Multi-index Evaluation based Reinforcement Learning Method for Cyclic Optimization of Multiple Energy Utilization in Steel Industry

Energy including coal, electricity, gas, etc., are directly related to the production process of steel industry. As such, a scientific and reasonable scheme for energy utilization is undoubtedly support the fulfillment of the production plan along with reduce energy consumption and environmental pollution. Aiming at optimizing the input amount of each energy resource in the Integrated Energy System (IES) of steel industry, a series of optimization models along with cyclic solution method based on Actor-Critic are proposed in this study, which can efficiently obtain the optimal energy utilization scheme considering both the global and local index. Firstly, the Energy Consumption per Ton Steel in the perspective of the whole IES and the emission of the byproduct gas regarding the energy subsystem are defined as the optimization objective respectively. Then, with the consideration of the practical constraints of the energy network, the mathematical programming models are accordingly established. Due to the existence of nonlinear constraints which brings about the difficulty for the conventional optimization method, a reinforcement learning based strategy is then designed to cyclically solve the optimization models for obtaining the final energy utilization scheme. Based on the practical data of steel industry, the experiment results demonstrate that compared with the commonly deployed methods, the proposed approach exhibits obvious superiority in controlling energy consumption as well as improving energy efficiency, which provides effective support for enterprises on energy saving.