Short-Term Electricity Price Forecasting Based on BP Neural Network Optimized by SAPSO

Min Yi,Li Mo,Wei Xie

doi:10.3390/en14206514

Abstract

In the electricity market environment, the market clearing price has strong volatility, periodicity and randomness, which makes it more difficult to select the input features of artificial neural network forecasting. Although the traditional back propagation (BP) neural network has been applied early in electricity price forecasting, it has the problem of low forecasting accuracy. For this reason, this paper uses the maximum information coefficient and Pearson correlation analysis to determine the main factors affecting electricity price fluctuation as the input factors of the forecasting model. The improved particle swarm optimization algorithm, called simulated annealing particle swarm optimization (SAPSO), is used to optimize the BP neural network to establish the SAPSO-BP short-term electricity price forecasting model and the actual sample data are used to simulate and calculate. The results show that the SAPSO-BP price forecasting model has a high degree of fit and the average relative error and mean square error of the forecasting model are lower than those of the BP network model and PSO-BP model, as well as better than the PSO-BP model in terms of convergence speed and accuracy, which provides an effective method for improving the accuracy of short-term electricity price forecasting.

Highlights

The nine models, back propagation (BP)-3N, BP-9N, BP-15N, Particle swarm optimization (PSO)-BP-3N, PSO-BP-9N, PSO-BP-15N, simulated annealing particle swarm optimization (SAPSO)-BP-3N, SAPSOBP-9N and SAPSO-BP-15N, were trained with the training set data and they were tested with the testing set data
In view of the randomness of electricity price in the electricity market environment and the low accuracy of traditional BP neutral network electricity price prediction, this paper proposes a short-term electricity price prediction model based on the SAPSO-BP
The linearly increased inertia weight was used to improve the disadvantage of the decline of the later convergence speed of PSO and to improve the convergence speed of the algorithm

Summary

Introduction

The prediction accuracy of the electricity price directly affects the income and risk of transactions and it is the information that market participants pay close attention to [1,2,3,4]. Due to the advance of power system development, the fluctuation of the electricity price is not increasing, but affected by many uncertain factors, such as the change of supply and demand, network congestion, market and the psychology of bidders [7]. These random factors, which are difficult to quantify and screen, make it more difficult to forecast electricity price

Methods

Results

Conclusion