiple power load chains, a power load distribution field of a target area is constructed to obtain a power load distribution field chain;

[0030] According to the power load distribution field chain, the complexity of regional load changes in the target area is analyzed, and computing power allocation decisions for cloud power dispatch are made to obtain cloud-based allocated computing power;

[0031] In multiple time windows, the power load information of multiple power users in the target area is collected, and the power load information includes specific power load locations and power load data, and multiple power load chains are obtained. The power load chains include the power locations and power load data of multiple power users in the target area at different time window nodes, and the time window is a fixed collection time node. Subsequently, based on the multiple power load chains, the power loads of multiple power users in the target area in each time window are obtained, and the power load distribution field of the target area is constructed. The power load distribution field of the target area is arranged in sequence according to multiple time windows to obtain a power load distribution field chain. Furthermore, according to the power load distribution field chain, the complexity of the regional load changes in the target area is analyzed, and computing power allocation decisions for cloud power scheduling are made to obtain cloud-allocated computing power.

[0032] like Figure 2 As shown, the method provided in the embodiment of the present application also includes:

[0033] Based on the multiple time windows, in the multiple power load chains, extracting power load information of multiple power users to obtain multiple power load information sets;

[0034] According to a plurality of power load information sets, a plurality of power load distribution fields of a plurality of time windows are constructed to form the power load distribution field chain.

[0035] Based on the multiple time windows, in the multiple power load chains, the power load information of multiple power users is extracted to obtain multiple power load information sets, wherein each power load information set corresponds to the power load information of multiple power users in a single time window. Based on the multiple power load information sets and the map data of the target area, a digital power load map of the target area in different time windows is constructed based on the digital twin technology. The location data and the power load data in the multiple power load information sets in the target area are marked with location points, and the power load data are marked and displayed according to the grayscale value or other color. Thus, the construction of the digital map of the target area is completed, and the establishment of the power load distribution field is completed. There is a corresponding relationship between the power load data and the grayscale value, and different power load data intervals correspond to a grayscale value or color. Multiple power load distribution fields corresponding to multiple time windows are constructed and obtained, and they are arranged in time sequence to form the power load distribution field chain.

[0036] like Figure 3 As shown, the method provided in the embodiment of the present application also includes:

[0037] Obtain a sample power load distribution field set, perform change complexity analysis, and obtain a sample change complexity set;

[0038] Based on the twin network, a power load complexity analyzer is constructed, and the sample power load distribution field set and the sample change complexity set are used for training until convergence;

[0039] According to the multiple power load distribution fields in the power load distribution field chain, multiple groups of two adjacent power load distribution fields are input into the power load complexity analyzer to obtain multiple adjacent change complexities;

[0040] Inputting the first power load distribution field and the last power load distribution field in the plurality of power load distribution fields into the power load complexity analyzer to obtain the overall change complexity;

[0041] Calculating and obtaining the basic load change complexity of the target area according to the multiple adjacent change complexities;

[0042] According to the overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity, and a computing power allocation decision for cloud power dispatching is made to obtain cloud-based allocated computing power.

[0043] When obtaining cloud-based computing power allocation, a sample power load distribution field set is obtained, and the sample power load distribution field set is a known historically constructed image data set of power load distribution fields. The data in the sample power load distribution field set is subjected to artificial change complexity analysis. During the analysis, the sample change complexity set is obtained by subtracting the similarity of the image data of adjacent power load distribution fields from 1. Based on the twin network, a power load complexity analyzer is constructed, and the sample power load distribution field set and the sample change complexity set are used for training until convergence, wherein the data in adjacent sample power load distribution fields and the sample change complexity set in the sample power load distribution field set correspond to each other. According to multiple power load distribution fields in the power load distribution field chain, multiple groups of two adjacent power load distribution fields are input into the power load complexity analyzer to obtain multiple adjacent change complexities. Subsequently, the first power load distribution field and the last power load distribution field in the multiple power load distribution fields are input into the power load complexity analyzer to obtain the overall change complexity. Furthermore, according to the plurality of adjacent change complexities, an average calculation is performed to obtain the basic load change complexity of the target area. According to the overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity, and a computing power allocation decision for cloud power dispatching is made to obtain cloud-based allocated computing power.

[0044] The method provided in the embodiment of the present application also includes:

[0045] Based on the historical power dispatch data of the target area, obtaining an average overall change complexity;

[0046] According to the overall change complexity and the average overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity;

[0047] Obtain a set of sample area load change complexity and a set of sample cloud computing power allocation, and build a cloud computing power decision maker based on the decision tree;

[0048] Based on the cloud computing power decision maker, a computing power allocation decision is made according to the complexity of the regional load change to obtain the cloud-allocated computing power.

