Answers are grounded in this paper and cite their sources.
Solar photovoltaic (PV) systems are strongly affected by nonlinear operating characteristics and variations in irradiance and temperature, while inadequate coordination among PV generation, battery storage (BS), and grid interaction can reduce energy utilization and economic performance. The main contributions of this paper are to present a novel hybrid Honey Badger Algorithm-Dynamic Temporal Fusion Graph Neural Network (HBA-DTFGNN) framework to handle these challenges by integrating maximum power point tracking (MPPT) and energy management (EM) for PV systems. The HBA optimizes the MPPT control parameters to achieve rapid and accurate maximum power extraction under varying operating conditions, while the DTFGNN captures temporal dependencies and interactions among PV generation, BS, and grid variables to support adaptive EM. The proposed framework is evaluated in MATLAB under varying operating conditions and compared with established MPPT and intelligent optimization methods. From the results, it has been observed that MPPT efficiency is 98.74%, settling time is 25 ms, overshoot is 0.8% and ripple is ± 0.5%. Furthermore, the suggested framework presents the lowest cost of energy (COE) which is 0.073 $/kWh, thus indicating better energy utilization and economic performance. These results validate the proposed HBA-DTFGNN method to be accurate in MPPT, effective in energy coordination, and good in overall PV system performance.
No takes yet. Share an insight, caveat, or question.
R et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: