Period-decoupled Short-term Price Prediction Model Based on Artificial Neural Network and Least Squares-Support Vector Machine Approach Optimized by Bacterial Colony Chemotaxis Algorithm

Abstract

The short-term price prediction result is an important bidding strategy basis for generating the enterprise consumers. Firstly, the index system for factors affecting the short-term electricity price was constructed and the core influencing factors were selected based on Artificial Neural Network (ANN); then, Bacterial Colony Chemotaxis (BCC) algorithm was built to determine the extra-parameters used in the least squares-support vector machine (LS-SVM) for short-term electricity price forecasting. In order to avoid BCC trapped in the local optimum, a perturbation was applied to the population to extricate itself out of the local optimal and start a new search and optimized BCC algorithm.