[0049] When making a computing power allocation decision and obtaining the cloud-allocated computing power, based on the historical power dispatching data of the target area, the historical power dispatching data in multiple time windows are obtained. Based on the historical power dispatching data in multiple time windows, the overall change complexity acquisition scheme is adopted to obtain the corresponding historical overall change complexity of each historical power dispatching data, and the average of each historical overall change complexity is calculated to obtain the average overall change complexity. A weighted average is performed according to the overall change complexity and the average overall change complexity. The specific weight data can be set based on the technical personnel. The average is calculated according to the weighted average result and the basic load change complexity to obtain the regional load change complexity. A sample regional load change complexity set and a sample cloud-allocated computing power set are obtained. The sample cloud-allocated computing power set is a set of allocation computing power data corresponding to the sample regional load change complexity set. Further, a decision tree is constructed based on the sample regional load change complexity set and the sample cloud-allocated computing power set to obtain a cloud computing power decision maker. The cloud computing power decision maker is used to make computing power allocation decisions based on the regional load change complexity. Finally, based on the cloud computing power decision maker, a computing power allocation decision is made based on the complexity of the regional load change to obtain the corresponding cloud-allocated computing power.

[0050] According to the power load distribution field chain, the load change complexity and timeliness of the multiple power users are analyzed to obtain multiple subject complexities and multiple subject timeliness;

[0051] According to the timeliness of the multiple subjects, the power dispatching and computing positions of the multiple power-consuming subjects are optimized to obtain an optimal dispatching scheme, wherein the power dispatching and computing position includes a cloud or an edge end, and the optimal dispatching scheme includes multiple edge dispatching and computing positions and multiple cloud dispatching and computing positions;

[0052] Based on the optimal allocation plan and combined with the complexity of the multiple entities, an allocation decision is made on the computing power of the multiple edge scheduling computing locations, multiple edge-end allocation computing powers are obtained, and combined with the cloud-side allocation computing power, power scheduling for multiple electricity users is deployed.

[0053] According to the power load distribution field chain, the load change complexity and timeliness of the multiple power users are analyzed to obtain multiple subject complexities and multiple subject timeliness. Further, according to the multiple subject timeliness, the power dispatching and computing positions of the multiple power users are optimized to obtain the optimal dispatching scheme, wherein the power dispatching and computing positions include the cloud or the edge, and the optimal dispatching scheme includes multiple edge dispatching and computing positions and multiple cloud dispatching and computing positions. Finally, based on the optimal dispatching scheme and combined with the multiple subject complexities, the computing power of the multiple edge dispatching and computing positions is allocated and decided, that is, according to the complexity of the power user, the computing power of each edge is decided, and the complexity is proportional to the computing power. Multiple edge allocation computing powers are obtained, and combined with the cloud allocation computing power, the power dispatching of multiple power users is deployed. The intelligent allocation of power dispatching computing power is realized, and the utilization rate of computing power resources is improved.

[0054] The method provided in the embodiment of the present application also includes:

[0055] Calculate and obtain load variances of multiple electricity users according to the electricity load information of multiple electricity users in the electricity load distribution field chain;

[0056] According to the variance of multiple subject loads, multiple subject complexities are calculated;

[0057] According to the difference of adjacent power load information of multiple power users in the power load distribution field chain, combined with the multiple time windows, the variance of load changes of multiple users is calculated;

[0058] According to the variance of multiple subject load changes, multiple subject time validity is calculated.

[0059] Obtaining multiple subject complexities and multiple subject timeliness, including: performing variance calculations based on the power load information of multiple power users in the power load distribution field chain in different time windows, and calculating and obtaining multiple subject load variances. Based on the multiple subject load variances, then calculating the ratio of the variance of each subject to the historical average load variance of each subject, and calculating and obtaining multiple subject complexities. Among them, the historical average load variance is the mean of the corresponding subject load variances of the same power user in the same time window in history. Based on the difference in adjacent power load information of multiple power users in the power load distribution field chain, combined with the multiple time windows, calculate and obtain multiple subject load change variances. Based on the multiple subject load change variances, calculate and obtain multiple subject timeliness. That is, the ratio of the difference between multiple groups of adjacent power load information of each power user and the time span is calculated to obtain the power load change rate, and then the variance of multiple power load change rates is calculated to obtain multiple subject load change variances, and then the ratio of multiple subject load change variances to the corresponding power user's historical average power load change rate variance is calculated as the subject timeliness.

