Power grid load prediction method and system based on artificial intelligence and subspace aggregation

Abstract

The power grid load prediction method and system based on artificial intelligence and subspace aggregation first collects original data related to power grid load fluctuation, performs fuzzy processing on the original data to form a multi-dimensional fuzzy set of the original data; a fuzzy rule base is established according to the fuzzy rules between the power grid load fluctuation and its influencing factors, and a fuzzy reasoning engine is designed using the fuzzy rule base; the multi-dimensional feature space of the multi-dimensional fuzzy set is divided into multiple random subspaces, a fuzzy logic sub-model is established in each random subspace based on the fuzzy rule base and the fuzzy reasoning engine, and the prediction results of all random subspaces are aggregated to generate a final power grid load prediction model. Through the fuzzy logic system and random subspace division, the calculation time required for model training and prediction is reduced, and by adopting the strategy of random subspace division and multi-model integration, the calculation deviation caused by a single model is effectively reduced, and the stability and accuracy of the prediction model are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power grids, and particularly relates to a power grid load prediction method and system based on artificial intelligence and subspace aggregation. BACKGROUND

[0002] The stable operation of a power system is crucial for the normal operation of social economy. In a modern smart grid, accurate prediction of load fluctuation is an important link to ensure the stability of power supply. Traditional load fluctuation prediction methods rely on some single models or simple statistical methods. These methods have problems such as insufficient prediction accuracy and weak model generalization ability when dealing with complex nonlinear relationships or high-dimensional data, resulting in large fluctuations in prediction results in actual application and failing to meet the demand of high-precision prediction for power grid operation. In addition, traditional models lack effective methods in data feature space division and integration strategy, resulting in significant deficiencies in stability and accuracy of prediction results when dealing with large-scale power grid load prediction tasks.

[0003] In recent years, with the rapid development of artificial intelligence and machine learning technology, some advanced prediction models have been proposed, such as load prediction models based on deep learning. However, when faced with multi-dimensional data features and complex load fluctuations, deep learning models still have the limitation of being unable to fully capture nonlinear features. In addition, in terms of large data processing, a large amount of computing resources is often consumed, and existing technologies are difficult to optimize computing efficiency while ensuring high-precision model prediction.

[0004] Therefore, how to introduce more advanced algorithms in power grid load fluctuation prediction to improve the stability and accuracy of prediction models while optimizing the utilization efficiency of computing resources is still a technical problem to be solved. SUMMARY

[0005] The purpose of the present application is to provide a power grid load prediction method and system based on artificial intelligence and subspace aggregation with high prediction efficiency and high prediction accuracy to solve the above problems in the prior art.

[0006] To achieve the above purpose, the technical solutions of the present application are as follows:

[0007] In a first aspect, the present application provides a power grid load prediction method based on artificial intelligence and subspace aggregation, comprising:

[0008] S1, collecting original data related to power grid load fluctuation and performing fuzzy processing on the original data to form a multi-dimensional fuzzy set of the original data;

[0009] S2, based on the multi-dimensional fuzzy set of the original data, establishing a fuzzy rule library according to the fuzzy rules between the power grid load fluctuation and its influencing factors;

[0010] S3. Design a fuzzy reasoning engine using a fuzzy rule base, and establish a fuzzy logic model based on the fuzzy rule base and the fuzzy reasoning engine;

[0011] S4. Dividing the multidimensional feature space of the multidimensional fuzzy set into multiple random subspaces, and establishing a fuzzy logic submodel in each random subspace based on a fuzzy rule base and a fuzzy inference engine, and aggregating the prediction results of all random subspaces to generate a final power grid load prediction model;

[0012] S5. Input the real-time data related to the grid load fluctuation into the final grid load prediction model to perform real-time prediction of the grid load.

[0013] Said S1 comprises:

[0014] S11. Use the following formula to map various types of original data into fuzzy sets to obtain the fuzzy value of each original data:

[0015]

[0016]

[0017]

[0018] In the above formula, is the fuzzy value of the grid load power data, is the fuzzy value of weather data, is the fuzzy value of social and economic data, x is the data sample of various types of original data, μ P (x) is the membership function of the power grid load data, μ w (x) is the membership function of weather data, μ E (x) is the membership function of the socioeconomic data, P(t) is the grid load power at time t, W(t) is the weather data at time t, and E(t) is the socioeconomic data at time t;

[0019] S12. Combining the fuzzy values ​​of various types of original data to form a multidimensional fuzzy set:

[0020]

[0021] In the above formula, is a multidimensional fuzzy set.

[0022] The S2 includes:

[0023] S21. Based on the multidimensional fuzzy set of the original data, several fuzzy rules are defined to describe the nonlinear relationship between the power grid load fluctuation and its influencing factors. The form of each fuzzy rule is as follows:

[0024]

[0025] In the above formula, R i (t+1) is the fuzzy rule R i at time t+1 i The generated grid load prediction result, f is the fuzzy inference function, M is the total number of grid load power data, is the membership degree of the mth grid load power data, is the weight coefficient of the power grid load data, N is the total number of weather data, is the membership degree of the nth weather data, is the weight coefficient of weather data, L is the total number of social and economic data, is the membership degree of the lth socioeconomic data, is the weight coefficient of socioeconomic data;

[0026] S22. Combining the fuzzy rules to form a fuzzy rule base:

[0027]

[0028] In the above formula, is the fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

[0029] The fuzzy logic model in S3 includes:

[0030]

[0031]

[0032]

[0033] In the above formula, y i (t+1) is the fuzzy rule R i at time t+1 i The intermediate prediction result obtained by inference, f i is the fuzzy reasoning function based on the fuzzy rule base, is a multidimensional fuzzy set, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the i-th fuzzy rule R i When entering data The applicability of the time domain is given by t+1, Y(t+1) is the load forecast value determined at time t+1, X is the multidimensional feature space of the multidimensional fuzzy set, The fuzzy output result at time t+1 is the input data The membership function at .

