Hybridized Energy Management and Power Forecasting in Grid-Tied Solar Photovoltaic and Wind Turbine with Electric Vehicles

Abstract

The growing integration of renewable energy sources and electric vehicles (EVs) into grid systems poses serious challenges to energy forecasting, power management, and system stability. The conventional energy management frameworks fall short in responding to the uncertainty of renewables and dynamic load behavior of EVs. In this context, the current research suggests a novel hybridized energy management and power forecasting scheme to enhance grid resilience, sustainability, and efficiency. A two-way communication model is established to facilitate real-time electricity price and power coordination among solar photovoltaic (PV), wind turbines, energy storage devices, EVs, and industrial loads. The new kernel-based nonparametric energy mode optimizer model, which is trained on historical energy and weather patterns, strongly enhances the accuracy of power forecasting and system response. Experimental outcomes confirm peak PV generation of 17 kW at noon with inverter output of 16 kW, and voltage across microgrids (MG1: 0.94–1.06 V, MG2: 0.90–1.025 V) within the stable range. Battery state of charge varies between 180 and 200%, providing stable energy supply and load balancing. This research fills core energy forecasting and grid interfacing gaps and provides a scalable solution for future smart grid and EV-integrated renewable systems.