[0060] The method provided in the embodiment of the present application also includes:

[0061] According to the size of the cloud-allocated computing power, an optimization constraint condition is set, wherein the optimization constraint condition is that the sum of the power dispatching computing power in the cloud is not greater than the cloud-allocated computing power;

[0062] Based on the optimization constraint condition, construct a deployment plan space, wherein the deployment plan space includes multiple deployment plans that meet the optimization constraint condition;

[0063] Construct the deployment optimization function as follows:

[0064]

[0065] Among them, dep is the dispatching fitness, m is the number of power users that set the power dispatching calculation location at the edge in the dispatching plan, S i The subject timeliness of the i-th power user who sets the power dispatch calculation location at the edge;

[0066] Based on the deployment optimization function, the deployment plan with the maximum deployment fitness is optimized in the deployment plan space to obtain the optimal deployment plan.

[0067] Obtaining the optimal allocation plan includes: setting an optimization constraint condition according to the size of the cloud allocation computing power, wherein the optimization constraint condition is that the sum of the power dispatch computing power in the cloud is not greater than the cloud allocation computing power. Subsequently, based on the optimization constraint condition, a deployment plan space is constructed, wherein the deployment plan space includes multiple deployment plans that meet the optimization constraint condition, and the multiple deployment plans are deployment plans randomly set based on the optimization constraint condition. Further, a deployment optimization function is constructed, as shown in the following formula: Where, dep is the dispatching fitness, m is the number of power users that set the power dispatching calculation location at the edge in the dispatching scheme, and S i The timeliness of the subject of the i-th power user who sets the power dispatch calculation position at the edge. Optimize and obtain the dispatching scheme with the maximum sum of the timeliness of the power users who perform power dispatch calculation at the edge. Place the power dispatch of the subject with large timeliness at the corresponding edge to improve timeliness, and place the power dispatch calculation of the subject with small timeliness in the cloud. Finally, based on the dispatching optimization function, optimize the dispatching scheme with the maximum dispatching fitness in the dispatching scheme space to obtain the optimal dispatching scheme.

[0068] The method provided in the embodiment of the present application also includes:

[0069] Based on the power dispatch history data of the power users at the plurality of edge dispatch calculation locations, a plurality of sample subject complexity sets are collected, and a plurality of sample dispatch computing power sets are obtained;

[0070] The plurality of sample main body complexity sets and the plurality of sample allocation computing power sets are respectively adopted to construct a plurality of edge computing power allocation branches, and obtain an edge computing power allocator;

[0071] The edge computing power allocator is used to make decisions on the edge computing power of the electricity users at the multiple edge scheduling and computing locations to obtain multiple edge-allocated computing powers.

[0072] Based on the power dispatch history data of the power users at the multiple edge dispatch calculation locations, collect the corresponding multiple sample subject complexity sets of the power users, and obtain multiple sample allocation computing power sets. Subsequently, use the multiple sample subject complexity sets and the multiple sample allocation computing power sets to construct multiple edge computing power allocation branches, each edge computing power allocation branch corresponds to a complexity data, and obtain an edge computing power allocator. Finally, use the edge computing power allocator to make decisions on the edge computing power of the power users at the multiple edge dispatch calculation locations according to the complexity, and obtain multiple edge allocation computing powers.

[0073] The technical solution provided by the embodiment of the present invention obtains multiple power load chains by collecting power load information of multiple power users in the target area in multiple time windows. Based on the multiple power load chains, a power load distribution field of the target area is constructed to obtain a power load distribution field chain. According to the power load distribution field chain, the complexity of the regional load change of the target area is analyzed, and the computing power allocation decision of the cloud power dispatch is made to obtain the cloud allocation computing power. According to the power load distribution field chain, the load change complexity and timeliness of the multiple power users are analyzed to obtain multiple subject complexities and multiple subject timeliness. According to the multiple subject timeliness, the power dispatch calculation positions of the multiple power users are dispatched and optimized to obtain the optimal dispatch scheme, wherein the power dispatch calculation position includes the cloud or the edge, and the optimal dispatch scheme includes multiple edge dispatch calculation positions and multiple cloud dispatch calculation positions. Based on the optimal allocation scheme, combined with the complexity of the multiple entities, the computing power of the multiple edge scheduling calculation locations is allocated and decided, multiple edge-end allocation computing power is obtained, and combined with the cloud-based allocation computing power, the power dispatch of multiple power-consuming entities is deployed. The intelligent allocation of power dispatch computing power is realized, and the utilization rate of computing power resources is improved. The technical problem that the computing power allocation of power dispatch in the prior art is low in intelligence and it is difficult to improve the utilization rate of computing power resources is solved.

