A Hybrid Approach for Efficient EV Charging: Honey Badger Algorithm-Optimized ANN for Harmonic Mitigation in Solar PV and Grid-Connected Systems

This manuscript presents a novel Hybrid
Artificial Intelligence (AI) framework that incorporates a
Unified Power Quality Conditioner (UPQC) to regulate power
disturbances and improves the power quality and reliability of
solar Photovoltaic (PV) and grid-connected Electric Vehicle
Charging Stations (EVCS). For precise management of UPQC
under dynamic and nonlinear loading conditions, the Honey
Badger Algorithm (HBA)-optimized Artificial Neural Network
(ANN) is the main innovation. The dual function of the UPQC is
to enable stable bidirectional power flow between the load,
distributed Renewable Energy Sources (RES) like solar PV
arrays, and EVs using supercapacitor while simultaneously
reducing power quality problems including voltage sags, swells,
and current harmonics. Over thorough simulations in
MATLAB/Simulink, the proposed hybrid HBA-ANN
methodology is verified, and its performance is contrasted with
that of traditional optimization methods. The outcomes show
significant gains in energy transfer efficiency, voltage
stabilization and Total Harmonic Distortion (THD) reduction of
(1.56%), demonstrating the efficacy of this clever, power￾quality-aware EV charging system. A future-ready solution for
intelligent and robust EV charging infrastructure is ensured by
the combination of adaptive neural control and intelligent
optimization model