Intelligent Electric Vehicle Charging Hubs AI-Based Demand Forecasting and Smart Energy Management
Main Article Content
Abstract
The growing integration of electric vehicles (EVs) and their aggregated battery storage capacity offers significant opportunities for supporting smart grid operation while reducing dependence on fossil fuels in the transportation sector through increased utilization of renewable energy resources such as solar and wind power. Effective integration requires continuous monitoring of EV connection points, charging behavior, and available battery capacity to improve grid flexibility and facilitate wider renewable energy penetration. This study presents an implemented data warehouse framework designed to collect, organize, and analyze comprehensive EV charging information together with electricity price data obtained from the spot market. Over a period exceeding 2.5 years, the developed system accumulated charging information from 176 electric vehicles, enabling detailed investigation of charging behavior, station utilization, energy demand, and spatial charging patterns. Artificial Intelligence (AI) and machine learning techniques are incorporated into the analytical framework to identify recurring charging patterns, forecast EV charging demand, and estimate variations in available battery capacity across the vehicle fleet during different periods of the day. Predictive models can further analyze historical charging behavior, electricity prices, and temporal usage characteristics to support intelligent scheduling of charging activities. In addition, AI-based optimization techniques can determine suitable charging periods by considering electricity cost, predicted energy demand, battery availability, and renewable power generation. The proposed framework also enables users to reduce charging expenses by predicting low-price electricity intervals and scheduling charging accordingly. These analyses demonstrate how the combination of data warehousing, predictive analytics, and AI-assisted charging management can improve understanding of EV charging dynamics. The resulting information can support intelligent charging controllers, grid operators, and energy management systems in optimizing charging schedules, improving renewable energy utilization, reducing peak demand, and contributing to the development of a more efficient, reliable, and sustainable smart energy infrastructure
Article Details
Section
How to Cite
References
1. Eswaramoorthy, K., and V. K. Shunmughanaathan. "A Simple and Geometry Based Fast Space Vector PWM Technique For 15 Level Cascaded Multilevel Inverter with Reduction of Switches." Asian Journal of Research in Social Sciences and Humanities Vol.6, no. 10, pp.2305-2320 and 2016.
2. Muthukumar, P., Venkata Ramesh Maddukuri, K. Eswaramoorthy, N. Veeramuthulingam, and T. Jarin. "The review and investigation of sustainable 13-level multilevel inverter control strategies." World Review of Science, Technology and Sustainable Development 17, no. 2-3 (2021): 153-171.
3. Lekshmi Sree B, and M. G. Umamaheswari. "A Hankel matrix reduced order SEPIC model for simplified voltage control optimization and MPPT." Solar Energy 170 (2018): 280-292.
4. Sangari, A., R. Umamaheswari, and Mallapu Gopinath Umamaheswari. "A novel SOSMC based SVPWM control of Z-source inverter for AC microgrid applications." Microprocessors and Microsystems 75 (2020): 103045.
5. Sundaramoorthy, S., et al. "Hopfield Neural Network-Based Average Current Mode Control of Synchronous SEPIC Converter." IETE Journal of Research (2021): 1-19.
6. Muthukumar, P., L. Padmasuresh, K. Eswaramoorthy, and S. Jeevananthan. "Critical analysis of random frequency inverted sine carrier PWM fortification for half-controlled bipolar three-phase inverters." Journal of Power Electronics 20, no. 2 (2020): 479-491.
7. Paramasivan, Muthukumar, K. Eswaramoorthy, Rathinam Muniraj, Padmasuresh Lekshmi Kanthan, Thanikanti Sudhakar Babu, S. Jeevananthan, and Hassan Haes Alhelou. "An Alternative Level Enhanced Switching Angle Modulation Schemes for Cascaded H Bridge Multilevel inverters." IEEE Access (2023).