A deep reinforcement learning approach for chemical production scheduling. (4th October 2020)

• Record Type: Journal Article
• Authors: Hubbs, Christian D.; Li, Can; Sahinidis, Nikolaos V.; Grossmann, Ignacio E.; Wassick, John M.
• Is Part Of: Computers & chemical engineering. Volume 141(2020)
• Publication Date: 2020-10-04
• Subjects: Machine learning -- Reinforcement learning -- Optimization -- Scheduling -- Stochastic programming; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2020.106982
• Languages: English
• ISSNs: 0098-1354

Abstract

Abstract: This work examines applying deep reinforcement learning to a chemical production scheduling process to account for uncertainty and achieve online, dynamic scheduling, and benchmarks the results with a mixed-integer linear programming (MILP) model that schedules each time interval on a receding horizon basis. An industrial example is used as a case study for comparing the differing approaches. Results show that the reinforcement learning method outperforms the naive MILP approaches and is competitive with a shrinking horizon MILP approach in terms of profitability, inventory levels, and customer service. The speed and flexibility of the reinforcement learning system is promising for achieving real-time optimization of a scheduling system, but there is reason to pursue integration of data-driven deep reinforcement learning methods and model-based mathematical optimization approaches.