[0034] The S4 comprises:

[0035] S41, the multi-dimensional feature space of the multi-dimensional fuzzy set is distributed to each random subspace by using the following formula:

[0036]

[0037] In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n，j is the jth input feature distributed to the nth random subspace, and X is the multi-dimensional feature space of the multi-dimensional fuzzy set.

[0038] S42, a plurality of fuzzy logic sub-models M n，m , m = 1, 2,..., M n , M n，m represent the mth fuzzy logic sub-model in the nth random subspace, and a plurality of independent prediction results are generated in each random subspace by training each fuzzy logic sub-model independently is the prediction result of the mth fuzzy logic sub-model in the nth random subspace at time t+1.

[0039] S43, the prediction results of all fuzzy logic sub-models in the nth random subspace are integrated, and the following formula is used to obtain the prediction result of each random subspace:

[0040]

[0041] In the above formula, is the prediction result of the nth random subspace at time t+1, M n is all fuzzy logic sub-models in the nth random subspace, α n，m is the weight coefficient of the mth fuzzy logic sub-model.

[0042] S45, the prediction results of all random subspaces are aggregated to generate a final power grid load prediction model:

[0043]

[0044] In the above formula, is the prediction value of the power grid load at time t+1, β n is the contribution weight of each random subspace to the final prediction result.

[0045] In a second aspect, the present invention proposes a power grid load forecasting system based on artificial intelligence and subspace aggregation, comprising a multidimensional fuzzy set forming module, a fuzzy rule base establishing module, a fuzzy logic model establishing module, a power grid load forecasting model generating module, and a power grid load real-time forecasting module;

[0046] The multidimensional fuzzy set forming module is used to collect original data related to power grid load fluctuations and perform fuzzification processing on the original data to form a multidimensional fuzzy set of the original data;

[0047] The fuzzy rule base building module is used to build a fuzzy rule base based on the multidimensional fuzzy set of the original data and the fuzzy rules between the power grid load fluctuation and its various influencing factors;

[0048] The fuzzy logic model building module is used to design a fuzzy inference engine using a fuzzy rule base, and to build a fuzzy logic model based on the fuzzy rule base and the fuzzy inference engine;

[0049] The power grid load forecasting model generation module is used to divide the multidimensional feature space of the multidimensional fuzzy set into multiple random subspaces, and establish a fuzzy logic submodel in each random subspace based on the fuzzy rule base and the fuzzy inference engine, and aggregate the prediction results of all random subspaces to generate the final power grid load forecasting model;

[0050] The grid load real-time prediction module is used to input real-time data related to grid load fluctuation into the final grid load prediction model to perform real-time prediction of the grid load.

[0051] The multidimensional fuzzy set forming module includes a fuzzy value calculation unit and a multidimensional fuzzy set combining unit;

[0052] The fuzzy value calculation unit is used to map various types of original data into fuzzy sets using the following formula to obtain the fuzzy value of each original data:

[0053]

[0054]

[0055]

[0056] In the above formula, is the fuzzy value of the grid load power data, is the fuzzy value of weather data, is the fuzzy value of social and economic data, x is the data sample of various types of original data, μ P (x) is the membership function of the power grid load data, μ W (x) is the membership function of weather data, μ E(x) is a membership function of social economic data, P(t) is the power load of the power grid at time t, W(t) is weather data at time t, and E(t) is social economic data at time t;

[0057] The multi-dimensional fuzzy set combination unit is configured to combine the fuzzy values of various types of original data to form a multi-dimensional fuzzy set.

[0058]

[0059] In the above formula, is a multi-dimensional fuzzy set.

[0060] The fuzzy rule base establishment module includes a fuzzy rule definition unit and a fuzzy rule base formation unit.

[0061] The fuzzy rule definition unit is configured to define, based on the multi-dimensional fuzzy set of the original data, a plurality of fuzzy rules for describing the nonlinear relationship between the power grid load fluctuation and its influencing factors, each fuzzy rule being in the following form:

[0062]

[0063] In the above formula, R i is the power grid load prediction result generated by the i-th fuzzy rule R i at time t+1, f is a fuzzy inference function, M is the total number of power grid load power data, is the membership degree of the m-th power grid load power data, is a weight coefficient of the power grid load power data, N is the total number of weather data, is the membership degree of the n-th weather data, is a weight coefficient of the weather data, L is the total number of social economic data, is the membership degree of the l-th social economic data, is a weight coefficient of the social economic data.

[0064] The fuzzy rule base formation unit is configured to combine the fuzzy rules to form a fuzzy rule base:

[0065]

[0066] In the above formula, is a fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

[0067] The fuzzy logic model in the fuzzy logic model establishment module includes:

[0068]

[0069]

[0070]

[0071] In the above formula, y i (t+1) is the fuzzy output result at time t+1 determined by the ith fuzzy rule R i the intermediate prediction result obtained by reasoning, f i is a fuzzy reasoning function based on a fuzzy rule base, is a multi-dimensional fuzzy set, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the ith fuzzy rule R i at the input data , Y(t+1) is the load prediction value determined at time t+1, X is a multi-dimensional feature space of a multi-dimensional fuzzy set, is the membership function of the fuzzy output result at time t+1 at the input data .

