Power equipment resource pool dynamic capacity evaluation method, system, equipment and medium

Abstract

The invention relates to the field of power equipment resource pool assessment, in particular to a power equipment resource pool dynamic capacity assessment method and system, equipment and a medium, and the method comprises the steps: processing behavior resource parameters, related to a power equipment resource pool, of a to-be-assessed user to obtain a feature column; inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain index data of multiple dimensions representing the dynamic capacity of the power equipment resource pool; and comparing the index data of the plurality of dimensions with corresponding thresholds to obtain an evaluation result of the power equipment resource pool capacity. According to the method, the BiLSTM-KAN combined network model is adopted to automatically generate the multi-dimensional index data representing the resource capacity, multi-dimensional representation evaluation is achieved, evaluation indexes are easy to generate, and evaluation is more comprehensive and accurate.

Description

Technical Field

[0001] The present invention relates to the field of power equipment resource pool evaluation, and in particular to a method, system, equipment and medium for evaluating the dynamic capacity of a power equipment resource pool. Background Art

[0002] With the strict requirements on carbon emissions, the traditional power system is evolving towards a new power system that is clean, low-carbon, safe, controllable, flexible, efficient, open, interactive, intelligent and friendly. The "double high" (high proportion of renewable energy and high proportion of power electronic equipment) characteristics of the power system are further highlighted, and more demand-side adjustable resources (that is, power equipment resource pools) are needed to participate in the operation and regulation of the power grid. In the field of smart grids, the capacity assessment of the power equipment resource pool is a key link to ensure the stable operation of the power grid and optimize the allocation of power resources. The power equipment resource pool involves various types of resources, such as industrial loads, buildings, residents, energy storage equipment, etc.

[0003] However, accurately assessing the actual regulation capability and capacity of these resources is a complex process. Traditional assessment methods only verify single-dimensional data such as historical electricity consumption data or equipment capacity, which cannot comprehensively and accurately assess the capacity of the power equipment resource pool. Moreover, the verification process is computationally complex and requires high professional capabilities from technical personnel. Summary of the invention

[0004] In order to solve the problem that the capacity evaluation of the power equipment resource pool in the prior art is complex and single-dimensional, the present invention proposes a dynamic capacity evaluation method for the power equipment resource pool, comprising:

[0005] Processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column;

[0006] Inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool;

[0007] Compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool;

[0008] The BiLSTM-KAN joint network model includes a BiLSTM network and a KAN network connected in sequence, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension.

[0009] Optionally, the training steps of the BiLSTM-KAN joint network model include:

[0010] Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user;

[0011] Calculate multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool to obtain a target column;

[0012] The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed;

[0013] Among them, the input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column.

[0014] Optionally, the indicator data of multiple dimensions include resource response rate, resource response degree and resource capacity, wherein the resource response rate is the ratio of resources responding to control instructions within the control period; the resource response degree is the deviation between the response amount at each moment and the moment before the response during the resource response process; and the resource capacity is the average load of the resource.

[0015] Optionally, the indicator data of the multiple dimensions also include at least one of resource online rate or resource reliability, wherein the resource online rate is the ratio of the resource load that is not 0 at all times of the day; and the resource reliability is the overall fluctuation of the resource.

[0016] Optionally, the loss function of the BiLSTM-KAN joint network model is a weighted sum of the mean square errors of the indicator data of each dimension, and the weight of the mean square error of the indicator data of each dimension is obtained by one of the following methods:

[0017] Expert scoring, factorization, or the average of expert scoring and factorization.

[0018] Optionally, comparing the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool includes:

[0019] The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

[0020] Optionally, after obtaining the evaluation result of the power equipment resource pool capacity, the method further includes: inputting the evaluation result into a report template to generate an evaluation report.

[0021] Optionally, after obtaining the evaluation result of the power equipment resource pool capacity, the step further includes:

[0022] The indicator data and / or evaluation results of multiple dimensions are visualized.

