Under partial shading conditions, photovoltaic (PV) modules in a solar array experience varying irradiance. A Global Maximum (GM) and multiple Local Maximums (LMs) can originate on the Power-Voltage (P-V) curve under nonuniform irradiance conditions. There are many maximum power point tracking (MPPT) algorithms developed to detect the true maximum power point (MPP) of a PV array. However, in the real-world environment, limited samples of power-voltage (P-V) data might be available to quickly and accurately predict the position of the global maximum point. Since the change of environmental conditions are dynamic, limited time is available to locate the global peak. Machine learning and deep learning algorithms can be employed to overcome the above-mentioned problems by enabling the current MPPT algorithms to work faster and achieve better performance. These techniques are used to classify P-V curve type and predict the range within which the maximum power point (MPP) is most likely to be present so that the MPPT algorithm can be applied within a smaller range detected by the machine learning or deep learning algorithms. Among various tested algorithms, the best working algorithms are compared and presented in this work.
","abstract_html":"<p>Under partial shading conditions, photovoltaic (PV) modules in a solar array experience varying irradiance. A Global Maximum (GM) and multiple Local Maximums (LMs) can originate on the Power-Voltage (P-V) curve under nonuniform irradiance conditions. There are many maximum power point tracking (MPPT) algorithms developed to detect the true maximum power point (MPP) of a PV array. However, in the real-world environment, limited samples of power-voltage (P-V) data might be available to quickly and accurately predict the position of the global maximum point. Since the change of environmental conditions are dynamic, limited time is available to locate the global peak. Machine learning and deep learning algorithms can be employed to overcome the above-mentioned problems by enabling the current MPPT algorithms to work faster and achieve better performance. These techniques are used to classify P-V curve type and predict the range within which the maximum power point (MPP) is most likely to be present so that the MPPT algorithm can be applied within a smaller range detected by the machine learning or deep learning algorithms. Among various tested algorithms, the best working algorithms are compared and presented in this work.</p>","abstract_has_math":false,"creators":["Inamdar, Sumedha"],"institution":null,"degree_name":"Master of Science in Computer Science (MSCS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Dr. Yong Shi","Dr. Coskun Cetinkaya","Dr. Kun Suo"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-12-20T08:00:00Z","date_published":"2020-12-20T08:00:00Z","updated_at":"2026-07-24T02:43:42Z","subjects":["maximum power point tracking","temporal convolutional network","convolutional neural network","random forest","Data Science","Power and Energy"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.kennesaw.edu/cs_etd/39","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Yong Shi","Dr. Coskun Cetinkaya","Dr. Kun Suo"]},{"key":"dc:creator","label":"Author","values":["Inamdar, Sumedha"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-12-19T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science (MSCS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["maximum power point tracking","temporal convolutional network","convolutional neural network","random forest","Data Science","Power and Energy"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.kennesaw.edu/cs_etd/39"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Under partial shading conditions, photovoltaic (PV) modules in a solar array experience varying irradiance. A Global Maximum (GM) and multiple Local Maximums (LMs) can originate on the Power-Voltage (P-V) curve under nonuniform irradiance conditions. There are many maximum power point tracking (MPPT) algorithms developed to detect the true maximum power point (MPP) of a PV array. However, in the real-world environment, limited samples of power-voltage (P-V) data might be available to quickly and accurately predict the position of the global maximum point. Since the change of environmental conditions are dynamic, limited time is available to locate the global peak. Machine learning and deep learning algorithms can be employed to overcome the above-mentioned problems by enabling the current MPPT algorithms to work faster and achieve better performance. These techniques are used to classify P-V curve type and predict the range within which the maximum power point (MPP) is most likely to be present so that the MPPT algorithm can be applied within a smaller range detected by the machine learning or deep learning algorithms. Among various tested algorithms, the best working algorithms are compared and presented in this work.
"]},{"key":"dc:title","label":"Title","values":["Improving the Maximum Power Point Tracking Efficiency of Photovoltaic Arrays via Machine Learning and Deep Learning"]}]}],"canonical_facts":{"dc:contributor":["Dr. Yong Shi","Dr. Coskun Cetinkaya","Dr. Kun Suo"],"dc:creator":["Inamdar, Sumedha"],"dc:date.available":["2025-12-19T08:00:00Z"],"dc:description.abstract":["Under partial shading conditions, photovoltaic (PV) modules in a solar array experience varying irradiance. A Global Maximum (GM) and multiple Local Maximums (LMs) can originate on the Power-Voltage (P-V) curve under nonuniform irradiance conditions. There are many maximum power point tracking (MPPT) algorithms developed to detect the true maximum power point (MPP) of a PV array. However, in the real-world environment, limited samples of power-voltage (P-V) data might be available to quickly and accurately predict the position of the global maximum point. Since the change of environmental conditions are dynamic, limited time is available to locate the global peak. Machine learning and deep learning algorithms can be employed to overcome the above-mentioned problems by enabling the current MPPT algorithms to work faster and achieve better performance. These techniques are used to classify P-V curve type and predict the range within which the maximum power point (MPP) is most likely to be present so that the MPPT algorithm can be applied within a smaller range detected by the machine learning or deep learning algorithms. Among various tested algorithms, the best working algorithms are compared and presented in this work.
"],"dc:identifier":["https://digitalcommons.kennesaw.edu/cs_etd/39"],"dc:subject":["maximum power point tracking","temporal convolutional network","convolutional neural network","random forest","Data Science","Power and Energy"],"dc:title":["Improving the Maximum Power Point Tracking Efficiency of Photovoltaic Arrays via Machine Learning and Deep Learning"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MSCS)"]},"updated_at":"2026-07-24T02:43:42Z"}