[0072] The power grid load prediction model generation module includes a subspace allocation unit, a sub-model prediction result training generation unit, a subspace prediction result integration unit, and a power grid load prediction model aggregation unit.

[0073] The subspace allocation unit is configured to allocate the multi-dimensional feature space of the multi-dimensional fuzzy set to each random subspace using the following formula:

[0074]

[0075] In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n，j is the jth input feature allocated to the nth random subspace, and X is a multi-dimensional feature space of a multi-dimensional fuzzy set.

[0076] The sub-model prediction result training generation unit is configured to establish a plurality of fuzzy logic sub-models M n，m in each random subspace based on a fuzzy rule base and a fuzzy reasoning engine, m = 1, 2,..., M n , M n，m represents the mth fuzzy logic sub-model in the nth random subspace, and a plurality of independent prediction results are generated in each random subspace by independently training each fuzzy logic sub-model.

[0077] The subspace prediction result integration unit is configured to integrate the prediction results of all fuzzy logic sub-models in the nth random subspace, and the prediction result of each random subspace is obtained by using the following formula:

[0078]

[0079] In the above formula, is the prediction result of the nth random subspace at time t+1, M n is all fuzzy logic sub-models in the nth random subspace, and α n，m is the weight coefficient of the mth fuzzy logic sub-model;

[0080] The power grid load prediction model aggregation unit is configured to aggregate the prediction results of all random subspaces to generate a final power grid load prediction model:

[0081]

[0082] In the above formula, is the predicted value of the power grid load at time t+1, and β n is the contribution weight of each random subspace to the final prediction result.

[0083] Compared with the prior art, the present application has the following beneficial effects:

[0084] The application provides a power grid load prediction method and system based on artificial intelligence and subspace aggregation. The method first collects original data related to power grid load fluctuation, fuzzifies the original data to form a multi-dimensional fuzzy set of the original data, establishes a fuzzy rule library based on the multi-dimensional fuzzy set of the original data according to fuzzy rules between the power grid load fluctuation and its influencing factors, designs a fuzzy reasoning engine by using the fuzzy rule library, establishes a fuzzy logic model based on the fuzzy rule library and the fuzzy reasoning engine, divides a multi-dimensional feature space of the multi-dimensional fuzzy set into multiple random subspaces, establishes a fuzzy logic submodel in each random subspace based on the fuzzy rule library and the fuzzy reasoning engine, aggregates prediction results of all random subspaces to generate a final power grid load prediction model, and inputs real-time data related to the power grid load fluctuation into the final power grid load prediction model to perform real-time prediction of the power grid load. On the one hand, the method reduces the calculation time required for model training and prediction and improves the calculation efficiency of the prediction model by using the fuzzy logic system and the random subspace division process under the condition of limited calculation resources, and even in an emergency, the model can still complete the prediction calculation in a short time to provide timely support for the dispatching decision of the power grid. On the other hand, the method divides the multi-dimensional feature space of the multi-dimensional fuzzy set into multiple random subspaces, establishes a fuzzy logic submodel in each random subspace based on the fuzzy rule library and the fuzzy reasoning engine, adopts the strategy of random subspace division and multi-model integration, effectively reduces the calculation deviation caused by a single model, and significantly improves the stability and accuracy of the prediction model by integrating the prediction results of different random subspaces. BRIEF DESCRIPTION OF DRAWINGS

[0085] Figure 1 The method is shown in the overall flowchart.

[0086] Figure 2 The structure of the system is shown in the structure diagram. DETAILED DESCRIPTION

[0087] The application will be further described in detail below in combination with the specific embodiments and the drawings.

[0088] The application provides a power grid load prediction method and system based on artificial intelligence and subspace aggregation. The power grid system automatically collects original data related to power grid load fluctuation, aggregates prediction results of all random subspaces by using a fuzzy logic system and a random subspace division process to generate a final power grid load prediction model, finally evaluates the prediction performance of the power grid load fluctuation prediction model, dynamically adjusts the fuzzy rules and the random subspace division strategy according to the performance evaluation result, optimizes the power grid load fluctuation prediction model, provides fast and accurate load prediction for the power grid system in practical application, and provides strong technical support for the stable operation of the power grid.

[0089] Embodiment 1:

[0090] This embodiment takes the power grid system of a large industrial park in a coastal area as the research object. The power grid of the industrial park serves multiple high-energy-consuming manufacturing enterprises, and the production activities of the enterprises have obvious seasonal fluctuation characteristics. On July 25, 2024, the power grid system of the industrial park faced a sudden power load fluctuation problem. From 2:00 to 4:00 in the morning, the power grid monitoring system recorded a series of abnormal load fluctuations, and there was a significant deviation between the load prediction model and the actual load data. The traditional load prediction model failed to accurately predict the fluctuations, resulting in a risk of unstable power supply for the power grid dispatching center. In order to respond to this emergency, the power grid dispatching center quickly started the emergency analysis program based on the power grid load prediction method of the invention.

[0091] As shown in Figure 1 The power grid load prediction method based on artificial intelligence and subspace aggregation proceeds in the following steps:

[0092] 1. The power grid system automatically collects original data related to power grid load fluctuations during 2:00 to 4:00 in the morning, and performs fuzzy processing on the collected data to form a multi-dimensional fuzzy set of original data.

