Machine Learning for Predicting Photovoltaic Power Generation: an Application on a University Campus

Fabio Lopez, Markus Mock, Abraham Davila

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes the application of machine learning in an energy management system set up to monitor the use and generation of energy at a university campus. We explain how we built precise forecasting models for producing photovoltaic energy produced by solar panels at the University of Applied Sciences Landshut, Germany. We describe the practical challenges of dealing with data dropout and erroneous data when working with data from an actual in-production setting outside a simple lab scenario. Applying several data cleaning methods based on statistical methods, we obtained models that allow us to predict electrical energy produced by the solar panels with a precision of 0.97 as measured by the R2 metric. More importantly, the process described to arrive at this result, more than the result per se, serves as a real-world example of applying data science and machine learning methodology in an in-production setting.

Original languageEnglish
Title of host publicationProceedings - 2023 49th Latin American Computing Conference, CLEI 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350318876
DOIs
StatePublished - 2023
Event49th Latin American Computing Conference, CLEI 2023 - La Paz, Bolivia, Plurinational State of
Duration: 16 Oct 202320 Oct 2023

Publication series

NameProceedings - 2023 49th Latin American Computing Conference, CLEI 2023

Conference

Conference49th Latin American Computing Conference, CLEI 2023
Country/TerritoryBolivia, Plurinational State of
CityLa Paz
Period16/10/2320/10/23

Keywords

  • energy forecasting
  • machine learning
  • regression models
  • solar energy

Fingerprint

Dive into the research topics of 'Machine Learning for Predicting Photovoltaic Power Generation: an Application on a University Campus'. Together they form a unique fingerprint.

Cite this