Edge calculation distribution method and system for power data processing

Abstract

The invention relates to the technical field of power data processing, and discloses an edge calculation distribution method and system for power data processing. The method comprises the steps of configuring an electric power data processing scene, formulating an allocation method based on the scene and constructing an edge calculation allocation learning model, training the edge calculation allocation learning model to obtain an edge calculation allocation model, and obtaining a real-time electric power data processing demand and operating the edge calculation allocation model to obtain a corresponding allocation method. The system corresponds to the method. According to the method, classification of power data processing is realized through the configuration scene, a data basis is provided for targeted calculation, the data processing efficiency is improved, the pertinence of edge calculation distribution is improved through the customized distribution method, reasonable distribution of edge calculation of power data processing is realized through the edge calculation distribution model, and the power data processing efficiency is improved. And finally, the power data processing efficiency and quality are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power data processing, and specifically to an edge computing allocation method and system for power data processing. Background Art

[0002] With the rapid development of the power system, its intelligence level is increasing day by day, and a huge amount of data is generated at the same time. These data come from various links such as power generation, transmission, transformation, distribution and power consumption, including equipment operation status, power load changes, power quality parameters, etc. However, the traditional centralized data processing method shows obvious shortcomings when facing such a huge amount of data and real-time requirements. Therefore, it is necessary to study power data processing.

[0003] With the rise of edge computing technology, new solutions have been brought to power data processing. Edge computing can process and analyze data close to the data source, reduce data transmission delays, and improve response speed. However, the existing edge computing distribution methods and systems still have the following obvious problems in the application of the power field:

[0004] It is impossible to accurately allocate computing resources based on the characteristics of power data, such as data priority, resource requirements, processing complexity, and urgency.

[0005] This problem leads to untimely processing of key data, affecting the stable operation and optimization decision-making of the power system. Therefore, there is an urgent need for an efficient edge computing allocation method and system specifically for power data processing to improve the efficiency and quality of power data processing. Summary of the invention

[0006] The purpose of this application is to provide an edge computing allocation method and system for power data processing to solve the technical problems raised in the above background technology.

[0007] To achieve the above objectives, this application discloses the following technical solutions:

[0008] In a first aspect, the present application discloses an edge computing allocation method for power data processing, the method comprising:

[0009] S1: Configure power data processing scenarios, including operation management scenarios and marketing service scenarios;

[0010] S2: Formulate a corresponding allocation method based on the scenario and build an edge computing allocation learning model;

[0011] S3: Obtain historical power data processing records, and train the edge computing allocation learning model based on the historical power data processing records to obtain an edge computing allocation model;

[0012] S4: Obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

[0013] Preferably, the scenario of configuring power data processing specifically includes:

[0014] Classifying various types of power data processing based on operation management and marketing services, and defining the classification results as the scenarios;

[0015] Each type of power data processing is classified into the corresponding scenario, and a scenario label is set accordingly. The scenario label is used to characterize the scenario to which the power data processing of this type belongs.

[0016] Preferably, the corresponding allocation method based on the scenario specifically includes:

[0017] The first allocation method corresponding to the operation management scenario includes the following steps:

[0018] A1: Obtain data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US; wherein the data priority score is used to characterize the priority level of data calculation and the score is proportional to the priority level, the resource allocation score is used to characterize the quality level of resources used for data calculation and the score is proportional to the quality of resources used, the complexity score is used to characterize the complexity level of data calculation and the score is proportional to the complexity level, and the urgency score is used to characterize the time urgency level of data calculation and the score is proportional to the time urgency level;

[0019] A2: Calculate a first allocation score, where the first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is specifically:

[0020] AS first =α1*DpS+α2*RaS+α3*CS+α4*US

[0021] Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first scoring the first allocation;

[0022] The second allocation method corresponding to the marketing service scenario includes the following steps:

[0023] B1: Obtain the customer grade score CgS, the customer scale score CsS and the business score BS; the customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer, the customer scale score is used to characterize the size of the data volume corresponding to the customer scale and the score is proportional to the size of the data volume corresponding to the customer scale, and the business score is used to characterize the importance of the business and the score is proportional to the importance of the business;

[0024] B2: Calculate a second allocation score, which is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula of the second allocation score is specifically:

[0025] AS second =β1*CgS+β2*CsS+β3*BS

[0026] Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second scoring the second allocation;

[0027] An edge computing allocation method library is constructed, where the edge computing allocation method library is used to match the corresponding allocation method based on any one or more of the first allocation score and the second allocation score.