[0023] Optionally, the behavior resource parameters include user power data, resources in the user's power equipment resource pool, and parameters of the resources.

[0024] Optionally, the step of processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain the feature column includes:

[0025] The user's behavioral resource parameters related to the power equipment resource pool are supplemented, denoised, and redundant data is removed, and then integrated to obtain feature columns.

[0026] In another aspect, the present application provides a system for dynamic capacity assessment of a power equipment resource pool, comprising:

[0027] A processing module, used for processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column;

[0028] An indicator acquisition module, used for inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain indicator data of multiple dimensions representing the dynamic capacity of the power equipment resource pool;

[0029] A result acquisition module, used to compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool;

[0030] The BiLSTM-KAN joint network model includes a BiLSTM network and a KAN network connected in sequence, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension.

[0031] Optionally, the training steps of the indicator acquisition module BiLSTM-KAN joint network model include:

[0032] Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user;

[0033] Calculate multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool to obtain a target column;

[0034] The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed;

[0035] Among them, the input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column.

[0036] Optionally, the indicator data of multiple dimensions in the indicator acquisition module include resource response rate, resource response degree and resource capacity, wherein the resource response rate is the ratio of resources responding to control instructions within the control period; the resource response degree is the deviation between the response amount at each moment and the moment before the response during the resource response process; and the resource capacity is the average load of the resource.

[0037] Optionally, the indicator data of the multiple dimensions in the indicator acquisition module also include at least one of resource online rate or resource reliability, wherein the resource online rate is the ratio of the resource load that is not 0 at all times of the day; and the resource reliability is the overall fluctuation of the resource.

[0038] Optionally, the loss function of the BiLSTM-KAN joint network model in the indicator acquisition module is a weighted sum of the mean square errors of the indicator data of each dimension, and the weight of the mean square error of the indicator data of each dimension is obtained by one of the following methods:

[0039] Expert scoring, factorization, or the average of expert scoring and factorization.

[0040] Optionally, the result acquisition module compares the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool, including:

[0041] The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

[0042] Optionally, after the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, it also includes: inputting the evaluation result into a report template to generate an evaluation report.

[0043] Optionally, after the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, it also includes:

[0044] The indicator data and / or evaluation results of multiple dimensions are visualized.

[0045] Optionally, the behavior resource parameters in the processing module include user power data, resources in the user's power equipment resource pool, and parameters of the resources.

[0046] Optionally, the processing module processes the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain the feature column, including:

[0047] The user's behavioral resource parameters related to the power equipment resource pool are supplemented, denoised, and redundant data is removed, and then integrated to obtain feature columns.

[0048] In another aspect, the present application further provides a computing device, comprising: at least one processor and a memory;

[0049] The memory is used to store one or more programs;

[0050] When the one or more programs are executed by the one or more processors, a method for dynamic capacity assessment of a power equipment resource pool as described above is implemented.

[0051] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, a method for dynamic capacity assessment of a power equipment resource pool as described above is implemented.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention provides a method, system, device and medium for evaluating the dynamic capacity of an electric power equipment resource pool. The method comprises: processing the behavioral resource parameters of an evaluated user related to the electric power equipment resource pool to obtain a feature column; inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain index data of multiple dimensions characterizing the dynamic capacity of the electric power equipment resource pool; comparing the index data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the electric power equipment resource pool; and further, the present application adopts the BiLSTM-KAN joint network model to automatically generate multidimensional index data characterizing the resource capacity, thereby realizing multidimensional characterization evaluation, and the evaluation index generation is simple, and the evaluation is more comprehensive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a flow chart of the method for dynamic capacity assessment of power equipment resource pool proposed by the present invention;

[0055] Figure 2 A schematic diagram of the network architecture of the BiLSTM-KAN joint network model proposed in the present invention;

