Modified Artificial Hummingbird Algorithm for Determining Optimal Location of EVCS in Power Grid

The rapid increase in the adoption of electric vehicles (EVs) in recent years is leading to a significant impact on the electric grid. To ensure sufficient power to these EVs, multiple electric vehicle charging stations (EVCSs) need to be deployed strategically in the electrical power network. Randomly adding these EVCSs can cause potential power quality problems and necessitate additional infrastructure like new distribution/transmission lines, transformers and sub-stations. This can be overcome by optimal deployment of EVCSs. Many existing optimization techniques suffer from premature convergence, sensitivity to initial parameters, the curse of dimensionality and not performing well on non-linear problems. This leads to suboptimal results. To address these drawbacks, a novel method, based on the Artificial Hummingbird Algorithm (AHA), has been developed to identify the optimal location of EVCSs. The novel method, the Modified Artificial Hummingbird Algorithm (MAHA), has been applied to the standard power network–IEEE-57 bus system to find the optimal placement of EVCSs. When compared to existing methods of AHA, Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO), the results show that MAHA is more effective in determining the optimal placement of EVCSs.