[0028] Preferably, the construction of the edge computing allocation learning model specifically includes:

[0029] The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit;

[0030] Storing the scene tag in the tag identification unit;

[0031] storing the first allocation method and the second allocation method in the allocation analysis unit;

[0032] The edge computing allocation method library is stored in the method output unit.

[0033] Preferably, the training of the edge computing allocation learning model based on the historical power data processing record specifically includes:

[0034] Training the edge computing distribution learning model performs the following steps:

[0035] C1: obtaining the scenario tag in the historical power data processing, running the tag identification unit, and using the scenario tag to determine whether to use the first allocation method or the second allocation method;

[0036] C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score;

[0037] C3: running the method output unit to output the corresponding allocation method;

[0038] The trained edge computing allocation learning model is output and defined as the edge computing allocation model.

[0039] In a second aspect, the present application discloses an edge computing allocation system for power data processing, the system is applicable to the edge computing allocation method for power data processing as described above, and the system includes:

[0040] A scenario configuration module, the scenario configuration module is used to configure scenarios for power data processing, the scenarios including operation management scenarios and marketing service scenarios;

[0041] A model building module, the model building module is used to formulate a corresponding allocation method based on the scenario and build an edge computing allocation learning model;

[0042] A model training module, wherein the model training module is used to obtain historical power data processing records, and train the edge computing allocation learning model based on the historical power data processing records to obtain an edge computing allocation model;

[0043] An allocation method output module is used to obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

[0044] Preferably, the scenario of configuring power data processing specifically includes:

[0045] Classifying various types of power data processing based on operation management and marketing services, and defining the classification results as the scenarios;

[0046] Each type of power data processing is classified into the corresponding scenario, and a scenario label is set accordingly. The scenario label is used to characterize the scenario to which the power data processing of this type belongs.

[0047] Preferably, the corresponding allocation method based on the scenario specifically includes:

[0048] The first allocation method corresponding to the operation management scenario includes the following steps:

[0049] A1: Obtain data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US; wherein the data priority score is used to characterize the priority level of data calculation and the score is proportional to the priority level, the resource allocation score is used to characterize the quality level of resources used for data calculation and the score is proportional to the quality of resources used, the complexity score is used to characterize the complexity level of data calculation and the score is proportional to the complexity level, and the urgency score is used to characterize the time urgency level of data calculation and the score is proportional to the time urgency level;

[0050] A2: Calculate a first allocation score, where the first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is specifically:

[0051] AS first =α1*DpS+α2*RaS+α3*CS+α4*US

[0052] Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first scoring the first allocation;

[0053] The second allocation method corresponding to the marketing service scenario includes the following steps:

[0054] B1: Obtain the customer grade score CgS, the customer scale score CsS and the business score BS; the customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer, the customer scale score is used to characterize the size of the data volume corresponding to the customer scale and the score is proportional to the size of the data volume corresponding to the customer scale, and the business score is used to characterize the importance of the business and the score is proportional to the importance of the business;

[0055] B2: Calculate a second allocation score, which is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula of the second allocation score is specifically:

[0056] AS second =β1*CgS+β2*CsS+β3*BS

[0057] Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second scoring the second allocation;

[0058] An edge computing allocation method library is constructed, where the edge computing allocation method library is used to match the corresponding allocation method based on any one or more of the first allocation score and the second allocation score.

[0059] Preferably, the construction of the edge computing allocation learning model specifically includes:

[0060] The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit;

[0061] Storing the scene tag in the tag identification unit;

[0062] storing the first allocation method and the second allocation method in the allocation analysis unit;

[0063] The edge computing allocation method library is stored in the method output unit.