[0056] Figure 3 This is a process flow chart of the BiLSTM-KAN joint network model proposed in the present invention;

[0057] Figure 4 This is an application flow chart of the dynamic capacity evaluation method for power equipment resource pool proposed by the present invention;

[0058] Figure 5 This is a schematic diagram of the structure of the dynamic capacity evaluation system for the power equipment resource pool proposed by the present invention;

[0059] Figure 6 This is a schematic diagram of the structure of the electronic device proposed by the present invention. DETAILED DESCRIPTION

[0060] The present invention proposes a method, system, device and medium for evaluating the dynamic capacity of a power equipment resource pool, aiming to realize the evaluation of multiple dimensions of indicator data characterizing the dynamic capacity of a power equipment resource pool through a BiLSTM-KAN joint network model. The BiLSTM-KAN joint network model is obtained by splicing a BiLSTM network and a KAN network. The BiLSTM network has strong modeling capabilities and the ability to capture long-term dependencies, and learns the complex dynamics of historical load, electricity and other time series data; the attention mechanism of the KAN network dynamically identifies and focuses on factors that have a key impact on capacity evaluation, thereby realizing accurate evaluation of multiple dimensions of indicator data.

[0061] Embodiment 1:

[0062] A method for evaluating the dynamic capacity of a power equipment resource pool, such as Figure 1 As shown, it includes the following steps S1 to S3:

[0063] S1: Processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column.

[0064] The behavioral resource parameters of the user to be evaluated are sorted out, including the user's power data, the resources in the user's power equipment resource pool, and the parameters of the resources. The user's power data includes historical power load and power consumption, and the parameters of the power equipment resource pool include the equipment's adjustment capability, response time, maximum / minimum load and other parameters.

[0065] The user's behavior resource parameters are filled in, denoised, and redundant data removed to obtain feature columns. Specifically, the missing value filling, smoothing noise, and deleting duplicate data can be used for preprocessing, and a total of M feature fields are retained. Then, since some feature fields are highly correlated, N fields are retained after redundancy removal to obtain feature columns, M ≥ N. In this embodiment, M is 127 and N is 83.

[0066] S2: Input the feature column into the pre-trained BiLSTM-KAN joint network model to obtain indicator data of multiple dimensions characterizing the dynamic capacity of the power equipment resource pool.

[0067] The BiLSTM-KAN joint network model is obtained by splicing the BiLSTM network and the KAN network (such as Figure 2As shown), the output of the BiLSTM network is the input of the KAN network, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension. The input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column. In this embodiment, the input dimension of the BiLSTM-KAN joint network model is 300, the BiLSTM hidden layer dimension is 256, the number of hidden layers is 2, the output mode is the output of the last time step (last), the number of attention heads is set to 8, the packet loss rate is 0.2, the learning rate is 0.01, the batch size is 128, and the number of iterations is 30.

[0068] like Figure 3 As shown, the training steps of the BiLSTM-KAN joint network model include S21 to S23:

[0069] S21: Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user.

[0070] The historical behavior resource parameters of multiple users are obtained in the manner of step S1 and processed to obtain feature columns corresponding to the multiple users.

[0071] S22: Calculate indicator data of multiple dimensions representing the dynamic capacity of the power equipment resource pool to obtain a target column.

[0072] In a further preferred solution, the indicator data of the multiple dimensions include resource response rate, resource response degree and resource capacity.

[0073] Among them, the resource response rate C d is the ratio of resources responding to control instructions during the control period. The specific formula is:

[0074]

[0075] Among them, T d is the actual response time of the resource, T o is the end response time point required by the control instruction, T s The time point at which the control instruction starts responding.

[0076] Resource responsiveness C p It is the deviation between the response amount at each moment and the moment before the response in the resource response process. The specific formula is:

[0077]

[0078] Among them, L iis the load value of the i-th point, s is the start time of regulation, o is the end time of regulation, os is the difference between the end time of regulation and the start time of regulation, L s It is the load value at the time of no response, and is generally selected from the point before the first point in the control time period.

