Control Method for PEMFC Using Improved Deep Deterministic Policy Gradient Algorithm

Abstract

A data-driven PEMFC output voltage control method is proposed. Moreover, an Improved deep deterministic policy gradient algorithm is proposed for this method. The algorithm introduces three techniques: Clipped multiple Q-learning, policy delay update, and policy smoothing to improve the robustness of the control policy. In this algorithm, the hydrogen controller is treated as an agent, which is pre-trained to fully interact with the environment and obtain the optimal control policy. The effectiveness of the proposed algorithm is demonstrated experimentally.

Thermal Management of Proton‐Exchange Membrane Fuel Cells with Enhanced Fuzzy Control via an Improved Whale Optimization Algorithm

“…Furthermore, the widespread application of artificial intelligence (AI) technologies in the thermal management of fuel cell systems has achieved commendable results. [19,20] Wu et al [21,22] and Jia et al [23] applied data-driven methods to the management and control techniques of fuel cells, showcasing their strong adaptability and high-performance potential for broad development.…”

A novel automatic generation control method with hybrid sampling for multi-area interconnected girds

“…However, their intermittency, randomness, and unpredictability would severely jeopardize the stability and safety of the power systems. The conventional centralized automatic generation control (AGC) (Yu et al, 2011;Wang et al, 2014;Li et al, 2021a;Li et al, 2021b;Xie et al, 2022) aimed to only minimize the area control error (ACE) to output the total regulation power demands, which cannot achieve fast inter-area coordination in such a new type of power systems. Hence, centralized AGC cannot deal with the continuous declination in the control performance standards (CPS), such as system frequency and ACE, due to strong random disturbances.…”