Neural Network Based Control Scheme for Micro-Grid Integrated HRES

Abstract

Microgrids and HRES (Hybrid Renewable Energy Systems) are two related concepts that have gained considerable attention in recent years, particularly in the context of decentralized and sustainable energy systems. The integration of renewable energy sources in micro-grids is becoming increasingly important for meeting the electricity needs of rural areas. HRES contains a solar-air-biomass-bio-fuel-fuel cell and battery. Existing works involved sensitive analysis& utilized annual wind speed fluctuations, biofuel prices, energy costs, and net initial contribution costs. However, the instability of renewable materials such as sun and wind complicates the energy production process. In this paper, an optimal HRES configuration consisting of solar, wind, battery, and ultra-capacitor battery system is proposed. To optimize the HRES, a neural network-based control scheme is designed to balance the renewable energy output with peak load requirements, utilizing battery power storage. The proposed optimization strategy ensures the efficient operation of the HRES by minimizing energy losses, reducing carbon emissions, and improving the overall system reliability. The effectiveness of the proposed HRES and control scheme is demonstrated through simulation results. The proposed system contributes to the development of sustainable rural electrification solutions.