Interval forecasting system for electricity load based on data pre-processing strategy and multi-objective optimization algorithm

• Published in: Applied energy 2022-01, Vol.305, p.117911, Article 117911
• Main Authors: Wang, Jianzhou, Zhang, Linyue, Li, Zhiwu
• Format: Article
• Language: English
• Subjects: Data reconstruction strategy; Electricity load; Hybrid model; Interval forecasting; Multi-objective optimization algorithm
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2021.117911

•Interval forecasting system is proposed to quantify the uncertainty information.•Data decomposition strategy is employed to process original data.•A novel method of determining weight to combine all individual models.•The Pareto optimal solution is theoretically proved.•Experiments demonstrate the availability and reliability of the proposed model. Electricity load prediction is of great significance to the development of the power market and stable operation of power systems. In recent years, scholars in this field have only considered point forecasting, which ignores the inevitable prediction bias and uncertain information. To fill this gap, this study proposes an interval prediction system consisting of an advanced data reconstruction strategy, a multi-objective optimization algorithm based on the theory of non-negative constraints, and an outstanding interval forecasting model fitted by the predicted fluctuation characteristics. Moreover, this study theoretically proves that the weight assigned by the optimization algorithm is the Pareto optimal solution. Empirical data with 30 min intervals from Queensland, Australia are selected as samples for research. The results not only demonstrate the superiority of the proposed model but also provide effective technical support for power grid operation and dispatch by quantifying changes in the prediction results caused by uncertainties.