Electricity Strategy Optimization for Industrial Users with Real-Time Price Estimation in the Electricity Market Transition

Industrial users need to optimize their electricity consumption strategy under the dynamic real-time electricity prices in the electricity market transition. This paper presents a method that integrates real-time electricity price prediction and multi-objective optimization for this problem. The method employs a deep learning model based on TimesNet to forecast the future real-time electricity prices and then formulates a multi-objective optimization model that allocates the electricity consumption for various types of industrial loads in different time periods according to the predicted prices and users own load demand. The method applies AMOPSO-MD algorithm to solve the model and obtain a set of Pareto optimal solutions. The method is evaluated by simulations based on the real data of magnesium industry, and validates the effectiveness and superiority of the proposed method.