Two-layer optimization configuration method for distributed photovoltaic and energy storage systems based on IDEC-K clustering

Abstract

A two-layer optimization configuration method for distributed photovoltaic (DPV) and energy storage systems (ESS) based on IDEC-K clustering is proposed to address the issues of voltage violations and excessive network losses caused by the high proportion of distributed resource integration into distribution grids. Firstly, an improved Deep Embedded Clustering (IDEC) algorithm is combined with the K-means clustering algorithm to cluster historical data of distributed photovoltaics and loads, generating typical scenarios. Then, based on typical scenarios, considering the economy and reliability of DPV and ESS, a two-layer optimal configuration model is established, solved using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). Finally, simulation experiments are conducted on the improved IEEE 33-bus distribution system. The experimental results demonstrate the effectiveness of the proposed method can reduce the voltage range of each node of the distribution network, reduce the fluctuation range of node voltage, and reduce the risk of voltage over-limit and line loss rate of the distribution network.