University of Tehran Journal of Solar Energy Research 2588-3097 8 4 2023 10 01 Smart Maintenance with Regression Analysis for Efficiency Improvement in Photovoltaic Energy Systems 1663 1679 95014 10.22059/jser.2023.363200.1335 EN İlker Ay Department of Alternative Energy Resources Technology Program, Hacettepe Ankara Chamber of Industry 1st Organized Industrial Zone Vocational School, Hacettepe University, Ankara, Türkiye Murat Kademli Department of Alternative Energy Resources Technology Program, Hacettepe Ankara Chamber of Industry 1st Organized Industrial Zone Vocational School, Hacettepe University, Ankara, Türkiye Serkan Savaş Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Kırıkkale University, Kırıkkale, Türkiye. Sotirios Karellas National Technical University of Athens, Athens, Greece Angelos Markopoulos National Technical University of Athens, Athens, Greece Christina-Stavroula Hatzilau National Technical University of Athens, Athens, Greece Philip Devlin North West Regional College, Londonderry, Northern Ireland Hüseyin Duşbudak Sincan District Directorate of National Education, Ankara, Türkiye Ali Samet Arslan Impektra IT Software, Ankara, Türkiye Mustafa Koç Yenikent Ahmet Çiçek Vocational and Technical Anatolian High School, Ankara, Türkiye 0000-0002-8994-4942 Kazım Duraklar Private Ankara Chamber of Industry Technical College Vocational and Technical Anatolian High School, Ankara, Türkiye Kamil Sunal Ankara Chamber of Industry 1st Organized Industrial Zone Management, Ankara, Türkiye Mathieu Mehmet Ozer Oryx-Data Incubator EURL, Paris, France Journal Article 2023 08 04 This research had the overarching goal of optimizing maintenance intervals and reducing the maintenance workload by enhancing accessibility for individuals lacking technical expertise in the upkeep of photovoltaic systems, with a particular focus on rooftop applications. The study achieved this objective by employing a linear regression algorithm to analyse climatic parameters such as wind speed, humidity, ambient temperature, and light intensity, collected from the installation site of a photovoltaic solar energy system. Simultaneously, the current and voltage values obtained from the system were also examined. This analysis not only facilitated the determination of power generation within the system but also enabled real-time detection of potential issues such as pollution, shadowing, bypass, and panel faults on the solar panels. Additionally, an artificial intelligence-supported interface was developed within the study, attributing any decline in power generation to specific causes and facilitating prompt intervention to rectify malfunctions, thereby ensuring more efficient system operation. https://jser.ut.ac.ir/article_95014_0059e2a9b852144694e0b205c13529eb.pdf