A novel multivariate nonlinear time-delayed grey model for forecasting electricity consumption

Abstract

Accurate and stable annual electricity consumption forecasting play vital role in modern social and economic development, which can provide effective planning and guaranteeing a reliable supply of sustainable electricity. Given that electricity consumption series present nonlinearity, poor information, and time-delayed characteristics, this paper proposes a multivariate nonlinear time-delayed grey model. Three primary efforts have been made as follows. First, we introduce the nonlinear and time-delayed terms into the typical multivariate grey model to identify the relationship between electricity consumption sequence and its driving factor sequence. Second, based on the Monte-Carlo simulation, an intelligent algorithm matching framework is designed to seek for the optimal model parameters of the model, which enhances the model’s applicability and flexibility. Third, we use datasets of China’s and America’s electricity consumption from 2000 to 2021 to validate the effectiveness of the newly-proposed model. Additionally, sensitivity analysis under different time horizons further verifies the model’s robustness. The experiment results indicates the superior prediction accuracy and robustness when comparing with other prevailing benchmarks. Overall, the newly-designed model is an effective technique for forecasting electricity consumption in China and America. Based on this, the forecasts of China’s and America’s electricity consumption in the following years can serve as a valuable reference for formulating related policies.