A short-term load forecasting method and system based on feature selection of DFS and SVM

Abstract

The invention relates to a short-term load forecasting method and system based on feature selection of DFS and SVM. The method comprises the steps of obtaining a feature subset according to the F-score value influencing the feature of the short-term load forecasting, determineing the optimal feature subset according to the classification accuracy of the SVM classification model corresponding to the feature subset, training the short-term load forecasting model by using the historical data corresponding to the feature of the optimal feature subset, and forecasting the daily load value by usingthe short-term load forecasting model. The method of the invention realizes the effective dimensionality reduction of the input data, comprehensively considers the global searching ability and the local searching ability, realizes the optimization of the weight value and the threshold value of the neural network, avoids falling into the local optimum, and improves the precision of the load forecasting.

Description

Technical field [0001] The present invention relates to the technical field of electric power engineering, in particular to a short-term load forecasting method and system based on DFS and SVM feature selection. Background technique [0002] The short-term load forecasting of the power system is related to the planning and reliable and economic operation of the power system. The accurate short-term load forecasting results help to improve the safety and stability of the system and reduce the cost of power generation. However, in recent years, with the comprehensive construction of intelligent, digital, and informatized power grids, the amount of data in the power industry has shown an explosive growth trend. How to dig out relatively important information from the massive data becomes extremely important, so a kind of data is needed. Mining methods to improve the accuracy of short-term load forecasting. [0003] According to different data sources, smart grid big data can be divid...

AI Technical Summary

Problems solved by technology

However, as far as the current massive power data is concerned, the existing load forecasting methods have certain limitations. The regression analysis method: only describes the quantitative relationship between variables in a statistical sense, and often limits the amount of data; the neural network method: In the training process, overfitting is prone to occur. In the face of multiple input variables, there may be problems such as slow convergence and falling into a local minimum.

For massive data, on the one hand, the more the feature quantity is, the more information can be obtained; on the other hand, too many features will increase the complexity of calculation, and redundant, irrelevant and even noise information will affect the accuracy of the results. accuracy

Images