The popularity of Electric Cars (EVs) is altering the future of transport by introducing a vision that effectively reduces GHG emissions and hence the carbon footprint. When the rate of EV adoption accelerates, there is a genuine chance of seeing major reductions in GHG emissions, and EVs play a critical part in this effort. However, like with most fast-rising sectors, there is an issue integrating EVs into current energy networks. A well-designed Energy Management System is required for optimal performance and easy communication with the energy network. The objective of this research is to discover such an EMS function in response to variable energy demand and supply while maintaining the integrity of the grid. Traditional rule-based and optimization-based EMS approaches are analyzed, revealing their limitations and the necessity for more dynamic and responsive solutions. Key technologies such as Bi-LSTM for load forecasting, reinforcement learning for optimal energy allocation and control, and vehicle-to-grid (V2G) for bidirectional power flow are explored.