Scheduling and Dynamic Energy Optimization in Cement Mills

Background/Aim: This study aims to address energy consumption challenges in cement milling operations by developing an integrated framework that incorporates production uncertainties and inventory management efficiency. The main objective is to minimize energy costs while improving production planning and environmental sustainability.Methods: In this context, statistical and machine learning techniques, including Autoregressive Integrated Moving Average (ARIMA), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM), are employed for electricity price forecasting. Based on the forecasting results, a Mixed Integer Linear Programming (MILP) model is developed to optimize production scheduling and energy consumption. The proposed framework incorporates forecasted electricity-price fluctuations into production scheduling to generate cost-oriented production plans while satisfying operational constraints.Results: Among the forecasting methods, the LSTM model demonstrates superior performance with the lowest error rates. Furthermore, the optimization model provides efficient production plans that satisfy operational constraints and improve resource utilization.Conclusion: The results indicate that integrating forecasting techniques with optimization models significantly enhances energy efficiency and production management in cement plants, while also contributing to environmental sustainability and strengthening the competitive advantage of industrial operations.