Short-term electricity price forecasting method based on local mean value decomposition and optimized RBF neural network

Abstract

The invention relates to the technical field of electricity price prediction, more specifically, to a short-term electricity price prediction method based on local mean decomposition and optimized RBFneural network. Firstly, historical electricity price data are obtained and pretreated. Then, the historical electricity price data is decomposed into a series of PF components with physical meaningby using local mean decomposition. Then, the prediction model of RBF neural network is optimized by crossover algorithm to predict all PF components in advance by 0.5 h. Finally, all the predicted values of PF components are superposed to obtain the actual predicted results. The invention utilizes local mean value decomposition to reduce non-stationarity and non-linearity of electricity price sequence, the hybrid model of radial basis function neural network is optimized by crossover algorithm, which makes up for the shortcoming that neural network is easy to fall into local optimum, improvesthe generalization ability of neural network, reduces the influence of complex characteristics of electricity price series on forecasting results, and improves the accuracy of short-term electricity price forecasting.

Description

technical field [0001] The present invention relates to the technical field of electricity price prediction, and more specifically, relates to a short-term electricity price prediction method based on local mean value decomposition and optimized RBF neural network. Background technique [0002] With the reform of the electricity market, electricity prices can be traded in the market like ordinary commodities. The electricity price forecast is to fully consider the relationship between market supply and demand, market participants to implement factors such as the size of the electricity market, and social activities. Conduct research on electricity price data, analyze the changing law of electricity price itself, and predict the market marginal price of the future electricity market. From the point of view of the power generation side, accurate electricity price prediction is conducive to grasping the market trend and grasping market opportunities, so as to construct the opti...

AI Technical Summary

Problems solved by technology

Compared with the conventional neural network model, the neural network model after cross-cutting optimization makes up for many shortcomings. It avoids the defect that the parameters of the neural network fall into local optimum, and improves the generalization ability of the neural network, so it can be used for short-term For electricity price forecasting, however, a single forecasting model cannot accurately predict electricity prices. Due to the complex characteristics of non-stationary and nonlinear electr

Images