[0074] Embodiment 2

[0075] Based on the same inventive concept as the cloud-edge collaborative computing power allocation method for power dispatching in the aforementioned embodiment, the present invention also provides a system for the cloud-edge collaborative computing power allocation method for power dispatching. The system can be implemented in hardware and / or software, and can generally be integrated into an electronic device to execute the method provided by any embodiment of the present invention. Figure 4 As shown, the system comprises:

[0076] The data acquisition module 11 is used to collect the power load information of multiple power users in the target area in multiple time windows to obtain multiple power load chains;

[0077] A load distribution acquisition module 12 is used to construct a power load distribution field of a target area based on multiple power load chains, and obtain a power load distribution field chain;

[0078] The cloud computing power allocation module 13 is used to analyze the complexity of regional load changes in the target area according to the power load distribution field chain, and make computing power allocation decisions for cloud power dispatching to obtain cloud-allocated computing power;

[0079] The data analysis module 14 is used to analyze the load change complexity and timeliness of the multiple power users according to the power load distribution field chain to obtain multiple subject complexities and multiple subject timeliness;

[0080] The dispatching scheme acquisition module 15 is used to dispatch and optimize the power dispatching calculation positions of the multiple power-consuming entities according to the timeliness of the multiple entities to obtain an optimal dispatching scheme, wherein the power dispatching calculation position includes a cloud or an edge end, and the optimal dispatching scheme includes multiple edge dispatching calculation positions and multiple cloud dispatching calculation positions;

[0081] The scheduling and deployment module 16 is used to make scheduling decisions on the computing power of the multiple edge scheduling computing locations based on the optimal scheduling plan and the complexity of the multiple entities, obtain multiple edge-end scheduling computing powers, and deploy power scheduling for multiple electricity users in combination with cloud-based scheduling computing powers.

[0082] Furthermore, the load distribution acquisition module 12 is also used for:

[0083] Based on the multiple time windows, in the multiple power load chains, extracting power load information of multiple power users to obtain multiple power load information sets;

[0084] According to a plurality of power load information sets, a plurality of power load distribution fields of a plurality of time windows are constructed to form the power load distribution field chain.

[0085] Furthermore, the cloud computing power allocation module 13 is also used for:

[0086] Obtain a sample power load distribution field set, perform change complexity analysis, and obtain a sample change complexity set;

[0087] Based on the twin network, a power load complexity analyzer is constructed, and the sample power load distribution field set and the sample change complexity set are used for training until convergence;

[0088] According to the multiple power load distribution fields in the power load distribution field chain, multiple groups of two adjacent power load distribution fields are input into the power load complexity analyzer to obtain multiple adjacent change complexities;

[0089] Inputting the first power load distribution field and the last power load distribution field in the plurality of power load distribution fields into the power load complexity analyzer to obtain the overall change complexity;

[0090] Calculating and obtaining the basic load change complexity of the target area according to the multiple adjacent change complexities;

[0091] According to the overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity, and a computing power allocation decision for cloud power dispatching is made to obtain cloud-based allocated computing power.

[0092] Furthermore, the cloud computing power allocation module 13 is also used for:

[0093] Based on the historical power dispatch data of the target area, obtaining an average overall change complexity;

[0094] According to the overall change complexity and the average overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity;

[0095] Obtain a set of sample area load change complexity and a set of sample cloud computing power allocation, and build a cloud computing power decision maker based on the decision tree;

[0096] Based on the cloud computing power decision maker, a computing power allocation decision is made according to the complexity of the regional load change to obtain the cloud-allocated computing power.

[0097] Furthermore, the data analysis module 14 is also used for:

[0098] Calculate and obtain load variances of multiple electricity users according to the electricity load information of multiple electricity users in the electricity load distribution field chain;

[0099] According to the variance of multiple subject loads, multiple subject complexities are calculated;

[0100] According to the difference of adjacent power load information of multiple power users in the power load distribution field chain, combined with the multiple time windows, the variance of load changes of multiple users is calculated;

[0101] According to the variance of multiple subject load changes, multiple subject time validity is calculated.

