Coordinated energy management strategy for multi-energy hub with thermo-electrochemical effect based power-to-ammonia: A multi-agent deep reinforcement learning enabled approach

Abstract

Power-to-ammonia (P2A) technology has attracted more and more attention since ammonia is recognized as a natural zero-carbon fuel. In this context, this paper constructs a renewable energy powered multi-energy hub (MEH) system which integrates with a thermo-electrochemical effect based P2A facility. Subsequently, the energy management of proposed MEH system is casted to a multi-agent coordinated optimization problem, which aims to minimize operating cost and carbon dioxide emissions while satisfying constraints. Then, a novel multi-agent deep reinforcement learning method called CommNet is applied to solve this problem to obtain the optimal coordinated energy management strategy of each energy hub by achieving the distributed computation of global information. Finally, the simulation results show that the proposed method can achieve better performance on reducing operating cost and carbon emissions than other benchmark methods.