VEHICLE TO GRID ENERGY MANAGEMENT PLATFORM USING AI DRIVEN LOAD OPTIMIZATION

The proposed V2G platform integrates protected battery sensing, ESP32-based local control, framed serial communication, short-term load forecasting and constrained energy optimization. Its main contribution is an auditable division of responsibility: the PC recommends an operating action, while the embedded controller decides whether the action is safe to execute. The design supports repeatable comparison of forecasting and scheduling methods without depending on cloud services or direct utility-grid connection. Future work will complete calibrated hardware trials, compare forecasting models on unseen profiles, investigate probabilistic forecasts and model predictive control, and evaluate migration to CAN, Modbus or vehicle-charging protocols. Any hardware scale-up will retain independent protection and require new insulation, thermal and certification analysis.

[1] W. Kempton and J. Tomic, ‘Vehicle-to-grid power fundamentals: Calculating capacity and net revenue,’ Journal of Power Sources, 2005. [2] W. Kempton and J. Tomic, ‘Vehicle-to-grid power implementation: From stabilizing the grid to supporting renewable energy,’ Journal of Power Sources, 2005. [3] ISO 15118-20, Road vehicles - Vehicle to grid communication interface - Part 20. [4] IEC 61851-1, Electric vehicle conductive charging system - General requirements. [5] G. L. Plett, Battery Management Systems, Volumes I and II, Artech House. [6] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice. [7] Espressif Systems, ESP32 Series Datasheet and ESP-IDF Programming Guide. [8] Texas Instruments, INA226 Bidirectional Current and Power Monitor Datasheet.