Main content area

Novel grey prediction model with nonlinear optimized time response method for forecasting of electricity consumption in China

Xu, Ning, Dang, Yaoguo, Gong, Yande
Energy 2017 v.118 pp. 473-480
algorithms, electric energy consumption, electricity, energy, models, prediction, system optimization, China
Forecasting of electricity energy consumption (EEC) has been always playing a vital role in China's power system management, and requires promising prediction techniques. This paper proposed an optimized hybrid GM(1,1) model to improve prediction accuracy of EEC in short term. GM(1,1) model, in spite of successful employing in various fields, sometimes gives rise to inaccurate solution in practical applications. Time response function (TRF) is an important factor deeply influencing modeling precision. Aiming to enhance forecasting performance, this paper proposed a novel grey model with optimal time response function, referred to as IRGM(1,1) model. As of unknown variables in TRF, a nonlinear optimization method, based on particle swarm algorithm, is constructed to obtain optimal values, for shrinking simulation errors and improving adaptability to characteristics of raw data. The forecasting performance has been confirmed by electricity consumption data of China, comparing with three alternative grey models. Application demonstrates that the proposed method can significantly promote modeling accuracy.