CROSS LABORATORY 

Jinesh Mohan

Working-adult program, Energy Course, D3 student

​

Photovoltaic system power modeling utilizing transfer Learning

With the rapid adoption of photovoltaic (PV) systems and their integration into the electricity grid, it has become a necessity to accurately forecast the photovoltaic output at their intended site of use for effective energy management to mitigate the instability of the grid caused by the intermittency of solar power. However, the scarcity of data in new installations is a big impediment to effective energy management. In the master's research, a solar power forecast system utilizing inductive transfer learning from a pre-trained machine learning model that can predict solar irradiance was proposed and analyzed. The doctoral research aims to investigate the effect of cloud cover on forecast accuracy and address seasonal variations by clustering through case studies of Hyderabad Railway Station and Cochin International Airport Limited. See figure below for overall concept of the research in general.