IoT-integrated smart energy management system with enhanced ANN controller for small-scale microgrid

This research paper focuses on an intelligent energy management system (EMS) designed and deployed for small-scale microgrid systems. Due to the scarcity of fossil fuels and the occurrence of economic crises, this system is the predominant solution for remote communities. Such systems tend to employ renewable energy sources, particularly in hybrid models, to minimize fuel costs and promote environmental sustainability. However, in small-scale microgrids, a significant challenge lies in maximizing power utilization amidst rapid variations in ecological conditions in renewable energy resources, ensuring energy balance during peak demand, and preventing wastage during low demand condition. To address these issues, this research focuses on two main areas. Firstly, the implementation of the GWO-tuned feed-forward neural network MPPT algorithm in both solar and wind energy conversion systems. This control algorithm demonstrates superior performance compared to existing controllers by efficiently tracking the maximum power point (MPP) value and rapidly utilizing the available power. Secondly, IoT-based energy monitoring system is implemented in small-scale microgrid systems to track the real time of data from sources like wind, solar, and batteries. Furthermore, intelligent rule-based strategies are employed to enhance the control function of EMS and ensure stability within the microgrid. This system effectively manages microgrid demand and prevents power wastage. In this specific EMS setup, the battery storage unit is a key component, but challenges arise when there are sudden load and power generation fluctuations, leading to disruptions in control mechanisms. To address this, a GWO-tuned ANN controller is integrated into the voltage control loop of the battery controller unit, effectively correcting DC bus voltage fluctuations and maintaining stability. The entire work has been designed, and system performances are analyzed in the MATLAB Simulink environment and compared with existing work. The simulation results have been validated by means of experimental setup.