[0079] Resource Capacity C s is the average load of the resource, and the formula is as follows:

[0080]

[0081] In a further preferred solution, the dimension also includes at least one of resource online rate or resource reliability.

[0082] Resource online rate C o It is the ratio of the resource load that is not 0 at all times (i.e. 96 times) every day. The specific formula is as follows:

[0083]

[0084] in, is the indicator function, indicating that the load value L at the i-th point i When it is not 0, is 1, the formula is as follows:

[0085]

[0086] Resource reliability C r is the overall fluctuation of resources, the specific formula is as follows:

[0087]

[0088] The assessment dimensions in this embodiment are the above five dimensions. The above formula is used to calculate the values ​​of these five dimensions based on historical resource data to obtain the target column. Therefore, the feature column and the target column constitute a data set. Part of them is used as a training set and the other part is used as a test set to train and test the BiLSTM-KAN joint network model respectively.

[0089] In a further preferred embodiment, the weighted sum of the mean square error of the indicator data of each dimension is obtained by the expert scoring method, the factor decomposition method, or the average value of the expert scoring method and the factor decomposition method as the loss function of the BiLSTM-KAN joint network model. The weight corresponding to the five-dimensional indicator in this application is q i ={0.33,0.24,0.19,0.15,0.09}, then the corresponding loss function loss is:

[0090]

[0091] in, is the predicted value of resource response rate, d t is the true value of the resource response rate, is the predicted value of resource responsiveness, p t is the true value of resource responsiveness, is the predicted value of resource online rate, o t is the real value of the resource online rate, is the predicted value of resource capacity, s t is the true value of resource capacity, is the predicted value of resource reliability, r t is the true value of resource reliability, Q is the total number of users, and t is the tth user.

[0092] S23: The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed.

[0093] The BiLSTM-KAN joint network model is trained using the feature columns in the training set as input and the corresponding target columns as output until the number of iterations reaches a preset value and the training is completed.

[0094] S3: Compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool.

[0095] The step of comparing the indicator data of multiple dimensions with corresponding thresholds to obtain an evaluation result of the capacity of the power equipment resource pool includes:

[0096] The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

[0097] In a further preferred solution, after obtaining the evaluation result of the power equipment resource pool capacity, the method further includes: inputting the evaluation result into a report template to generate an evaluation report, and further analyzing the reasons for failure.

[0098] In a further preferred solution, after obtaining the evaluation result of the power equipment resource pool capacity, the step further includes:

[0099] The indicator data and / or evaluation results of multiple dimensions are visualized.

[0100] The application process of the dynamic capacity evaluation method of the power equipment resource pool in this application is as follows Figure 4As shown, firstly, the user behavior resource parameters are obtained, and the behavior resource parameters are processed to obtain the feature column and the target column. Then, a BiLSTM-KAN joint network model is constructed, and the feature column is used as input, and the target column is used as output to train the BiLSTM-KAN joint network model to obtain the trained BiLSTM-KAN joint network model. The trained BiLSTM-KAN joint network model is used to evaluate the dynamic capacity of the power equipment resource pool, and then a multi-dimensional visualization display can be performed and a non-conforming list and an evaluation report can be generated.

[0101] Embodiment 2:

[0102] The present invention based on the same inventive concept also provides a dynamic capacity evaluation system for a power equipment resource pool, such as Figure 5 As shown, including:

[0103] A processing module, used for processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column;

[0104] An indicator acquisition module, used for inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain indicator data of multiple dimensions representing the dynamic capacity of the power equipment resource pool;

[0105] A result acquisition module, used to compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool;

[0106] The BiLSTM-KAN joint network model includes a BiLSTM network and a KAN network connected in sequence, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension.