[0102] Furthermore, the deployment plan acquisition module 15 is also used for:

[0103] According to the size of the cloud-allocated computing power, an optimization constraint condition is set, wherein the optimization constraint condition is that the sum of the power dispatching computing power in the cloud is not greater than the cloud-allocated computing power;

[0104] Based on the optimization constraint condition, construct a deployment plan space, wherein the deployment plan space includes multiple deployment plans that meet the optimization constraint condition;

[0105] Construct the deployment optimization function as follows:

[0106]

[0107] Among them, dep is the dispatching fitness, m is the number of power users that set the power dispatching calculation location at the edge in the dispatching plan, S i The subject timeliness of the i-th power user who sets the power dispatch calculation location at the edge;

[0108] Based on the deployment optimization function, the deployment plan with the maximum deployment fitness is optimized in the deployment plan space to obtain the optimal deployment plan.

[0109] Furthermore, the scheduling and deployment module 16 is also used for:

[0110] Based on the power dispatch history data of the power users at the plurality of edge dispatch calculation locations, a plurality of sample subject complexity sets are collected, and a plurality of sample dispatch computing power sets are obtained;

[0111] The plurality of sample main body complexity sets and the plurality of sample allocation computing power sets are respectively adopted to construct a plurality of edge computing power allocation branches, and obtain an edge computing power allocator;

[0112] The edge computing power allocator is used to make decisions on the edge computing power of the electricity users at the multiple edge scheduling and computing locations to obtain multiple edge-allocated computing powers.

[0113] The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0114] Embodiment 3

[0115] Figure 5 The schematic diagram of the structure of the electronic device provided in the third embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 5 As shown, the electronic device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 5 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the electronic device can be connected through a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0116] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the cloud-edge collaborative computing power allocation method for power dispatching in the embodiment of the present invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 32, that is, realizing the above-mentioned cloud-edge collaborative computing power allocation method for power dispatching.

[0117] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A cloud-edge collaborative computing power allocation method for power dispatching, characterized in that: The method comprises: Collect the power load information of multiple power users in the target area in multiple time windows to obtain multiple power load chains; Based on multiple power load chains, construct a power load distribution field in the target area to obtain a power load distribution field chain; According to the power load distribution field chain, the complexity of regional load changes in the target area is analyzed, and computing power allocation decisions for cloud power dispatch are made to obtain cloud-based allocated computing power; According to the power load distribution field chain, the load change complexity and timeliness of the multiple power users are analyzed to obtain multiple subject complexities and multiple subject timeliness; According to the timeliness of the multiple subjects, the power dispatching and computing positions of the multiple power-consuming subjects are optimized to obtain an optimal dispatching scheme, wherein the power dispatching and computing position includes a cloud or an edge end, and the optimal dispatching scheme includes multiple edge dispatching and computing positions and multiple cloud dispatching and computing positions; Based on the optimal allocation plan and combined with the complexity of the multiple entities, an allocation decision is made on the computing power of the multiple edge scheduling computing locations, multiple edge-end allocation computing powers are obtained, and combined with the cloud-side allocation computing power, power scheduling for multiple electricity users is deployed.

2. The method according to claim 1, characterized in that Based on multiple power load chains, the power load distribution field of the target area is constructed to obtain the power load distribution field chain, including: Based on the multiple time windows, in the multiple power load chains, extracting power load information of multiple power users to obtain multiple power load information sets; According to a plurality of power load information sets, a plurality of power load distribution fields of a plurality of time windows are constructed to form the power load distribution field chain.

3. The method according to claim 1, characterized in that According to the power load distribution field chain, the complexity of regional load changes in the target area is analyzed, and a computing power allocation decision for cloud power dispatch is made to obtain cloud-based allocated computing power, including: Obtain a sample power load distribution field set, perform change complexity analysis, and obtain a sample change complexity set; Based on the twin network, a power load complexity analyzer is constructed, and the sample power load distribution field set and the sample change complexity set are used for training until convergence; According to the multiple power load distribution fields in the power load distribution field chain, multiple groups of two adjacent power load distribution fields are input into the power load complexity analyzer to obtain multiple adjacent change complexities; Inputting the first power load distribution field and the last power load distribution field in the plurality of power load distribution fields into the power load complexity analyzer to obtain the overall change complexity; Calculating and obtaining the basic load change complexity of the target area according to the multiple adjacent change complexities; According to the overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity, and a computing power allocation decision for cloud power dispatching is made to obtain cloud-based allocated computing power.

