Optimizing Solar Panel Tilt Using Machine Learning Techniques
| Autor: | Sakshi Kulkarni, Laveen Chandwani, Suhas Kakade, Rohan S. Kulkarni, Kshitij Duraphe, Sakshi Jaiswal |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Boosting (machine learning)
Maximum power principle Computer science business.industry Photovoltaic system ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Perceptron Machine learning computer.software_genre Renewable energy Power (physics) Electricity generation Artificial intelligence Gradient boosting business computer |
| Zdroj: | 2021 3rd Global Power, Energy and Communication Conference (GPECOM). |
| DOI: | 10.1109/gpecom52585.2021.9587892 |
| Popis: | As the world seeks to produce energy from renewable sources, the number of photovoltaic installations has increased. With this, there arises a need for maximizing power output. Higher availability of data and computational units have helped machine learning algorithms to make predictions faster. The need to predict the optimum tilt angle for maximum power generation is essential. Choosing an optimum angle of inclination of a solar panel often involves theoretical calculations which have interdependent and location specific variables. This paper presents a machine learning model that takes other environmental weather dependent factors and changing seasons across the year to compare and presents a model that can estimate the inclination angle for optimum generation of power by the solar array. We use algorithms like gradient boosting, extreme gradient boosting and multilayer perceptrons to establish a relationship between inclination angle and power generation. With our system, we predict an increase of 8.44%-11.8% with the predicted optimised angle. Our models predict an optimized inclination with a variation of 1.5% in the final value. We also present an analytical model which has been used to corroborate the results obtained from the machine learning models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|