[0064] Preferably, the training of the edge computing allocation learning model based on the historical power data processing record specifically includes:

[0065] Training the edge computing distribution learning model performs the following steps:

[0066] C1: obtaining the scenario tag in the historical power data processing, running the tag identification unit, and using the scenario tag to determine whether to use the first allocation method or the second allocation method;

[0067] C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score;

[0068] C3: running the method output unit to output the corresponding allocation method;

[0069] The trained edge computing allocation learning model is output and defined as the edge computing allocation model.

[0070] Beneficial effects: The edge computing allocation method and system for power data processing of the present application realizes the classification of power data processing by configuring scenarios, provides a data basis for targeted calculations, and improves the efficiency of data processing. The customized allocation method improves the targeted nature of edge computing allocation, and realizes the reasonable allocation of edge computing for power data processing through the edge computing allocation model, thereby improving the efficiency and quality of power data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0072] Figure 1 A flowchart of an edge computing allocation method for power data processing provided in an embodiment of the present application;

[0073] Figure 2 A schematic block diagram of an edge computing distribution system for power data processing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0075] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0076] In a first aspect, this embodiment discloses Figure 1 An edge computing distribution method for power data processing is shown, the method comprising:

[0077] S1: Configure power data processing scenarios, including operation management scenarios and marketing service scenarios.

[0078] In a simple example, the data in the operation management scenario can be, but is not limited to, data obtained from grid status monitoring and evaluation, data generated by grid optimization and scheduling, etc. The data in the marketing service scenario can be, but is not limited to, data generated by electricity billing, data generated by customer electricity usage behavior analysis.

[0079] S2: Formulate corresponding allocation methods based on scenarios and build edge computing allocation learning models.

[0080] S3: Obtain historical power data processing records, train an edge computing allocation learning model based on the historical power data processing records, and obtain an edge computing allocation model.

[0081] S4: Obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

[0082] By configuring scenarios, the classification of power data processing is realized, which provides a data basis for targeted calculations and improves the efficiency of data processing. The customized allocation method improves the targeted allocation of edge computing. The reasonable allocation of edge computing for power data processing is achieved through the edge computing allocation model, which improves the efficiency and quality of power data processing.

[0083] Specifically, the scenarios for configuring power data processing include:

[0084] Various types of power data processing are classified based on operation management and marketing services, and the classification results are defined as scenarios.

[0085] Each type of power data processing is classified into a corresponding scene, and a scene label is set accordingly. The scene label is used to characterize the scene to which the power data processing of this type belongs.

[0086] In this embodiment, the classification of various types of power data processing is based on the common knowledge of those skilled in the art, and the setting of corresponding scenario labels is intended to quickly identify which scenario this type of power data processing is applicable to, providing a data basis and reference for scoring.

[0087] Specifically, a corresponding allocation method is formulated based on the scenario, including:

[0088] The first allocation method corresponding to the operation management scenario includes the following steps:

[0089] A1: Get the data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US. The data priority score is used to characterize the priority of data calculation and the score is proportional to the priority. The resource allocation score is used to characterize the quality of resources used for data calculation and the score is proportional to the quality of resources used. The complexity score is used to characterize the complexity of data calculation and the score is proportional to the complexity. The urgency score is used to characterize the time urgency of data calculation and the score is proportional to the time urgency.

[0090] A2: Calculate the first allocation score. The first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is as follows:

[0091] AS first =α1*DpS+α2*RaS+α3*CS+α4*US

[0092] Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first Score the first assignment.

[0093] The second allocation method corresponding to the marketing service scenario includes the following steps:

[0094] B1: Obtain the customer grade score CgS, customer scale score CsS and business score BS. The customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer. The customer scale score is used to characterize the amount of data corresponding to the customer scale and the score is proportional to the amount of data corresponding to the customer scale. The business score is used to characterize the importance of the business and the score is proportional to the importance of the business.

[0095] B2: Calculate the second allocation score. The second allocation score is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula for the second allocation score is as follows:

[0096] AS second =β1*CgS+β2*CsS+β3*BS

[0097] Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second Score the second assignment.