4. The method according to claim 3, characterized in that According to the overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity, and a computing power allocation decision for cloud power dispatch is made, including: Based on the historical power dispatch data of the target area, obtaining an average overall change complexity; According to the overall change complexity and the average overall change complexity, the basic load change complexity is corrected and calculated to obtain the regional load change complexity; Obtain a set of sample area load change complexity and a set of sample cloud computing power allocation, and build a cloud computing power decision maker based on the decision tree; Based on the cloud computing power decision maker, a computing power allocation decision is made according to the complexity of the regional load change to obtain the cloud-allocated computing power.

5. The method according to claim 1, characterized in that According to the power load distribution field chain, the load change complexity and timeliness of the multiple power users are analyzed to obtain multiple subject complexities and multiple subject timeliness, including: Calculate and obtain load variances of multiple electricity users according to the electricity load information of multiple electricity users in the electricity load distribution field chain; According to the variance of multiple subject loads, multiple subject complexities are calculated; According to the difference of adjacent power load information of multiple power users in the power load distribution field chain, combined with the multiple time windows, the variance of load changes of multiple users is calculated; According to the variance of multiple subject load changes, multiple subject time validity is calculated.

6. The method according to claim 1, characterized in that According to the timeliness of the multiple subjects, the power dispatching calculation positions of the multiple power users are optimized to obtain an optimal dispatching solution, including: According to the size of the cloud-allocated computing power, an optimization constraint condition is set, wherein the optimization constraint condition is that the sum of the power dispatching computing power in the cloud is not greater than the cloud-allocated computing power; Based on the optimization constraint condition, construct a deployment plan space, wherein the deployment plan space includes multiple deployment plans that meet the optimization constraint condition; Construct the deployment optimization function as follows: Among them, dep is the dispatching fitness, m is the number of power users that set the power dispatching calculation location at the edge in the dispatching plan, S i The subject timeliness of the i-th power user who sets the power dispatch calculation location at the edge; Based on the deployment optimization function, the deployment plan with the maximum deployment fitness is optimized in the deployment plan space to obtain the optimal deployment plan.

7. The method according to claim 1, characterized in that Based on the optimal allocation scheme and in combination with the complexity of the multiple entities, an allocation decision is made on the computing power of the multiple edge scheduling computing positions to obtain multiple edge end allocation computing powers, including: Based on the power dispatch history data of the power users at the plurality of edge dispatch calculation locations, a plurality of sample subject complexity sets are collected, and a plurality of sample dispatch computing power sets are obtained; The plurality of sample main body complexity sets and the plurality of sample allocation computing power sets are respectively adopted to construct a plurality of edge computing power allocation branches, and obtain an edge computing power allocator; The edge computing power allocator is used to make decisions on the edge computing power of the electricity users at the multiple edge scheduling and computing locations to obtain multiple edge-allocated computing powers.

8. A cloud-edge collaborative computing power allocation system for power dispatching, characterized in that: The system comprises: A data acquisition module is used to collect power load information of multiple power users in a target area in multiple time windows to obtain multiple power load chains; A load distribution acquisition module is used to construct a power load distribution field of a target area based on multiple power load chains and obtain a power load distribution field chain; A cloud computing power allocation module is used to analyze the complexity of regional load changes in the target area according to the power load distribution field chain, and make computing power allocation decisions for cloud power dispatching to obtain cloud-allocated computing power; A data analysis module, configured to analyze the load change complexity and timeliness of the plurality of power users according to the power load distribution field chain, and obtain the complexity of the plurality of users and the timeliness of the plurality of users; A dispatching scheme acquisition module is used to dispatch and optimize the power dispatching calculation positions of the multiple power-consuming entities according to the timeliness of the multiple entities to obtain an optimal dispatching scheme, wherein the power dispatching calculation position includes a cloud or an edge end, and the optimal dispatching scheme includes multiple edge dispatching calculation positions and multiple cloud dispatching calculation positions; The scheduling and deployment module is used to make scheduling decisions on the computing power of the multiple edge scheduling calculation locations based on the optimal scheduling plan and the complexity of the multiple entities, obtain multiple edge-end scheduling computing powers, and deploy power scheduling for multiple electricity users in combination with cloud-based scheduling computing powers.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the cloud-edge collaborative computing power allocation method for power dispatching as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the cloud-edge collaborative computing power allocation method for power dispatching as described in any one of claims 1-7.

Citation Information

Cited By

  • Method and system for evaluating comprehensive performance of electric energy meter

    CN119439037A