[0107] In a further preferred solution, the training steps of the index acquisition module BiLSTM-KAN joint network model include:

[0108] Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user;

[0109] Calculate multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool to obtain a target column;

[0110] The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed;

[0111] Among them, the input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column.

[0112] In a further preferred scheme, the indicator data of multiple dimensions in the indicator acquisition module include resource response rate, resource response degree and resource capacity, wherein the resource response rate is the ratio of resource response to control instructions within the control period; the resource response degree is the deviation between the response amount at each moment and the moment before response during the resource response process; and the resource capacity is the average load of the resource.

[0113] In a further preferred scheme, the indicator data of multiple dimensions in the indicator acquisition module also include at least one of resource online rate or resource reliability, wherein the resource online rate is the ratio of the resource load that is not 0 at all times of the day; and the resource reliability is the overall fluctuation of the resource.

[0114] In a further preferred solution, the loss function of the BiLSTM-KAN joint network model in the indicator acquisition module is the weighted sum of the mean square errors of the indicator data of each dimension, and the weight of the mean square error of the indicator data of each dimension is obtained by one of the following methods:

[0115] Expert scoring, factorization, or the average of expert scoring and factorization.

[0116] In a further preferred solution, the result acquisition module compares the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool, including:

[0117] The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

[0118] In a further preferred solution, after the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, it also includes: inputting the evaluation result into a report template to generate an evaluation report.

[0119] In a further preferred solution, after the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, it also includes:

[0120] The indicator data and / or evaluation results of multiple dimensions are visualized.

[0121] In a further preferred solution, the behavior resource parameters in the processing module include user power data, resources in the user's power equipment resource pool, and parameters of the resources.

[0122] In a further preferred solution, the processing module processes the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain the feature column including:

[0123] The user's behavioral resource parameters related to the power equipment resource pool are supplemented, denoised, and redundant data is removed, and then integrated to obtain feature columns.

[0124] Example 3

[0125] like Figure 6 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0126] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a dynamic capacity assessment method for a power equipment resource pool in the above-mentioned embodiment.

[0127] Example 4

[0128] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a dynamic capacity evaluation method of a power equipment resource pool in the above embodiment.

[0129] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for evaluating the dynamic capacity of a power equipment resource pool, characterized in that: include: Processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column; Inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool; Compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool; The BiLSTM-KAN joint network model includes a BiLSTM network and a KAN network connected in sequence, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension.

2. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: The training steps of the BiLSTM-KAN joint network model include: Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user; Calculate multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool to obtain a target column; The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed; Among them, the input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column.

3. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: The indicator data of the multiple dimensions include resource response rate, resource response degree and resource capacity, wherein the resource response rate is the ratio of resource response to control instructions within the control period; the resource response degree is the deviation between the response amount at each moment and the moment before the response during the resource response process; and the resource capacity is the average load of the resource.

4. The method for dynamic capacity assessment of a power equipment resource pool according to claim 3, characterized in that: The indicator data of the multiple dimensions also include at least one of resource online rate or resource reliability, wherein the resource online rate is the ratio of the resource load that is not 0 at all times of the day; and the resource reliability is the overall fluctuation of the resource.

5. The method for dynamic capacity assessment of a power equipment resource pool according to claim 2, characterized in that: The loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension, and the weight of the mean square error of the indicator data of each dimension is obtained by one of the following methods: Expert scoring, factorization, or the average of expert scoring and factorization.

6. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: The step of comparing the indicator data of multiple dimensions with corresponding thresholds to obtain an evaluation result of the capacity of the power equipment resource pool includes: The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

7. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: After obtaining the evaluation result of the power equipment resource pool capacity, the method further includes: inputting the evaluation result into a report template to generate an evaluation report.

8. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: After obtaining the evaluation result of the power equipment resource pool capacity, the method further includes: The indicator data and / or evaluation results of multiple dimensions are visualized.

9. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: The behavior resource parameters include user power data, resources in the user's power equipment resource pool, and parameters of the resources.

