SAFE & DATA-EFFICIENT SAC BASED MPPT UNDER PARTIAL SHADING WITH SIM-TO-REAL VALIDATION
Abstract
This paper proposes a Safe and Data-efficient Soft Actor–Critic (SAC) based MPPT approach for photovoltaic (PV) systems operating under partial shading and dynamic irradiance. The proposed controller leverages SAC’s continuous-action learning capability to achieve fast convergence and ripple-free steady-state operation while ensuring safe duty-cycle adaptation. A comprehensive simulation benchmark comparing SAC, PID, and Intelligent Perturb & Observe (P&O) was performed using a simplified PV model with dynamic irradiance and temperature profiles. Results demonstrate that SAC achieved a 97.79% average tracking efficiency, 97.58% energy efficiency, and a significantly reduced steady-state error (2.06%) and ripple (9.70%), outperforming PID (50.05%) and P&O (41.80%) controllers. The proposed method effectively bridges the gap between AI based MPPT adaptability and real-world reliability through a safe, data-efficient learning design validated in sim-to-real scenarios.
References
O. Boubaker, “MPPT techniques for photovoltaic systems: a systematic review in current trends and
recent advances in artificial intelligence,” Discover Energy, 2023, doi: 10.1007/s43937-023-00024-2.
N. Kacimi, A. Idir, S. Grouni, and M. S. Boucherit, “Improved MPPT Control Strategy for PV
Connected to Grid Using IncCond-PSO-MPC Approach,” CSEE Journal of Power and Energy
Systems, May 2023, doi: 10.17775/CSEEJPES.2021.08810.
N. F. Ibrahim, M. M. Mahmoud, H. Alnami, D. E. Mbadjoun Wapet, S. A. E. M. Ardjoun, M. I.
Mosaad, A. M. Hassan, and H. Abdelfattah, “A new adaptive MPPT technique using an improved
INC algorithm supported by fuzzy self-tuning controller for a grid-linked photovoltaic system,” PLOS
ONE, Nov. 3, 2023, doi: 10.1371/journal.pone.0293613.
M. Mishra, P. Mahajan, and R. Garg, “Implementation and comparison of metaheuristically modified
ANN MPPT controllers under varying solar irradiance conditions,” Electrical Engineering, vol. 106,
pp. 3427–3443, 2024, doi: 10.1007/s00202-023-02165-y.
R. Khezri, M. Naderi, and S. G. Zadeh, “Adaptive Model Predictive Control-Based MPPT Technique
for Solar PV System with Novel Multi-Input Converter,” Frontiers in Energy Research, Aug. 29,
, doi: 10.3389/fenrg.2024.1430740.
A. Wadehra, S. Bhalla, V. Jaiswal, K. P. S. Rana, and V. Kumar, “A deep recurrent reinforcement
learning approach for enhanced MPPT in PV systems,” Applied Soft Computing, vol. 162, p. 111728,
Sep. 2024, doi: 10.1016/j.asoc.2024.111728.
H. Wang, L. Li, H. Ye, and W. Zhao, “Enhancing MPPT efficiency in PV systems under partial
shading: A hybrid POA&PO approach for rapid and accurate energy harvesting,” International
Journal of Electrical Power & Energy Systems, vol. 162, p. 110260, Nov. 2024, doi: 10.1016/j.
ijepes.2024.110260.
L. F. Giraldo, J. F. Gaviria, M. I. Torres, C. Alonso, and M. Bressan, “Deep reinforcement learning using
deep-Q-network for Global Maximum Power Point tracking: Design and experiments in real photovoltaic
systems,” Heliyon, vol. 10, no. 21, p. e37974, Nov. 15, 2024, doi: 10.1016/j.heliyon.2024.e37974.
R. Celikel, M. Yilmaz, and A. Gundogdu, “Improved voltage scanning algorithm based MPPT
algorithm for PV systems under partial shading conduction,” Heliyon, vol. 10, no. 20, p. e39382, Oct.
, 2024, doi: 10.1016/j.heliyon.2024.e39382.
A. Chellakhi and S. El Beid, “High-efficiency MPPT strategy for PV Systems: Ripple-free precision
with comprehensive simulation and experimental validation,” Results in Engineering, vol. 24, p.
, Dec. 2024, doi: 10.1016/j.rineng.2024.103230.
X. Zhang and P. Yang, “Maximum Power Point Tracking Technology for PV Systems: Current Status
and Future Prospects,” Energy Engineering, Jul. 26, 2024, doi: 10.1080/01998595.2024.2336067.
