Title
A Game Theory-Reinforcement Learning (Gt-Rl) Method To Develop Optimal Operation Policies For Multi-Operator Reservoir Systems
Keywords
Conflict resolution; Evolutionary algorithm; Game theory; Optimization; Reinforcement learning; Reservoir operation
Abstract
Reservoir systems with multiple operators can benefit from coordination of operation policies. To maximize the total benefit of these systems the literature has normally used the social planner's approach. Based on this approach operation decisions are optimized using a multi-objective optimization model with a compound system's objective. While the utility of the system can be increased this way, fair allocation of benefits among the operators remains challenging for the social planner who has to assign controversial weights to the system's beneficiaries and their objectives. Cooperative game theory provides an alternative framework for fair and efficient allocation of the incremental benefits of cooperation. To determine the fair and efficient utility shares of the beneficiaries, cooperative game theory solution methods consider the gains of each party in the status quo (non-cooperation) as well as what can be gained through the grand coalition (social planner's solution or full cooperation) and partial coalitions. Nevertheless, estimation of the benefits of different coalitions can be challenging in complex multi-beneficiary systems. Reinforcement learning can be used to address this challenge and determine the gains of the beneficiaries for different levels of cooperation, i.e., non-cooperation, partial cooperation, and full cooperation, providing the essential input for allocation based on cooperative game theory. This paper develops a game theory-reinforcement learning (GT-RL) method for determining the optimal operation policies in multi-operator multi-reservoir systems with respect to fairness and efficiency criteria. As the first step to underline the utility of the GT-RL method in solving complex multi-agent multi-reservoir problems without a need for developing compound objectives and weight assignment, the proposed method is applied to a hypothetical three-agent three-reservoir system.
Publication Date
11-7-2014
Publication Title
Journal of Hydrology
Volume
519
Issue
PA
Number of Pages
732-742
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.jhydrol.2014.07.061
Copyright Status
Unknown
Socpus ID
84906765896 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84906765896
STARS Citation
Madani, Kaveh and Hooshyar, Milad, "A Game Theory-Reinforcement Learning (Gt-Rl) Method To Develop Optimal Operation Policies For Multi-Operator Reservoir Systems" (2014). Scopus Export 2010-2014. 8239.
https://stars.library.ucf.edu/scopus2010/8239