Predictive Maintenance Strategy for Photovoltaic Power Systems: Collaborative Optimization of Transformer-Based Lifetime Prediction and Opposition-Based Learning HHO Algorithm

In view of the insufficient utilization of condition-monitoring information and the improper scheduling often observed in conventional maintenance strategies for photovoltaic (PV) modules, this study proposes a predictive maintenance (PdM) strategy based on Remaining Useful Life (RUL) estimation. First, a RUL prediction model is established using the Transformer architecture, which enables the effective processing of sequential degradation data. By employing the historical degradation data of PV modules, the proposed model provides accurate forecasts of the remaining useful life, thereby supplying essential inputs for maintenance decision-making. Subsequently, the RUL information obtained from the prediction process is integrated into the optimization of maintenance policies. An opposition-based learning Harris Hawks Optimization (OHHO) algorithm is introduced to jointly optimize two critical parameters: the maintenance threshold L, which specifies the degradation level at which maintenance should be performed, and the recovery factor r, which reflects the extent to which the system performance is restored after maintenance. The objective of this joint optimization is to minimize the overall operation and maintenance cost while maintaining system availability. Finally, simulation experiments are conducted to evaluate the performance of the proposed PdM strategy. The results indicate that, compared with conventional corrective maintenance (CM) and periodic maintenance (PM) strategies, the RUL-driven PdM approach achieves a reduction in the average cost rate by approximately 20.7% and 17.9%, respectively, thereby demonstrating its potential effectiveness for practical PV maintenance applications.