[0093] The original data related to power grid load fluctuations include power grid load power data: 1750 MW at 2:00, 1790 MW at 2:30, 1820 MW at 3:00, 1900 MW at 3:30, and 1950 MW at 4:00; local weather data: temperature 32℃, humidity 85%, wind speed 10m / s; social and economic data: industrial production index 110, residential electricity consumption 850MW;

[0094] The collected original data is preprocessed, including data cleaning, removal of outliers, and filling of missing values, and the preprocessed data is fuzzy processed to convert the continuous data set into a fuzzy set.

[0095] The membership function corresponding to the original data related to power grid load fluctuations is set. The membership function is used to map the original data to a fuzzy set, and each type of data is fuzzy processed according to the preset membership function. The following formula is used to map each type of original data to a fuzzy set to obtain the fuzzy value of each original data:

[0096]

[0097]

[0098]

[0099] In the above formula, is the fuzzy value of the grid load power data, is the fuzzy value of weather data, is the fuzzy value of social and economic data, x is the data sample of various types of original data, μ P (x) is the membership function of the power grid load data, μ W (x) is the membership function of weather data, μ E (x) is the membership function of social and economic data, P(t) is the grid load power at time t, W(t) is the weather data at time t, including temperature data T(t), humidity data H(t) and wind speed data V(t) at time t, E(t) is the social and economic data at time t, including industrial production index data I(t) and residential electricity consumption data R(t) at time t;

[0100] The fuzzy values ​​of various types of original data are combined to form a multidimensional fuzzy set:

[0101]

[0102] In the above formula, is a multidimensional fuzzy set.

[0103] 2. Based on the multidimensional fuzzy set of the original data, a fuzzy rule base is established according to the fuzzy rules between the power grid load fluctuation and its various influencing factors;

[0104] Based on the statistical analysis results of historical grid load data and expert experience, the correlation between grid load fluctuations and its influencing factors, including grid load power factors, weather factors, and socioeconomic factors, is analyzed. Several fuzzy rules are defined to describe the nonlinear relationship between grid load fluctuations and its influencing factors. The form of each fuzzy rule is as follows:

[0105]

[0106] In the above formula, R i (t+1) is the fuzzy rule R i at time t+1 i The generated grid load prediction result, f is the fuzzy inference function, M is the total number of grid load power data, is the membership degree of the mth grid load power data, is the weight coefficient of the power grid load data, N is the total number of weather data, is the membership degree of the nth weather data, is the weight coefficient of weather data, L is the total number of social and economic data, is the membership degree of the lth socioeconomic data, The weight coefficient of the social economic data; the weight coefficient of each data type, reflecting the relative importance of different factors on the power grid load fluctuation;

[0107] For each fuzzy rule, the following formula is used to define its corresponding membership function, which is used to describe the applicability of the fuzzy rule under different input conditions:

[0108]

[0109] In the above formula, is the i-th fuzzy rule R i The applicability of the input data , α m , β n , γ1 are the weighted indexes of the power grid load power data, weather data, and social economic data, respectively.

[0110] Each fuzzy rule is combined to form a fuzzy rule base:

[0111]

[0112] In the above formula, is the fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

[0113] 3. Design a fuzzy reasoning engine using the fuzzy rule base, and establish a fuzzy logic model based on the fuzzy rule base and the fuzzy reasoning engine;

[0114] The fuzzy logic model includes the intermediate prediction result of the power grid load, the fuzzy output result, and the determined load prediction value.

[0115] Based on the fuzzy rule base, a fuzzy reasoning engine is designed to reason the multi-dimensional fuzzy set of the original data, and obtain the intermediate prediction result of the power grid load:

[0116]

[0117] In the above formula, y i (t+1) is the intermediate prediction result obtained by the i-th fuzzy rule R i at time t+1, f i is the fuzzy reasoning function based on the fuzzy rule base, is the multi-dimensional fuzzy set.

[0118] Using the weighted average method, the intermediate prediction results of the power grid load under each fuzzy rule are aggregated to generate the final fuzzy output result:

[0119]

[0120] In the above formula, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the ith fuzzy rule R i at the input data ;

[0121] The final fuzzy output result after fuzzy aggregation is de-fuzzied by using the weighted integral method, and is converted into a deterministic load prediction value:

[0122]

[0123] In the above formula, Y(t+1) is the deterministic load prediction value at time t+1, X is the multi-dimensional feature space of the multi-dimensional fuzzy set, is the membership function of the fuzzy output result at time t+1 at the input data .

[0124] 4. The multi-dimensional feature space of the multi-dimensional fuzzy set is divided into multiple random subspaces, and a fuzzy logic sub-model is established in each random subspace based on the fuzzy rule base and the fuzzy reasoning engine, and the prediction results of all random subspaces are aggregated to generate a final power grid load prediction model;

[0125] The multi-dimensional feature space of the multi-dimensional fuzzy set is allocated to each random subspace by using the following formula, and each random subspace contains several features:

[0126]

[0127] In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n，j is the jth input feature allocated to the nth random subspace, X is the multi-dimensional feature space of the multi-dimensional fuzzy set, and x={x1, x2,..., x p};

[0128] The load prediction value of each random subspace is calculated by using the following formula:

[0129]

[0130] In the above formula, Y n (t+1) is the load prediction value generated by the nth random subspace at time t+1, f n is the reasoning prediction function of the nth random subspace, which is calculated by reasoning based on the rules in the fuzzy rule base, w n，j is the weight of the corresponding input feature X n，j in the nth random subspace, input feature X n，j membership degree at time t;

