Early Warning Method of Energy-Consuming Industry Chain Risk Based on Autoregressive Sliding Average Model and Correlation Analysis

With the increasing penetration of renewable energy sources (RES) in energy systems, the relationship between energy supply and demand shows the characteristics of dynamic change, which may lead to a severe imbalance between energy supply and demand in the industry chain of energy systems. Therefore, the timely and accurate early warning of the possible short-term supply and demand imbalance risk in the energy industry chain is of great significance for optimizing resource allocation and preventing the transmission and expansion of risks in the energy and power industry chain. In this work, an effective correlation analysis-based early warning method for risks in the energy and power industry chain is proposed. First, an autoregressive integrated moving average (ARIMA)-based industrial power demand forecasting method is proposed to predict the distribution of electricity consumption in each link of the energy industrial chain. Then, a Pearson's correlation coefficient-based early warning method is proposed, which can evaluate and report the risk of energy-consuming in advance by analyzing the correlation of power flow in the industrial chain. Finally, the energy consumption data of an industrial chain in Zhejiang province, China is used to validate the efficacy of the proposed method. The simulation results show that the proposed method can achieve better risk warning effects for the energy-consuming industry chain by exploring the correlations among various links in the energy-consuming industry chain.