1Evangelin Jeba J, Assistant Professor, Department of Electrical and Electronics Engineering, Maria College of Engineering and Technology, Attoor (Tamil Nadu), India.
2C. R. Rajesh, Assistant Professor, Department of Electrical and Electronics Engineering, CSI Institute of Technology, Thovalai (Tamil Nadu), India.
Manuscript received on 08 July 2023 | Revised Manuscript received on 05 August 2023 | Manuscript Accepted on 15 August 2023 | Manuscript published on 30 August 2023 | PP: 22-29 | Volume-12 Issue-6, August 2023 | Retrieval Number: 100.1/ijeat.F42490812623 | DOI: 10.35940/ijeat.F4249.0812623
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In micro grids, energy management is referred to as an information and control system that offers the essential functionality to ensure that the energy supply from the generation and distribution systems occurs at the lowest possible operational cost. Energy management systems (EMS) support distributed energy resource utilization in micro grids, especially when variable generation and pricing are present. In this paper, an Artificial Neural Network (ANN)-based energy management approach for a hybrid wind, solar and Battery Storage System (BSS) is presented. To sustain the DC voltage, a 3 Port DC-DC Converter is also proposed. While renewable energy systems have numerous advantages, one of the challenges they face is the intermittency of power generation, leading to fluctuations in the power supply to the grid. Therefore, EMS aims to reduce these variations. Another goal is to maintain the battery state of charge (SOC) within the allowed ranges to extend the battery life. The implementation is carried out in Simulink/Matlab platform. To demonstrate the efficacy of the suggested approach, we compare the Total Harmonic Distortion (THD) of the proposed controller (1.52%) with that of conventional controllers, including the ZSI-based PID controller (3.05%), PI controller (4.02%), and FO-PI (3.32%) controller.
Keywords: Artificial Neural Network, Battery Energy System, Energy Management System, State of Charge
Scope of the Article: Artificial Intelligence