Title: Power quality enhancement in smart grid connected renewable energy system using hybrid deep learning and optimised Cuk-SEPIC converter

Authors: Amit Kumar; Jayanti Chaudhary

Addresses: Department of Electrical Engineering, National Institute of Technology (NIT) Patna, Patna, Bihar, India ' Department of Electrical Engineering, National Institute of Technology (NIT) Patna, Patna, Bihar, India

Abstract: Power generation from Hybrid Renewable Energy Systems (HRES) such as PV, FC and batteries is subject to weather conditions, resulting in Power Quality (PQ) problems such as voltage variations, harmonics, swells and sags. This paper proposes a model that integrates a STATCOM with an HRES to enhance the system's fixed operating limit and compensate for PQ issues. An optimised Cuk-SEPIC converter to improve voltage regulation and reduce output voltage ripple. Also, a new deep-learning model that includes DBNs and Bi-LSTM algorithm and hybrid optimisation techniques such as Golden Eagle Optimisation (GEO) and Slime Mould Optimisation (SMO) is used to optimise the STATCOM parameters for maximum efficiency. The proposed approach is evaluated using power flow and quality analyses on the IEEE 9 bus system. The MATLAB/SIMULINK platform is used to examine the efficacy of the proposed approach. As a result, the THD level was lowered by 0.17601%, which is better than other currently utilised methods.

Keywords: power quality; STATCOM; static synchronous compensator; SEPIC; single-ended primary-inductance converter; SMO; slime mould optimisation; GEO; golden eagle optimisation; BESS.

DOI: 10.1504/IJWMC.2026.150863

International Journal of Wireless and Mobile Computing, 2026 Vol.30 No.1, pp.85 - 105

Received: 15 Jun 2023
Accepted: 14 Jan 2024
Published online: 24 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article