Predictive Modelling and Simulation of Vehicle-to-Grid Systems Using Hidden Markov Algorithm and Microgrid Integration

Abstract

This paper proposes a predictive modelling approach for vehicle-to-grid (V2G) systems using Hidden Markov Algorithm (HMA). V2G systems allow electric vehicles (EVs) to be used as a source of energy for the grid, enabling bidirectional power flow and offering a range of benefits, such as improved energy management and reduced greenhouse gas emissions. The proposed predictive modelling approach uses HMA to model the stochastic behavior of EVs and their charging and discharging patterns. The HMA-based model is trained on historical data and can be used to predict future charging and discharging events of EVs connected to the grid. The proposed approach aims to optimize the performance of V2G systems by predicting the energy demand and supply in advance, and accordingly scheduling the charging and discharging events of EVs to balance the energy supply and demand. The proposed approach is evaluated using a real-world dataset of EVs connected to the grid. The experimental results show that the HMA-based model can accurately predict the future charging and discharging events of EVs with high accuracy. The predicted results are then used to optimize the energy management of the V2G system, which leads to improved energy efficiency and reduced operational costs. Overall, this research demonstrates the effectiveness of using HMA for the predictive modelling of V2G systems, which can help in optimizing the performance of the V2G systems and facilitating the integration of renewable energy sources into the microgrid.