[0098] An edge computing allocation method library is constructed. The edge computing allocation method library is used to match the corresponding allocation method based on any one or more of the first allocation score and the second allocation score. It should be noted that the edge allocation method library in this embodiment is obtained based on the historical edge computing allocation method.

[0099] Specifically, we build an edge computing allocation learning model, which includes:

[0100] The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit.

[0101] The scene tags are stored in the tag recognition unit.

[0102] The first allocation method and the second allocation method are stored in the allocation analysis unit.

[0103] Store the edge computing allocation method library into the method output unit.

[0104] Specifically, the edge computing allocation learning model is trained based on historical power data processing records, including:

[0105] Training the edge computing distribution learning model performs the following steps:

[0106] C1: Obtain scene labels in the historical power data processing, run the label recognition unit, and use the scene labels to determine whether to use the first allocation method or the second allocation method.

[0107] C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score.

[0108] C3: Run the method output unit to output the corresponding allocation method.

[0109] The trained edge computing allocation learning model is output and defined as an edge computing allocation model.

[0110] In this embodiment, the following technical effects are achieved through the edge computing allocation model:

[0111] Identify applicable scenarios for power data processing and implement targeted classification before calculation.

[0112] The scientific scoring of power data processing provides accurate data reference for edge computing allocation based on the first allocation score and the second allocation score.

[0113] In a second aspect, this embodiment discloses Figure 2 An edge computing distribution system for power data processing is shown, and the system is applicable to the edge computing distribution method for power data processing as described above, and the system includes:

[0114] Scenario configuration module: The scenario configuration module is used to configure scenarios for power data processing, including operation management scenarios and marketing service scenarios.

[0115] The model building module is used to formulate corresponding allocation methods based on scenarios and build edge computing allocation learning models.

[0116] The model training module is used to obtain historical power data processing records, train the edge computing allocation learning model based on the historical power data processing records, and obtain the edge computing allocation model.

[0117] The allocation method output module is used to obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

[0118] Specifically, the scenarios for configuring power data processing include:

[0119] Various types of power data processing are classified based on operation management and marketing services, and the classification results are defined as scenarios.

[0120] Each type of power data processing is classified into a corresponding scene, and a scene label is set accordingly. The scene label is used to characterize the scene to which the power data processing of this type belongs.

[0121] Specifically, a corresponding allocation method is formulated based on the scenario, including:

[0122] The first allocation method corresponding to the operation management scenario includes the following steps:

[0123] A1: Get the data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US. The data priority score is used to characterize the priority of data calculation and the score is proportional to the priority. The resource allocation score is used to characterize the quality of resources used for data calculation and the score is proportional to the quality of resources used. The complexity score is used to characterize the complexity of data calculation and the score is proportional to the complexity. The urgency score is used to characterize the time urgency of data calculation and the score is proportional to the time urgency.

[0124] A2: Calculate the first allocation score. The first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is as follows:

[0125] AS first =α1*DpS+α2*RaS+α3*CS+α4*US

[0126] Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first Score the first assignment.

[0127] The second allocation method corresponding to the marketing service scenario includes the following steps:

[0128] B1: Obtain the customer grade score CgS, customer scale score CsS and business score BS. The customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer. The customer scale score is used to characterize the amount of data corresponding to the customer scale and the score is proportional to the amount of data corresponding to the customer scale. The business score is used to characterize the importance of the business and the score is proportional to the importance of the business.

[0129] B2: Calculate the second allocation score. The second allocation score is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula for the second allocation score is as follows:

[0130] AS second =β1*CgS+β2*CsS+β3*BS

[0131] Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second Score the second assignment.

[0132] An edge computing allocation method library is constructed, and the edge computing allocation method library is used to match a corresponding allocation method based on any one or more of the first allocation score and the second allocation score.

[0133] Specifically, we build an edge computing allocation learning model, which includes:

[0134] The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit.

[0135] The scene tags are stored in the tag recognition unit.

[0136] The first allocation method and the second allocation method are stored in the allocation analysis unit.

[0137] Store the edge computing allocation method library into the method output unit.