[0131] Based on the input feature of each random subspace and its corresponding fuzzy rule base, the load prediction value of each random subspace is trained, and in the training process, the error function L n Optimize the weight parameter W of the corresponding input feature in each random subspace n，j , to get more accurate load prediction value of each random subspace;

[0132] In each random subspace, based on the fuzzy rule base and fuzzy inference engine, a number of fuzzy logic sub-models M n，m , m = 1, 2,..., M n , M n，m represent the mth fuzzy logic sub-model in the nth random subspace, and the error function L n Each fuzzy logic sub-model is trained independently, and a number of independent prediction results are generated in each random subspace is the prediction result of the mth fuzzy logic sub-model in the nth random subspace at time t+1;

[0133] The minimized error function L n is:

[0134]

[0135] In the above formula, T is the total length of the time series, Y n，m (t+1) is the actual value of the mth fuzzy logic sub-model in the nth random subspace at time t+1;

[0136] The prediction results of all fuzzy logic sub-models in the nth random subspace are integrated by the random subspace aggregation algorithm, and the following formula is used to obtain the prediction result of each random subspace:

[0137]

[0138] In the above formula, is the prediction result of the nth random subspace at time t+1, M n is all fuzzy logic sub-models in the nth random subspace, α n，m is the weight coefficient of the mth fuzzy logic sub-model, which satisfies

[0139] The prediction results of all random subspaces are aggregated to generate the final power grid load prediction model:

[0140]

[0141] In the above formula, is the predicted value of the grid load at time t+1, β n The contribution weight of each random subspace to the final prediction result satisfies

[0142] 5. Evaluate the prediction performance of the grid load fluctuation prediction model using a validation dataset, namely historical grid load power data, weather data, and socioeconomic data, including:

[0143] The validation dataset V = {V1, V2, ..., V q}, input into the generated grid load forecast model, and calculate the grid load forecast value at time t+1 The root mean square error (RMSE), mean absolute percentage error (MAPE) and R 2 , quantifying the prediction performance of the grid load fluctuation prediction model:

[0144]

[0145]

[0146]

[0147] In the above formula, q is the total number of samples in the validation dataset, Y true，j (t+1) is the actual load value of the jth sample in the validation dataset at time t+1, is the predicted value of grid load fluctuation at time t+1, is the average value of the actual load values ​​of all samples in the validation dataset; 2 It reflects the ability of the power grid load fluctuation prediction model to explain data variation. The closer the value is to 1, the better the performance of the power grid load fluctuation prediction model.

[0148] 6. Dynamically adjust the fuzzy rules and random subspace partitioning strategy of the original data related to power grid load fluctuations based on the performance evaluation results to optimize the power grid load fluctuation prediction model;

[0149] By fine-tuning the membership functions in the fuzzy rule base, adjusting the partition range of the fuzzy set, or redistributing the input characteristic variables in the multidimensional fuzzy set feature space, and optimizing the random subspace partitioning strategy, the final power grid load forecasting model is optimized until the performance indicators of the power grid load forecasting model reach the preset optimization goals, thus forming the optimal power grid load forecasting model;

[0150] By introducing a dynamic adjustment mechanism to assess the prediction performance of the model in real time, dynamically optimizing the fuzzy rule base and random subspace partitioning strategy, the prediction model can be continuously optimized and adjusted to quickly respond to changes in real-time data in the power grid system, ensuring that the model adapts to the complex fluctuations of the power grid load. In the face of real-time data, it can quickly respond and provide more accurate load prediction results, greatly improving the adaptability and stability of the prediction model, especially suitable for complex and variable power grid operating environments.

[0151] 7. Inputting the real-time data related to the power grid load fluctuation into the optimized power grid load prediction model to perform real-time prediction of the power grid load;

[0152] The actual power grid load data collected during 2:00 to 4:00 in the morning is inputted into the power grid load prediction model to quickly generate the load prediction result for the next hour: the model predicts that the power grid system will reach a load of 2000MW at 4:30 and may further climb to 2050MW at 5:00.

[0153] To verify the effect of the present application, the dispatching center compared the actual load data from 2:00 to 4:00 on July 25, 2024 with the prediction data of the traditional method and the prediction data of the present application in detail, as shown in Table 1:

[0154] Table 1 Actual load data, traditional method prediction data, and present application prediction data

[0155] Time Actual Load Conventional method prediction Invention prediction 2:00 1750 MW 1700 MW 1745 MW 2:30 1790 MW 1720 MW 1785 MW 3:00 1820 MW 1750 MW 1815 MW 3:30 1900 MW 1800 MW 1890 MW 4:00 1950 MW 1850 MW 1945 MW ;

[0156] According to the prediction data in the above table, the prediction performance of the traditional prediction model and the prediction model of the present application was evaluated, and the evaluation results showed that in terms of prediction accuracy, the root mean square error of the traditional method was 75MW, and the average absolute percentage error was 4.8%, while the root mean square error of the present application method was only 25MW, and the average absolute percentage error was 1.3%. In addition, the R 2 value of the present application method reached 0.97, which was better than the 0.85 of the traditional method. Compared with the traditional prediction method, the prediction method of the present application showed higher prediction accuracy, and the prediction model could better explain the variability of the power grid load fluctuation;

[0157] Before this, the traditional prediction model predicts the load at 4:30 as 1900MW and the load at 5:00 as 1920MW, the actual load is far beyond the prediction range, which makes the power grid dispatching center passive in the early response, while the method of the application provides more accurate load prediction through the strategy of multi-model integration. In the subsequent operation, the power grid dispatching center dispatches standby power in advance at 4:00 according to the prediction result of the application, and completes the access of standby power at 4:15, ensuring the stable supply of electricity during 4:30 to 5:00, avoiding the production interruption event caused by insufficient power supply, and the post-analysis shows that if the traditional load prediction model is continued to be used, the power grid system is likely to face the risk of increased power supply pressure around 5:00;

[0158] The successful handling of this event proves the feasibility and effectiveness of the power grid load prediction method of the application in practical application, which not only far exceeds the traditional method in prediction accuracy, but also provides strong technical support in emergency handling and resource scheduling, laying a solid foundation for the stable operation of smart grid.

