Aiming at optimal siting and sizing for distributed photovoltaic (PV) access to distribution network

and considering the impacts of voltage fluctuation and voltage overlimit brought by grid connection on power quality

the voltage at distribution network nodes is regulated by introducing energy storage system. Firstly

an iterative self-organizing data analysis algorithm is employed to cluster the output data of distributed PV

and the clustering performance is evaluated based on between-class similarity and within-class similarity. Secondly

a two-stage optimization model for distribution network is established: the first stage aims to minimize the total cost by considering the siting and sizing of distributed PV and energy storage

and the planning parameters will be passed to the second stage; the second stage takes minimum node voltage deviation and minimum operation and maintenance costs as objective function. And then

the Beluga whale optimization algorithm is applied to solve the model

which incorporates variable spiral search strategy and crisscross strategy to enhance its local and global optimization capabilities. Finally

simulation verification is carried out on IEEE 33-node system.