[0138] Specifically, the edge computing allocation learning model is trained based on historical power data processing records, including:

[0139] Training the edge computing distribution learning model performs the following steps:

[0140] C1: Obtain scene labels in the historical power data processing, run the label recognition unit, and use the scene labels to determine whether to use the first allocation method or the second allocation method.

[0141] C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score.

[0142] C3: Run the method output unit to output the corresponding allocation method.

[0143] The trained edge computing allocation learning model is output and defined as an edge computing allocation model.

[0144] It should be noted that the edge computing distribution system for power data processing of this embodiment corresponds to the aforementioned edge computing distribution method for power data processing. Therefore, the contents not specifically described in the edge computing distribution system for power data processing of this embodiment, including but not limited to specific functional definitions, working principles and technical effects are the same as those of the edge computing distribution method for power data processing, and will not be repeated in this text.

[0145] In summary, the edge computing allocation method and system for power data processing in this embodiment realizes the classification of power data processing through configuration scenarios, provides a data basis for targeted calculations, and improves the efficiency of data processing. The customized allocation method improves the targeted nature of edge computing allocation, and realizes the reasonable allocation of edge computing for power data processing through the edge computing allocation model, thereby improving the efficiency and quality of power data processing.

[0146] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0147] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An edge computing allocation method for power data processing, characterized in that: The method includes: S1: Configure power data processing scenarios, including operation management scenarios and marketing service scenarios; S2: Formulate a corresponding allocation method based on the scenario and build an edge computing allocation learning model; S3: Obtain historical power data processing records, and train the edge computing allocation learning model based on the historical power data processing records to obtain an edge computing allocation model; S4: Obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

2. The edge computing allocation method for power data processing according to claim 1, characterized in that: The scenario of configuring power data processing specifically includes: Classifying various types of power data processing based on operation management and marketing services, and defining the classification results as the scenarios; Each type of power data processing is classified into the corresponding scenario, and a scenario label is set accordingly. The scenario label is used to characterize the scenario to which the power data processing of this type belongs.

3. The edge computing allocation method for power data processing according to claim 1, characterized in that: The corresponding allocation method based on the scenario specifically includes: The first allocation method corresponding to the operation management scenario includes the following steps: A1: Obtain data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US; wherein the data priority score is used to characterize the priority level of data calculation and the score is proportional to the priority level, the resource allocation score is used to characterize the quality level of resources used for data calculation and the score is proportional to the quality of resources used, the complexity score is used to characterize the complexity level of data calculation and the score is proportional to the complexity level, and the urgency score is used to characterize the time urgency level of data calculation and the score is proportional to the time urgency level; A2: Calculate a first allocation score, where the first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is specifically: AS first =α1*DpS+α2*RaS+α3*CS+α4*US Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first scoring the first allocation; The second allocation method corresponding to the marketing service scenario includes the following steps: B1: Obtain the customer grade score CgS, the customer scale score CsS and the business score BS; the customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer, the customer scale score is used to characterize the size of the data volume corresponding to the customer scale and the score is proportional to the size of the data volume corresponding to the customer scale, and the business score is used to characterize the importance of the business and the score is proportional to the importance of the business; B2: Calculate a second allocation score, which is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula of the second allocation score is specifically: AS second =β1*CgS+β2*CsS+β3*BS Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second scoring the second allocation; An edge computing allocation method library is constructed, where the edge computing allocation method library is used to match the corresponding allocation method based on any one or more of the first allocation score and the second allocation score.

4. The edge computing allocation method for power data processing according to claim 3 is characterized in that: The construction of the edge computing allocation learning model specifically includes: The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit; Storing the scene tag in the tag identification unit; storing the first allocation method and the second allocation method in the allocation analysis unit; The edge computing allocation method library is stored in the method output unit.

5. The edge computing allocation method for power data processing according to claim 3, characterized in that: The training of the edge computing allocation learning model based on the historical power data processing record specifically includes: Training the edge computing distribution learning model performs the following steps: C1: obtaining the scenario tag in the historical power data processing, running the tag identification unit, and using the scenario tag to determine whether to use the first allocation method or the second allocation method; C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score; C3: running the method output unit to output the corresponding allocation method; The trained edge computing allocation learning model is output and defined as the edge computing allocation model.

