A Game-Theoretical Approach for Optimal Supervisory Control of Discrete Event Systems under Energy Constraints

Abstract

In this paper, we investigate the problem of optimal supervisory control for the discrete event systems under energy constraints. We consider that the execution of events consumes energy and the energy can be replenished at specific reload states. When the energy level drops below zero, the system will be crashed. To capture the above scenario, we introduce a new model, called consumption discrete event system (cDES). Our objective is to find the minimal initial energy value and synthesize an optimal supervisor ensuring that the energy will never be exhausted. To solve this problem, we propose a game-theoretical approach by converting the cDES as a consumption two-player graph game (cTPG) and reformulate the optimal supervisory control problem in game theory. In particular, we demonstrate that the converted game can be decomposed into independent reachability games related to reload vertices, which can be solved by a fixed point iterative algorithm proposed in this paper. Through iteratively removing unsafe reload vertices and solving reachability games for the remaining reload vertices, a solution can be found.