Reliable Power Scheduling of an Emission-Free Ship: Multiobjective Deep Reinforcement Learning

Abstract

Environmental pollutants, as a global concern, have led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in all-electric ships, as well as power grids, has increased in recent years. In this article, in order to have a zero-emission and cost-effective energy management in an all-electric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, the loss of load expectation (LOLE) as a reliability index is considered in the energy management context and the problem is solved by the deep reinforcement learning in a multiobjective manner. The results of the consideration of two common standards, including DNVGL-ST-0033 and DNVGL-ST-0373, demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.