A Steelmaking-continuous Casting Scheduling Optimization Method Considering Time-of-use Electricity Pricing

Small-scale scrap metal recycling and remanufacturing enterprises show great potential in the situation of green transformation and sustainable development faced by the steel industry. It has the main advantages of protecting the environment and saving resources. However the production planning and energy consumption problems of steelmaking-continuous casting (SCC) plague its development. In light of these considerations, this paper proposes an enhanced gray wolf optimization algorithm, designated as Q-GWO, which incorporates Q-Iearning to address the scheduling challenges associated with SCC under the influence of time-of-use electricity pricing. The method was tested in the context of production scheduling for a small scrap metal recycling and remanufacturing enterprise in Guangdong. The results demonstrated that the algorithm is capable of effectively scheduling the production process, optimizing the makespan, and initiating high-energy-consuming processes during periods of low electricity prices, thereby minimizing the total electricity cost. Furthermore, comparative experiments were conducted with the common Dynamic Programming (DP) algorithm, Gray Wolf Optimization (GWO) algorithm, and Genetic Algorithm (GA). The results demonstrated that the proposed algorithm exhibited superior performance compared to the other comparative algorithms.