Short‐term Load Forecasting Based on a Generalized Regression Neural network optimized by an improved sparrow search algorithm using the empirical wavelet decomposition method

With the development of electric market, load forecasting has been increasingly pursued by many scholars. Because is affected factors, it characterized volatility and uncertainty, cannot be forecasted accurately only a single model. In research, short-term integrated model proposed to solve problem inaccurate The key point using forecast optimize decomposed sequence improve accuracy forecast. Empirical wavelet decomposition (EWT) used decompose into stationary sequences avoid modal aliasing; Sparrow search algorithm (SSA) simulates anti-forecasting behavior sparrow population, which very similar electricity consumption various industries good optimization effect; Generalized regression neural network (GRNN) for reconstruction; This EWT-SSA-GRNN paper studies analyzes power city in southern Australia. results show that reduces through optimization, can accuracy.This article protected copyright. All rights reserved.