[0159] Embodiment 2:

[0160] As shown in the figure, the power grid load prediction system based on artificial intelligence and subspace aggregation includes a multi-dimensional fuzzy set formation module, a fuzzy rule base establishment module, a fuzzy logic model establishment module, a power grid load prediction model generation module, and a power grid load real-time prediction module. Figure 2

[0161] The system includes a multi-dimensional fuzzy set formation module, a fuzzy rule base establishment module, a fuzzy logic model establishment module, a power grid load prediction model generation module, and a power grid load real-time prediction module.

[0162] The multi-dimensional fuzzy set formation module is used to collect original data related to power grid load fluctuation, and to perform fuzzy processing on the original data to form a multi-dimensional fuzzy set of the original data.

[0163] The fuzzy rule base establishment module is used to establish a fuzzy rule base based on the multi-dimensional fuzzy set of the original data according to the fuzzy rules between the power grid load fluctuation and its influencing factors.

[0164] The fuzzy logic model establishment module is used to design a fuzzy reasoning engine using the fuzzy rule base, and to establish a fuzzy logic model based on the fuzzy rule base and the fuzzy reasoning engine.

[0165] ​The power grid load prediction model generation module is configured to divide a multi-dimensional feature space of the multi-dimensional fuzzy set into a plurality of random subspaces, and establish a fuzzy logic sub-model in each random subspace based on a fuzzy rule base and a fuzzy reasoning engine, and aggregate prediction results of all random subspaces to generate a final power grid load prediction model.

[0166] The power grid load real-time prediction module is configured to input real-time data related to power grid load fluctuation into the final power grid load prediction model to perform real-time prediction of the power grid load.

[0167] The multi-dimensional fuzzy set formation module includes a fuzzy value calculation unit and a multi-dimensional fuzzy set combination unit.

[0168] The fuzzy value calculation unit is configured to map various types of original data into a fuzzy set by using the following formula to obtain fuzzy values of the original data:

[0169]

[0170]

[0171]

[0172] In the above formula, is a fuzzy value of power grid load power data, is a fuzzy value of weather data, is a fuzzy value of social and economic data, x is a data sample of various types of original data, and μ P (x) is a membership function of power grid load power data, μ W (x) is a membership function of weather data, μ E (x) is a membership function of social and economic data, P(t) is power grid load power at time t, W(t) is weather data at time t, and E(t) is social and economic data at time t.

[0173] The multi-dimensional fuzzy set combination unit is configured to combine fuzzy values of various types of original data to form a multi-dimensional fuzzy set:

[0174]

[0175] In the above formula, is a multi-dimensional fuzzy set.

[0176] The fuzzy rule base establishment module includes a fuzzy rule definition unit and a fuzzy rule base formation unit.

[0177] The fuzzy rule definition unit is used to define a number of fuzzy rules for describing the nonlinear relationship between the power grid load fluctuation and its influencing factors based on the multidimensional fuzzy set of the original data. The form of each fuzzy rule is as follows:

[0178]

[0179] In the above formula, R i (t+1) is the fuzzy rule R i at time t+1 i The generated grid load prediction result, f is the fuzzy inference function, M is the total number of grid load power data, is the membership degree of the mth grid load power data, is the weight coefficient of the power grid load data, N is the total number of weather data, is the membership degree of the nth weather data, is the weight coefficient of weather data, L is the total number of social and economic data, is the membership degree of the lth socioeconomic data, is the weight coefficient of socioeconomic data;

[0180] The fuzzy rule base forming unit is used to combine the fuzzy rules to form a fuzzy rule base:

[0181]

[0182] In the above formula, is the fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

[0183] The fuzzy logic model in the fuzzy logic model building module includes:

[0184]

[0185]

[0186]

[0187] In the above formula, y i (t+1) is the fuzzy rule R i at time t+1 i The intermediate prediction result obtained by inference, f i is the fuzzy reasoning function based on the fuzzy rule base, is a multidimensional fuzzy set, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the i-th fuzzy rule R i When entering data the degree of applicability of the fuzzy set at time t+1, Y(t+1) is the predicted load value determined at time t+1, X is a multi-dimensional feature space of the multi-dimensional fuzzy set, is the membership function at the input data of the fuzzy output result at time t+1.

[0188] The power grid load prediction model generation module includes a subspace allocation unit, a sub-model prediction result training generation unit, a subspace prediction result integration unit, and a power grid load prediction model aggregation unit.

[0189] The subspace allocation unit is configured to allocate the multi-dimensional feature space of the multi-dimensional fuzzy set to each random subspace using the following formula:

[0190]

[0191] In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n，j is the jth input feature allocated to the nth random subspace, and X is the multi-dimensional feature space of the multi-dimensional fuzzy set.