10. The method for dynamic capacity assessment of a power equipment resource pool according to claim 1, characterized in that: The process of processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain the feature column includes: The user's behavioral resource parameters related to the power equipment resource pool are supplemented, denoised, and redundant data is removed, and then integrated to obtain feature columns.

11. A dynamic capacity assessment system for a power equipment resource pool, characterized in that: include: A processing module, used for processing the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain a feature column; An indicator acquisition module, used for inputting the feature column into a pre-trained BiLSTM-KAN joint network model to obtain indicator data of multiple dimensions representing the dynamic capacity of the power equipment resource pool; A result acquisition module, used to compare the indicator data of multiple dimensions with corresponding thresholds respectively to obtain an evaluation result of the capacity of the power equipment resource pool; The BiLSTM-KAN joint network model includes a BiLSTM network and a KAN network connected in sequence, and the loss function of the BiLSTM-KAN joint network model is the weighted sum of the mean square errors of the indicator data of each dimension.

12. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: The training steps of the BiLSTM-KAN joint network model of the indicator acquisition module include: Obtain historical behavior resource parameters of multiple users related to the power equipment resource pool and process them to obtain feature columns corresponding to each user; Calculate multiple dimensions of indicator data representing the dynamic capacity of the power equipment resource pool to obtain a target column; The BiLSTM-KAN joint network model is trained using the feature column as input and the target column as output until the number of iterations reaches a preset value and the training is completed; Among them, the input dimension of the BiLSTM-KAN joint network model is greater than or equal to the dimension of the feature column.

13. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: The indicator data of multiple dimensions in the indicator acquisition module include resource response rate, resource response degree and resource capacity, wherein the resource response rate is the ratio of resource response to control instructions within the control period; the resource response degree is the deviation between the response amount at each moment and the moment before the response during the resource response process; and the resource capacity is the average load of the resource.

14. The power equipment resource pool dynamic capacity assessment system according to claim 13, characterized in that: The indicator data of the multiple dimensions in the indicator acquisition module also include at least one of resource online rate or resource reliability, wherein the resource online rate is the ratio of the resource load that is not 0 at all times of the day; and the resource reliability is the overall fluctuation of the resource.

15. The power equipment resource pool dynamic capacity assessment system according to claim 12, characterized in that: The loss function of the BiLSTM-KAN joint network model in the indicator acquisition module is the weighted sum of the mean square errors of the indicator data of each dimension, and the weight of the mean square error of the indicator data of each dimension is obtained by one of the following methods: Expert scoring, factorization, or the average of expert scoring and factorization.

16. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: The result acquisition module compares the indicator data of multiple dimensions with corresponding thresholds respectively to obtain the evaluation result of the capacity of the power equipment resource pool, including: The indicator data of multiple dimensions are compared with the corresponding thresholds respectively. If the indicator data of each dimension meets the threshold requirements, the corresponding dynamic capacity of the power equipment resource pool is qualified, otherwise it is unqualified.

17. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: After the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, the method further includes: inputting the evaluation result into a report template to generate an evaluation report.

18. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: After the result acquisition module obtains the evaluation result of the power equipment resource pool capacity, it also includes: The indicator data and / or evaluation results of multiple dimensions are visualized.

19. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: The behavior resource parameters in the processing module include user power data, resources in the user's power equipment resource pool, and parameters of the resources.

20. The power equipment resource pool dynamic capacity assessment system according to claim 11, characterized in that: The processing module processes the behavior resource parameters of the user to be evaluated related to the power equipment resource pool to obtain the feature columns including: The user's behavioral resource parameters related to the power equipment resource pool are supplemented, denoised, and redundant data is removed, and then integrated to obtain feature columns.

21. A computer device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the method for dynamic capacity assessment of a power equipment resource pool according to any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, the dynamic capacity evaluation method for the power equipment resource pool as described in any one of claims 1 to 10 is implemented.

Images