Deep Reinforcement Learning Based on Proximal Policy Optimization for the Maintenance of a Wind Farm with Multiple Crews

The life cycle of wind turbines depends on the operation and maintenance policies adopted. With critical components being equipped with condition monitoring Prognostics Health Management (PHM) capabilities, it is feasible to significantly optimize (O&M) by combining (uncertain) information provided PHM other factors influencing O&M activities, including limited availability crews, variability energy demand corresponding production requests, long-time horizons systems operation. In this work, we consider optimization in farms woth multiple crews. A new formulation problem as a sequential decision over horizon proposed solved deep reinforcement learning based proximal policy optimization. method applied farm 50 turbines, considering optimal found outperforms state-of-the-art strategies, regardless number available