سال انتشار:
2020
عنوان انگلیسی مقاله:
A deep reinforcement learning approach for chemical production scheduling
ترجمه فارسی عنوان مقاله:
یک رویکرد یادگیری تقویتی عمیق برای برنامه ریزی تولید مواد شیمیایی
منبع:
Sciencedirect - Elsevier - Computers and Chemical Engineering, 141 (2020) 106982. doi:10.1016/j.compchemeng.2020.106982
نویسنده:
Christian D. Hubbs a , Can Li a , Nikolaos V. Sahinidis a , ∗, Ignacio E. Grossmann a , John M. Wassick b
چکیده انگلیسی:
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 optimiza- tion of a scheduling system, but there is reason to pursue integration of data-driven deep reinforcement learning methods and model-based mathematical optimization approaches.
Keywords: Machine learning | Reinforcement learning | Optimization | Scheduling | Stochastic programming
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0