Date of Submission
Fall 12-20-2020
Degree Type
Thesis
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
Committee Chair/First Advisor
Dr. Yong Shi
Track
Big Data
Chair
Dr. Coskun Cetinkaya
Committee Member
Dr. Kun Suo
Committee Member
Dr. Sumit Chakravarty
Committee Member
Dr. Sandip Das
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.