Artificial Rabbits Optimized Neural Network-Based Energy Management System for PV, Battery, and Supercapacitor Based Isolated DC Microgrid System

• Published in: IEEE access 2023, Vol.11, p.142411-142432
• Main Authors: D., Sandeep S., Mohanty, Satyajit
• Format: Article
• Language: English
• Subjects: Artificial neural network; Artificial neural networks; artificial rabbits optimization; Batteries; Costs; Data buses; DC machines; DC microgrid; Distributed generation; Electric potential; Energy management; energy management system; Energy management systems; Energy storage; Incremental conductance; Maximum power tracking; Microgrids; Modulators; Neural networks; Optimization methods; Power management; PV system; Rabbits; Regulators; storage system; Supercapacitors; Voltage; Voltage control
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3340856

This article introduces a method for managing energy in an isolated DC microgrid by utilizing a battery and a supercapacitor. The approach employs an artificial rabbits optimized neural network (ARONN) control system. The principal goal of this power management method is to meet the power demand while ensuring balanced production and consumption, along with maintaining a stable DC bus voltage. One notable advantage of this method is that its losses are accounted for during the design of power modulators, achieved through scheming the actual power accessible on the shared common bus. The isolated DC microgrid regulator combines the incremental conductance maximum power point tracking (MPPT) technique for maximizing power extraction from PV sources and ARONN control for managing the power modulator in the storage scheme. By effectively controlling the flow of power on the shared DC bus, the steadyness of the bus DC voltage is maintained with minimal error from the reference voltage. This approach also minimizes battery stress by directing low-frequency current control for the battery and higher-frequency current control for the supercapacitor. The efficiency of the suggested energy management and regulator strategies is confirmed by the outcomes obtained from the simulation.