Combined framework based on data preprocessing and multi-objective optimizer for electricity load forecasting

In recent years, accurate electricity load forecasting has become increasingly essential for improving the management efficiency of power-generation systems. However, previously proposed hybrid models directly apply signal-processing technology in data preprocessing, resulting in poor efficiency in matching the electricity sequence characteristics. Moreover, most studies exhibit non-optimal performance in practical applications because they focus on forecasting accuracy and ignore forecasting stability. In this study, a combined framework that includes amodified noise processing strategy, multi-objective optimization algorithm, and deep neural network is proposed to solve the low prediction-accuracy problem in electricity load forecasting. The 30-minute real time data of electricity load from Queensland, Australia, are employed to verify the reliability of the proposed framework. The mean absolute percentage error values of the proposed framework in a multi-step prediction approached the values of MAPE1−step=0.79%, MAPE2−step=1.13%, and MAPE3−step=1.50% in Series 1, which significantly outperformed the existing contrast models.