Distributed deep reinforcement learning-based gas supply system coordination management method for solid oxide fuel cell

In order to sustain solid oxide fuel cell (SOFC) net output power and prevent violation of oxygen excess ratio (OER) constraint and fuel utilization (FU) constraint, a data-driven gas supply system coordination management method is proposed. Accordingly, a population evolution-based multi-agent double delay deep deterministic policy gradient (PE-MA4DPG) algorithm is introduced. The artificial intelligence design of the algorithm is guided by the concepts of imitation learning and curriculum learning, whereby different agents of different combinations are trained in different environments, thus improving the robustness of the coordination strategy. In this algorithm, the hydrogen controller and the air controller are treated as two agents. The centralized training enables agents with different objectives to coordinate with each other. The effectiveness of the proposed algorithm is demonstrated in three experiments, wherein the proposed algorithm is compared with a group of existing algorithms.

Automated summary

To maintain the net output power of solid oxide fuel cells (SOFC) and avoid violating oxygen excess ratio and fuel utilization constraints, a data-driven gas supply system coordination management method is proposed. The algorithm, called PE-MA4DPG, is based on population evolution and utilizes multi-agent double delay deep deterministic policy gradient. The algorithm's effectiveness is demonstrated in comparison to existing algorithms through three experiments.