A Hybrid GA–Digital Twin Strategy for Real-Time Nighttime Reactive Power Compensation in Utility-Scale PV Plants

This paper proposes a hybrid strategy that integrates a Genetic Algorithm (GA) with Digital Twin (DT) technology to address the issue of nighttime reactive power backfeed in large-scale photovoltaic (PV) power plants. First, a GA is employed to optimize the location and number of multitask inverters to minimize line losses and eliminate the reactive power backfeed. Subsequently, the DT continuously monitors the grid conditions and performs a rolling dispatch of the inverter units to respond to the residual reactive power caused by the nighttime voltage fluctuations. The experimental results show that GA-based optimization reduces the line losses from 0.346  kW to 0.2818 kW, a reduction of approximately 18.6%, and helps to prevent thermal damage to the inverters. When combined with DT technology, the strategy further enhances voltage stability and demonstrates strong adaptive control capabilities. The proposed method effectively reduces the operation and maintenance costs of PV plants and shows a promising potential for practical deployment.