Simulation Modelling of Power Management Strategy for Grid Interactive Hybrid Power Supply Using Novel Artificial Neural Network

Baskaran, J (2025) Simulation Modelling of Power Management Strategy for Grid Interactive Hybrid Power Supply Using Novel Artificial Neural Network. IET Power Electronics, 18 (1). ISSN 1755-4535

[thumbnail of Simulation Modelling of Power Management Strategy for Grid Interactive Hybrid Power Supply Using Novel Artificial Neural Network.pdf] Text
Simulation Modelling of Power Management Strategy for Grid Interactive Hybrid Power Supply Using Novel Artificial Neural Network.pdf - Published Version
Available under License Creative Commons Attribution.

Download (5MB)

Abstract

Conventional power management methods struggle to respond effectively to the real‐time variability of hybrid renewable energy systems, affecting efficiency and reliability. This study introduces a novel configuration for a grid interactive hybrid power supply (GI‐HPS) that integrates power from renewable sources and the utility grid to serve industrial or utility loads. A key feature is the use of an intelligent controller implementing an instantaneous current reference scheme (ICRS)‐based power management system (PMS), which dynamically adjusts to changes in wind speed, solar irradiance, and load demand by continuously updating the reference current. Additionally, the study explores the design of an interleaved boost converter (IBC) with an optimal number of phases to reduce ripple and complexity. The MATLAB/SIMULINK response comparing the performance of two‐phase and four‐phase IBC revealed that the four‐phase configuration achieves lower current and voltage ripple (0.021 A and 0.53 V, respectively). Therefore, the four‐phase IBC is adopted in the GI‐HPS to stabilise voltage at the point of common coupling (PCC) under dynamic conditions. Simulation and experimental results using an embedded controller (EC) and artificial neural network (ANN) confirm the system's high stability and reliability.

Item Type: Article
Subjects: C Computer Science and Engineering > Artificial Neural Networks
D Electrical and Electronics Engineering > Power plant engineering
D Electrical and Electronics Engineering > Power System
Divisions: Electrical and Electronics Engineering
Depositing User: Dr Krishnamurthy V
Date Deposited: 05 Aug 2025 04:15
Last Modified: 05 Aug 2025 04:15
URI: https://ir.psgitech.ac.in/id/eprint/1484

Actions (login required)

View Item
View Item