Bayesian Optimization based Random Forest Method for State-of Charge Prediction for Congestion Management in Distribution System Considering Charging Coordination of Plug-in Electric Vehicle

During the past decade, the sharp rise in plug-in electric vehicle (PEV) in transportation sector reflects it popularity in worldwide. The concept of transportation electrification has established mainly due to the gradual exhaustion of fossil fuels which are the main primary sources of fuel in conventional vehicle. But, as the penetration level of PEVs increases, the need for reformation of electrical infrastructure also increases. The rise in net electrical load during charging of PEVs tends the system towards the level of congestion. In this paper, the grid-to-vehicle (G2V) and vehicle-to-grid (V2G) concept has been adopted during charging coordination strategy in distribution system. Also, charging place has been considered as solar powered chargingcum-parking lot (SPCPL) in the distribution system. In this work, random forest and Bayesian optimization has been combined for PEVs state-of-charge (SOC) prediction during coordination strategy. The particle swarm optimization (PSO) based coordination strategy has been established for the effective congestion management in 38 bus distribution system.