Research on Estimation of Regional Distributed Photovoltaic Output Based on K-medoids Algorithm

Distributed photovoltaic (PV) power generation has been widely applied in recent years. The monitoring of distributed PV output plays an important role in the safe and stable operation of power grid. However, the current monitoring capability cannot cover all distributed PV power stations. To solve this problem, a method for estimating regional distributed PV output based on k-medoids algorithm is proposed. Firstly, the feature set of each station is constructed. Then, the phased clustering and sample station selection are realized based on k- medoids algorithm. Finally, combined with the real-time power data of sample stations, the regional distributed PV output is estimated. The experimental results show that when the number of sample stations reaches more than 22% of the number of stations in this region, estimation accuracy can reach more than 90%. The method proposed in this paper needs fewer monitoring sites, which has strong practicability.