Dr. Norazlan Hashim is a Senior Lecturer at the School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA (UiTM), Malaysia, where he has been serving since 2008. He holds a Ph.D. in Electrical Engineering from Universiti Teknologi Malaysia (2022), an M.Eng in Electrical Energy and Power Systems from Universiti Malaya (2007), and a B.Eng in Electrical Engineering from Universiti Malaya (2001). His current research focuses on Maximum Power Point Tracking (MPPT), Power Electronic Converters, Artificial Intelligence, Photovoltaic Systems, and Educational Technology. He has led numerous research projects as Project Leader, including FRGS and Lestari grants, and has supervised multiple Ph.D. and Master's students. An active researcher with a Scopus H-index of 10 and over 300 Scopus citations, he has published extensively in WoS/SCOPUS-indexed journals and conference proceedings. He has received numerous awards including the Anugerah Perkhidmatan Cemerlang UiTM (2012, 2022), multiple Best Paper Awards, and medals for research innovations. He also serves as a reviewer for various international journals and conferences and has held significant administrative roles at UiTM, including Power Discipline Coordinator and Entrepreneurship Development Coordinator

Abstract Title: AI-Driven Maximum Power Point Tracking in Photovoltaic Systems Abstract:This guest lecture explores the application of nature-inspired AI-based metaheuristic optimization techniques for Maximum Power Point Tracking (MPPT) in photovoltaic (PV) systems. It begins with the fundamental operating characteristics of PV systems and the role of MPPT in maximizing energy extraction under varying irradiance and temperature conditions. Conventional MPPT techniques, including Perturb and Observe (P&O) and Incremental Conductance (INC), are introduced, with particular emphasis on their limitations under partial shading, where multiple local maximum power points (LMPPs) and a single global maximum power point (GMPP) may occur. Metaheuristic techniques are then examined as alternative approaches for identifying the GMPP through exploration-exploitation mechanisms in nonlinear and multimodal search spaces. As numerous new optimization methods continue to be introduced, selecting an appropriate algorithm for MPPT has become an increasingly important challenge, particularly because no single method is universally superior across all applications. The lecture therefore focuses on the key characteristics and evaluation criteria of suitable AI-based MPPT methods, including reliable GMPP identification, fast convergence, low computational burden, stable search behaviour, robustness under varying operating conditions, and suitability for real-time implementation. The stochastic nature of metaheuristic algorithms is also addressed, together with the importance of statistically reliable evaluation over multiple independent trials rather than reliance on a single successful outcome. The trade-offs among these criteria and their implications for practical deployment are further discussed. Overall, the lecture provides a systematic framework for understanding, evaluating, and selecting nature-inspired AI-based metaheuristic optimization techniques for efficient, reliable, and practical MPPT applications in modern PV energy systems. Keywords: Artificial Intelligence, Maximum Power Point Tracking, Photovoltaic Systems, Global Maximum Power Point, Metaheuristic Optimization, Partial Shading Conditions