Cognitive fuzzy logic-integrated energy management for self-sustaining hybrid renewable microgrids

The Sustainable Energy Resource integrated with Energy Storage System is deployed inside a microgrid, using a power management method to effectively regulate energy consumption during peak demand. Demand-based energy management measures, such as distributing load and stalling appliance usage amid peak hours are executed. An Integrated Energy Management System (EMS) was proposed employing fuzzy logic as a solution to manage the energy needs of loads in this work. The system effectively used a combination of the hybrid utility grid, photovoltaic (PV), wind, and battery to optimise the utilisation of renewable energy resources for load supply. The implementation of an effective management system is intended to control the energy production of a novel hybrid electrical power system by changes in load. The EMS concomitantly considers power demand, renewable power, and State of Charge (SoC) through the incorporation of fuzzy logic control. Cost analysis employing three optimisation techniques like Firefly, PSO and Genetic Algorithm for the equivalent load profile and sources also conducted. Fuzzy EMS enhances energy management by 41.40% LCOE in comparison to the Firefly Algorithm. It decreases expenses by 24.09% more effectively than the PSO Algorithm. In comparison to the Genetic Algorithm, the Fuzzy EMS demonstrates a 45.02% reduction in LCOE, hence establishing its capacity to provide a more economical energy solution. This technique considers security constraints and makes an intelligent choice of energy sources based on grid electricity costs. Maximising system resilience and making the most effective feasible utilisation of green energy sources are the primary goals.