PREDICTIVE MODELING OF SOLAR PHOTOVOLTAIC POWER GENERATION USING MACHINE LEARNING

Date

2024-1-24

Author

Qureshi, Huzaifa Saleh

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

60
views

0
downloads

Cite This

As machine learning popularity is increasing, every field of life is incorporating machine learning techniques into their operations because of their robustness, efficiency, and everevolving features. Considering this, most European countries are emphasizing Weather Intelligence for Renewable Energies (WIRE). It is believed that there is a lot of potential for machine learning to improve the percentage of photovoltaic energy mix into grid systems with accurate short-term generation predictions. In this thesis work, the island of Cyprus (as a large area) with ten sub-locations is selected to build a photovoltaic power generation predictive model based on machine learning. For every location, fifteen different variations of PV modules are incorporated into the hourly PVPG predictive model. METU NCC’s 1MW PV power plant is considered as the base model, with some variations related to each location. For that, multiple regression models are tested with only necessary features, selected on the basis of different analyses. The Random Forest model produced the best evaluative results, 1.062 kW, 2.193 kW, 5.311 kW2, and 99.9% for MAE, RMSE, MSE and R2 respectively. This predictive model can be used by system designers, power companies, and policy makers to optimize the location and module of PV for maximum electricity generation by solar PV systems. The predictive model is also tested on unseen data to verify its accuracy. Moreover, the evaluative results are also presented in comparison with the existing multilocational studies.

Subject Keywords

PVPG prediction, Machine Learning, Solar photovoltaic power, Random Forest regression

URI

https://hdl.handle.net/11511/108876

Collections

Northern Cyprus Campus, Thesis