[0192] The sub-model prediction result training generation unit is configured to establish a plurality of fuzzy logic sub-models M n，m in each random subspace based on the fuzzy rule base and the fuzzy reasoning engine, m = 1, 2,..., M n M n，m represents the mth fuzzy logic sub-model in the nth random subspace, and a plurality of independent prediction results are generated in each random subspace by independently training each fuzzy logic sub-model.

[0193] The subspace prediction result integration unit is configured to integrate the prediction results of all fuzzy logic sub-models in the nth random subspace, and obtain the prediction result of each random subspace using the following formula:

[0194]

[0195] In the above formula, is the prediction result of the nth random subspace at time t+1, M n is all fuzzy logic sub-models in the nth random subspace, and α n，m is the weight coefficient of the mth fuzzy logic sub-model.

[0196] The power grid load prediction model aggregation unit is configured to aggregate the prediction results of all random subspaces to generate a final power grid load prediction model.

[0197]

[0198] In the above formula, is the predicted value of the power grid load at time t+1, β n is the contribution weight of each random subspace to the final prediction result.

Claims

1. A power grid load forecasting method based on artificial intelligence and subspace aggregation, characterized in that: include: S1. Collecting raw data related to power grid load fluctuations and fuzzifying the raw data to form a multi-dimensional fuzzy set of the raw data; S2. Based on the multidimensional fuzzy set of the original data, a fuzzy rule base is established according to the fuzzy rules between the power grid load fluctuation and its various influencing factors; S3. Design a fuzzy reasoning engine using a fuzzy rule base, and establish a fuzzy logic model based on the fuzzy rule base and the fuzzy reasoning engine; S4. Divide the multidimensional feature space of the multidimensional fuzzy set into multiple random subspaces, and establish a fuzzy logic submodel in each random subspace based on the fuzzy rule base and the fuzzy inference engine. Aggregate the prediction results of all random subspaces to generate the final power grid load prediction model, including: S41. Use the following formula to distribute the multidimensional feature space of the multidimensional fuzzy set into each random subspace: In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n,j is the jth input feature assigned to the nth random subspace, X is the multidimensional feature space of the multidimensional fuzzy set; S42. In each random subspace, several fuzzy logic submodels M are established based on the fuzzy rule base and fuzzy inference engine. n,m ,m=1,2,...,M n , M n,m Represents the mth fuzzy logic sub-model in the nth random subspace, and generates several independent prediction results in each random subspace by independently training each fuzzy logic sub-model is the prediction result of the mth fuzzy logic sub-model in the nth random subspace at time t+1; S43. Integrate the prediction results of all fuzzy logic sub-models in the nth random subspace and obtain the prediction results of each random subspace using the following formula: In the above formula, is the prediction result of the nth random subspace at time t+1, M n are all fuzzy logic submodels in the nth random subspace, α n，m is the weight coefficient of the mth fuzzy logic sub-model; S45. Aggregate the prediction results of all random subspaces to generate the final power grid load prediction model: In the above formula, is the predicted value of the grid load at time t+1, β n The contribution weight of each random subspace to the final prediction result; S5. Input the real-time data related to the grid load fluctuation into the final grid load prediction model to perform real-time prediction of the grid load.

2. The power grid load forecasting method based on artificial intelligence and subspace aggregation according to claim 1 is characterized in that: Said S1 comprises: S11. Use the following formula to map various types of original data into fuzzy sets to obtain the fuzzy value of each original data: In the above formula, is the fuzzy value of the grid load power data, is the fuzzy value of weather data, is the fuzzy value of social and economic data, x is the data sample of various types of original data, μ p (x) is the membership function of the power grid load data, μ W (x) is the membership function of weather data, μ E (x) is the membership function of the socioeconomic data, P(t) is the grid load power at time t, W(t) is the weather data at time t, and E(t) is the socioeconomic data at time t; S12. Combining the fuzzy values ​​of various types of original data to form a multidimensional fuzzy set: In the above formula, is a multidimensional fuzzy set.

3. The power grid load forecasting method based on artificial intelligence and subspace aggregation according to claim 1 is characterized in that: The S2 includes: S21. Based on the multidimensional fuzzy set of the original data, several fuzzy rules are defined to describe the nonlinear relationship between the power grid load fluctuation and its influencing factors. The form of each fuzzy rule is as follows: In the above formula, R i (t+1) is the fuzzy rule R i at time t+1 i The generated grid load prediction result, f is the fuzzy inference function, M is the total number of grid load power data, is the membership degree of the mth grid load power data, is the weight coefficient of the power grid load data, N is the total number of weather data, is the membership degree of the nth weather data, is the weight coefficient of weather data, L is the total number of social and economic data, is the membership degree of the lth socioeconomic data, is the weight coefficient of socioeconomic data; S22. Combining the fuzzy rules to form a fuzzy rule base: In the above formula, is the fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

4. The power grid load forecasting method based on artificial intelligence and subspace aggregation according to claim 1 is characterized in that: The fuzzy logic model in S3 includes: In the above formula, y i (t+1) is the fuzzy rule R i at time t+1 i The intermediate prediction result obtained by inference, f i is the fuzzy reasoning function based on the fuzzy rule base, is a multidimensional fuzzy set, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the i-th fuzzy rule R i When entering data Y(t+1) is the load forecast value determined at time t+1, X is the multidimensional feature space of the multidimensional fuzzy set, The fuzzy output result at time t+1 is the input data The membership function at .

