Joint Manufacturing and Onsite Microgrid System Control Using Markov Decision Process and Neural Network Integrated Reinforcement Learning

Abstract

Onsite microgrid generation systems with renewable sources are considered a promising complementary energy supply system for manufacturing plant, especially when outage occurs during which the energy supplied from the grid is not available. Compared to the widely recognized benefits in terms of the resilience improvement when it is used as a backup energy system, the operation along with the electricity grid to support the manufacturing operations in non-emergent mode has been less investigated. In this paper, we propose a joint dynamic decision-making model for the optimal control for both manufacturing system and onsite generation system. Markov Decision Process (MDP) is used to formulate the decision-making model. A neural network integrated reinforcement learning algorithm is proposed to approximately estimate the value function given policy of MDP. A case study based on a manufacturing system as well as a typical onsite microgrid generation system is conducted to validate the proposed MDP model as well as the solution strategy.