University of TehranJournal of Solar Energy Research2588-309711220260401Optimising Photovoltaic Power Output Using Hybrid Deep Reinforcement Learning and Real-Time Environmental Adaptation2923293310659910.22059/jser.2026.410130.1708ENAhmedAl-MaqsoosiCenter of Computer and Informatics, Wasit University, Wasit, IraqHassanAl-BudairiCenter of Computer and Informatics, Wasit University, Wasit, IraqAbdurrahimAkgündoğduDepartment of Electrical and Electronics Engineering at the Faculty of Engineering, Istanbul University-Cerrahpaşa, TurkeyHananAl YodaoiMinistry of Trade, IraqJournal Article20260127Development of Artificial Intelligence (AI) systems has transformed the management of renewable energy by resolving long-standing challenges in efficiency, resilience, and responsiveness. Photovoltaic (PV) power generation, highly sensitive to environmental fluctuations, can particularly benefit from AI-based control strategies. This paper proposes a hybrid AI architecture combining model-free Deep Reinforcement Learning (DRL) using Deep Q-Networks (DQN) with Long Short-Term Memory (LSTM) networks to enhance Maximum Power Point Tracking (MPPT) under dynamic conditions including rapid irradiance, temperature, humidity variations, and partial shading. The system employs real-time environmental sensor inputs, namely solar irradiance, ambient and module temperature, relative humidity, and shading indices, as the DQN state. The LSTM processes historical sequences to predict near-future power trends and enable proactive MPPT decisions. Implementation on a low-cost, energy-efficient Raspberry Pi edge computing platform enables decentralised, low-latency control without cloud dependence, suitable for remote or off-grid applications. A 180-day field validation on a rooftop 5.4 kW PV array demonstrated a 37% reduction in convergence time compared with Perturb and Observe (P&O) and 28% relative to Fuzzy Logic MPPT. The system achieved a 12.4% average increase in daily energy yield, rising to 18.7% under sporadic cloud cover and partial shading in real-world operational scenarios contexts.https://jser.ut.ac.ir/article_106599_f369c281f93315b97eba786899f6a47a.pdfUniversity of TehranJournal of Solar Energy Research2588-309711220260409Numerical Investigation of Time-Dependent Dust Shading Effects on Fixed and Tracking Solar Photovoltaic Arrays2934295210646510.22059/jser.2026.410193.1709ENKudzanayiChitekaDepartment of Mechanical Engineering, University of South Africa, Science Campus, Florida 1710, South AfricaChristopherEnweremaduDepartment of Mechanical Engineering, University of South Africa, Science Campus, Florida 1710, South Africa0000-0002-5455-2500Journal Article20260128The global expansion of solar energy has been met with dust soiling which is a critical performance-limiting factor, especially in dusty climates. The present study proposed a dynamic numerical approach for quantifying the time-dependent effects of dust shading on fixed-tilt, single-axis tracking, and dual-axis tracking PV systems. The approach was to distinguish between direct and diffuse irradiance and account for diurnal and seasonal solar geometry while incorporating angular-dependent shading dynamics. Single-axis and dual-axis trackers achieved daily yields of 5.02 kWh/day and 5.16 kWh/day respectively under a surface-soiling fraction of 32.7% determined from binary image segmentation and pixel-area ratio surpassing the clean fixed-tilt baseline of 4.41 kWh/day. A laboratory validation was used to confirm the ability of model to capture angular-dependent losses. A techno-economic analysis done revealed a trade-off where tracking systems maximise the absolute energy generated. However, fixed-tilt systems delivered superior cost-effectiveness due to lower capital and maintenance requirements. The results revealed the need for a dynamic, time-resolved model to improve optimisation and performance prediction, and guide maintenance strategies in soiling-prone environments.https://jser.ut.ac.ir/article_106465_0d864aeb2cb40fca2d3f1ff6017df349.pdfUniversity of TehranJournal of Solar Energy Research2588-309711220260511Solar Photovoltaic-Based Green Hydrogen in West Africa: Pathways, Potential, and Prospects2953297610684910.22059/jser.2026.408953.1696ENIgnatius KemaOkakwuDepartment of Electrical and Electronics Engineering, Olabisi Onabanjo University, Ago-Iwoye, 120107, NigeriaNajeemAdelakunFederal College of Education, Iwo, Osun StateAyodejiOkubanjoDepartment of Electrical and Electronics Engineering, Olabisi Onabanjo University, Ago-Iwoye, 120107, NigeriaSamsonAyanladeDepartment of Electrical and Electronics Engineering, Olabisi Onabanjo University, Ago-Iwoye, 120107, NigeriaChristianIkeGlobacom Nigeria Limited, 1 Mike Adenuga Close, Victoria Island, Lagos, NigeriaAbrahamAmoleDepartment of Electrical and Electronics Engineering, Bells University of Technology, Ota, NigeriaEtinosaNoma-OsaghaeDepartment of Electrical and Electronics Engineering, Olabisi Onabanjo University, Ago-Iwoye, 120107, NigeriaAyodeleAkinremiDepartment of Electrical and Electronics Engineering, Olabisi Onabanjo University, Ago-Iwoye, 120107, NigeriaJournal Article20251227Solar photovoltaic-based green hydrogen offers a strategic pathway for transitioning West Africa towards a low-carbon and sustainable energy system. This review offers a region-specific evaluation of PV-based hydrogen production and integrating renewable resources, electrolyser technologies, and techno-economic performance into a single framework. The paper reviews the global and regional literature on production pathways, system integration, deployment opportunities, and complementary hydrogen pathways. Results show that Nigeria, Mali, Senegal, and Cape Verde have high potential for competitive hydrogen production with the levelised cost of hydrogen (LCOH) of about USD 2.0-2.6/kg due to their high solar irradiance. Broader analyses indicate costs ranging from USD 3.60-6.70/kg in large-scale systems and small-scale systems ranging over USD 20/kg. Electrolyser efficiencies are 60-85%, and PV capacity factors range from 20-28%, indicating the significance of technology choice and system design. Decentralised PV-electrolysis systems are a viable solution to industrial decarbonisation and expansion of energy access. The review key priorities include hybrid renewable integration, long-term hydrogen storage, lifecycle environmental assessment, and new electrolysis technologies. The result reveals West Africa as a potential low-cost hydrogen site with great potential to contribute to energy security and industrial development.https://jser.ut.ac.ir/article_106849_aaf370eb520e2aa81abdc3f82d9fd708.pdf