5. A power grid load forecasting system based on artificial intelligence and subspace aggregation, characterized by: The system includes a multi-dimensional fuzzy set forming module, a fuzzy rule base establishing module, a fuzzy logic model establishing module, a power grid load prediction model generating module, and a power grid load real-time prediction module; The multidimensional fuzzy set forming module is used to collect original data related to power grid load fluctuations and perform fuzzification processing on the original data to form a multidimensional fuzzy set of the original data; The fuzzy rule base building module is used to build a fuzzy rule base based on the multidimensional fuzzy set of the original data and the fuzzy rules between the power grid load fluctuation and its various influencing factors; The fuzzy logic model building module is used to design a fuzzy inference engine using a fuzzy rule base, and to build a fuzzy logic model based on the fuzzy rule base and the fuzzy inference engine; The power grid load forecasting model generation module is used to divide the multidimensional feature space of the multidimensional fuzzy set into multiple random subspaces, and establish a fuzzy logic submodel in each random subspace based on the fuzzy rule base and the fuzzy inference engine, and aggregate the prediction results of all random subspaces to generate the final power grid load forecasting model, including a subspace allocation unit, a submodel prediction result training and generation unit, a subspace prediction result integration unit, and a power grid load forecasting model aggregation unit; The subspace allocation unit is used to allocate the multidimensional feature space of the multidimensional fuzzy set to each random subspace using the following formula: In the above formula, X n is the nth random subspace, q n is the number of features contained in the nth random subspace, X n，j is the jth input feature assigned to the nth random subspace, X is the multidimensional feature space of the multidimensional fuzzy set; The sub-model prediction result training generation unit is used to establish several fuzzy logic sub-models M in each random subspace based on the fuzzy rule base and fuzzy inference engine. n,m , m=1, 2, ..., M n , M n,m Represents the mth fuzzy logic sub-model in the nth random subspace, and generates several independent prediction results in each random subspace by independently training each fuzzy logic sub-model is the prediction result of the mth fuzzy logic sub-model in the nth random subspace at time t+1; The subspace prediction result integration unit is used to integrate the prediction results of all fuzzy logic sub-models in the nth random subspace and obtain the prediction results of each random subspace using the following formula: In the above formula, is the prediction result of the nth random subspace at time t+1, M n are all fuzzy logic submodels in the nth random subspace, α n,m is the weight coefficient of the mth fuzzy logic sub-model; The power grid load prediction model aggregation unit is used to aggregate the prediction results of all random subspaces to generate a final power grid load prediction model: In the above formula, is the predicted value of the grid load at time t+1, β n The contribution weight of each random subspace to the final prediction result; The grid load real-time prediction module is used to input real-time data related to grid load fluctuation into the final grid load prediction model to perform real-time prediction of the grid load.

6. The power grid load forecasting system based on artificial intelligence and subspace aggregation according to claim 5 is characterized in that: The multidimensional fuzzy set forming module includes a fuzzy value calculation unit and a multidimensional fuzzy set combining unit; The fuzzy value calculation unit is used to map various types of original data into fuzzy sets using the following formula to obtain the fuzzy value of each original data: In the above formula, is the fuzzy value of the grid load power data, is the fuzzy value of weather data, is the fuzzy value of social and economic data, x is the data sample of various types of original data, μ P (x) is the membership function of the power grid load data, μ W (x) is the membership function of weather data, μ E (x) is the membership function of the socioeconomic data, P(t) is the grid load power at time t, W(t) is the weather data at time t, and E(t) is the socioeconomic data at time t; The multidimensional fuzzy set combination unit is used to combine the fuzzy values ​​of various types of original data to form a multidimensional fuzzy set: In the above formula, is a multidimensional fuzzy set.

7. The power grid load forecasting system based on artificial intelligence and subspace aggregation according to claim 5, characterized in that: The fuzzy rule base building module includes a fuzzy rule definition unit and a fuzzy rule base forming unit; The fuzzy rule definition unit is used to define a number of fuzzy rules for describing the nonlinear relationship between the power grid load fluctuation and its influencing factors based on the multidimensional fuzzy set of the original data. The form of each fuzzy rule is as follows: In the above formula, R i (t+1) is the fuzzy rule R i at time t+1 i The generated grid load prediction result, f is the fuzzy inference function, M is the total number of grid load power data, is the membership degree of the mth grid load power data, is the weight coefficient of the power grid load data, N is the total number of weather data, is the membership degree of the nth weather data, is the weight coefficient of weather data, L is the total number of social and economic data, is the membership degree of the lth socioeconomic data, is the weight coefficient of socioeconomic data; The fuzzy rule base forming unit is used to combine the fuzzy rules to form a fuzzy rule base: In the above formula, is the fuzzy rule base composed of all fuzzy rules, and K is the total number of rules in the fuzzy rule base.

8. The power grid load forecasting system based on artificial intelligence and subspace aggregation according to claim 5 is characterized in that: The fuzzy logic model in the fuzzy logic model building module includes: In the above formula, y i (t+1) is the fuzzy rule R i at time t+1 i The intermediate prediction result obtained by inference, f i is the fuzzy reasoning function based on the fuzzy rule base, is a multidimensional fuzzy set, is the fuzzy output result at time t+1, K is the total number of rules in the fuzzy rule base, is the i-th fuzzy rule R i When entering data Y(t+1) is the load forecast value determined at time t+1, X is the multidimensional feature space of the multidimensional fuzzy set, The fuzzy output result at time t+1 is the input data The membership function at .

Images