Machine learning based decision making for time varying systems: Parameter estimation and performance optimization
作者：
Highlights：
• A dynamic decision making problem is formulated for time varying systems.
• A machine learning method estimates unknown parameters using recorded data.
• A MPC method predicts the optimal decision using estimated parameters.
• A machine learning based MPC algorithm is proposed for decision making problems.
• The effective performance of the algorithm is evaluated in a case study.
摘要
•A dynamic decision making problem is formulated for time varying systems.•A machine learning method estimates unknown parameters using recorded data.•A MPC method predicts the optimal decision using estimated parameters.•A machine learning based MPC algorithm is proposed for decision making problems.•The effective performance of the algorithm is evaluated in a case study.
论文关键词：Machine learning,Model predictive control,Time varying system
论文评审过程：Received 1 March 2019, Revised 3 January 2020, Accepted 4 January 2020, Available online 10 January 2020, Version of Record 7 February 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.105479
