Abstract
The growth of renewable sources and electric vehicles' (EVs) load demand and associated uncertainties can stress the reliable network performance, such as uncertainty in both production and load sides, and power loss augmentation. These challenges can be mitigated by optimal planning considering variable output from wind and photovoltaic systems to meet the additional demand caused by EV charging. Swapping stations present an alternative solution for charging EVs that can lead to a different EV charging ecosystem. This study employs a stochastic clustering-based approach to optimally coallocate swapping stations, and wind-photovoltaic systems in networks. A K-means clustering method is implemented to classify price, energy demand, wind, and photovoltaic generation into appropriate clusters embedded into the particle swarm optimization (PSO) algorithm. The decision variables of PSO are the wind-photovoltaic system capacity and hybrid system placement to supply the EV load demand for battery swapping stations. The problem aims to maximize the net profit. The multi-criteria decision-making method, technique for order of preference by similarity to ideal solution, is applied to evaluate the results by considering all key influence criteria on the system's performance. The performance of the proposed optimal co-allocation method on the IEEE 33-bus system has been investigated to demonstrate the effectiveness of integrating battery swapping stations into distribution systems.