An O&M Dynamic Scheduling Method for Large-Scale Distributed PV Systems

Operation and Maintenance (O&M) becoming increasingly important in the asset management of photovoltaic (PV) systems. Compared to large PV power plants, distributed PV systems are widely distributed and often located in complex terrain, which seriously increases the pressure of O&M tasks. However, at present, there is still a lack of effective O&M scheduling method for large-scale distributed PV systems, resulting in the untimeliness of O&M and high costs. To this end, the O&M tasks, staff, and equipment are firstly analyzed. Second, considering both planned and random tasks, an O&M dynamic scheduling model for large-scale distributed PV systems is proposed, which comprehensively considers labor cost, depreciation cost, power loss, and transportation cost to optimize the O&M benefits. Afterward, aiming to solve the problem that traditional optimization algorithms are prone to fall into local optima, a hierarchical hybrid algorithm named HGA-BPSO is proposed, which combines the advantages of genetic algorithm (GA) and binary particle swarm optimization (BPSO). Finally, the validity and rationality of the proposed method are verified by the case study of distributed PV poverty alleviation project in Badong County, Hubei Province. The results show that in the three different cases, the proposed method can reasonably dispatch O&M staff and equipment. The total cost of case 1 is 879.8 yuan, the total cost of case 2 is 2962.6 yuan, and the total cost of case 3 is 1728.3 yuan. At the same time, compared with the traditional meta-heuristic algorithm algorithm, the proposed GA-BPSO algorithm can better search for the global optimal.