Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
PREDICTIVE MODELING OF SOLAR PHOTOVOLTAIC POWER GENERATION USING MACHINE LEARNING
Download
Huzaifa_MSc_Thesis.pdf
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
160
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
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
H. S. Qureshi, “PREDICTIVE MODELING OF SOLAR PHOTOVOLTAIC POWER GENERATION USING MACHINE LEARNING,” M.S. - Master of Science, Middle East Technical University, 2024.