An enhanced approach to optimally place the solar powered electric vehicle charging station in distribution network

Hazardous characteristics of the on-road vehicle-based emission rising an alarming situation for the urban communities. In this line, emission-free electric vehicles ensure a significant reduction in air pollution and improve ecological nature. However, the large-scale commercialization of electric vehicles is facing substantial addition in the electric demand which affects the stability of the distribution networks. Thus, in this paper, a comprehensive framework to optimally place the solar-powered charging stations in a distribution network with improved voltage profile, minimum power loss and reduced cost is proposed. The proposed methodology consists of a stochastic approach to predict the expected EV load demand at the charging stations, and a Feed-forward neural network to evaluate the expected solar power from the associated PV plant. Further, the impact of EV load demand on the distribution network, in terms of per unit voltage profile, voltage stability index, average voltage deviation index and power loss, is explored. Later, a computational methodology i.e. improved chicken swarm optimization is used to optimally place the charging stations in IEEE 33 bus system. The results are compared with the Jaya algorithm and teaching-learning-based optimization; the comparative study shows the dominance of the improved chicken swarm optimization.

Automated summary

This study proposes a comprehensive framework to optimally place solar-powered charging stations in a distribution network, aiming to improve voltage profile, minimize power loss, and reduce cost. The methodology involves a stochastic approach to predict EV load demand and a Feed-forward neural network to evaluate solar power from PV plants. The impact of EV load demand on the distribution network is explored, and an improved chicken swarm optimization method is used to optimize charging station placement in the IEEE 33 bus system, proving its dominance over other algorithms.