The Short-Term Power Load Forecasting Based on Sperm Whale Algorithm and Wavelet Least Square Support Vector Machine with DWT-IR for Feature Selection

摘要: Short-term power load forecasting is an important basis for the operation of integrated energy system, and accuracy directly affects economy system operation. To improve accuracy, this paper proposes a based on wavelet least square support vector machine sperm whale algorithm. Firstly, methods discrete transform inconsistency rate model (DWT-IR) are used to select optimal features, which aims reduce redundancy input vectors. Secondly, kernel function LSSVM replaced by improving nonlinear mapping ability LSSVM. Lastly, parameters W-LSSVM optimized algorithm, short-term method W-LSSVM-SWA established. Additionally, example verification results show that proposed outperforms other alternative has strong effectiveness feasibility in forecasting.