6. An edge computing distribution system for power data processing, the system being applicable to the edge computing distribution method for power data processing as described in any one of claims 1 to 5, characterized in that: The system includes: A scenario configuration module, the scenario configuration module is used to configure scenarios for power data processing, the scenarios including operation management scenarios and marketing service scenarios; A model building module, the model building module is used to formulate a corresponding allocation method based on the scenario and build an edge computing allocation learning model; A model training module, wherein the model training module is used to obtain historical power data processing records, and train the edge computing allocation learning model based on the historical power data processing records to obtain an edge computing allocation model; An allocation method output module is used to obtain real-time power data processing requirements, run the edge computing allocation model based on the real-time power data processing requirements, and obtain the corresponding allocation method.

7. The edge computing distribution system for power data processing according to claim 6, characterized in that: The scenario of configuring power data processing specifically includes: Classifying various types of power data processing based on operation management and marketing services, and defining the classification results as the scenarios; Each type of power data processing is classified into the corresponding scenario, and a scenario label is set accordingly. The scenario label is used to characterize the scenario to which the power data processing of this type belongs.

8. The edge computing distribution system for power data processing according to claim 6, characterized in that: The corresponding allocation method based on the scenario specifically includes: The first allocation method corresponding to the operation management scenario includes the following steps: A1: Obtain data priority score DpS, resource allocation score RaS, complexity score CS and urgency score US; wherein the data priority score is used to characterize the priority level of data calculation and the score is proportional to the priority level, the resource allocation score is used to characterize the quality level of resources used for data calculation and the score is proportional to the quality of resources used, the complexity score is used to characterize the complexity level of data calculation and the score is proportional to the complexity level, and the urgency score is used to characterize the time urgency level of data calculation and the score is proportional to the time urgency level; A2: Calculate a first allocation score, where the first allocation score is used to determine the allocation method when calculating data in the operation management scenario. The calculation formula of the first allocation score is specifically: AS first =α1*DpS+α2*RaS+α3*CS+α4*US Among them, α1~α4 are corresponding weight parameters and α1+α2+α3+α4=1, AS first scoring the first allocation; The second allocation method corresponding to the marketing service scenario includes the following steps: B1: Obtain the customer grade score CgS, the customer scale score CsS and the business score BS; the customer grade score is used to characterize the importance of the customer and the score is proportional to the importance of the customer, the customer scale score is used to characterize the size of the data volume corresponding to the customer scale and the score is proportional to the size of the data volume corresponding to the customer scale, and the business score is used to characterize the importance of the business and the score is proportional to the importance of the business; B2: Calculate a second allocation score, which is used to determine the allocation method when calculating data in the marketing service scenario. The calculation formula of the second allocation score is specifically: AS second =β1*CgS+β2*CsS+β3*BS Among them, β1~β3 are corresponding weight parameters and β1+β2+β3=1, AS second scoring the second allocation; An edge computing allocation method library is constructed, where the edge computing allocation method library is used to match the corresponding allocation method based on any one or more of the first allocation score and the second allocation score.

9. The edge computing distribution system for power data processing according to claim 8, characterized in that: The construction of the edge computing allocation learning model specifically includes: The edge computing allocation learning model includes a label recognition unit, an allocation analysis unit and a method output unit; Storing the scene tag in the tag identification unit; storing the first allocation method and the second allocation method in the allocation analysis unit; The edge computing allocation method library is stored in the method output unit.

10. The edge computing distribution system for power data processing according to claim 8, characterized in that: The training of the edge computing allocation learning model based on the historical power data processing record specifically includes: Training the edge computing distribution learning model performs the following steps: C1: obtaining the scenario tag in the historical power data processing, running the tag identification unit, and using the scenario tag to determine whether to use the first allocation method or the second allocation method; C2: running the allocation analysis unit to perform corresponding calculations to obtain any one or more of the first allocation score and the second allocation score; C3: running the method output unit to output the corresponding allocation method; The trained edge computing allocation learning model is output and defined as the edge computing allocation model.

Images