Modeling Power Output of Horizontal Solar Panels Using Multivariate Linear Regression and Random Forest Machine Learning

Abstract

United States Air Force energy resiliency goals are aimed to increase renewable energy implementation. Researchers at the Air Force Institute of Technology distributed 37 photovoltaic test systems around the world. This research uses multivariate linear regression and random forest machine learning to determine which modeling technique will better predict power output for horizontal solar panels. If power output of a horizontal solar panel can be predicted using available weather data, then assessing the possibility of utilizing horizontal panels in any global location becomes possible. The linear model accounted for 56.2 of the variance in a validation dataset. The random forest model accounted for 65.8 variance. The most important variable in reducing the random forest model mean squared error was the month of the year, closely followed by cloud ceiling. Wind speed was the least important variable in reducing model error. More predictor variables are needed to increase predictability of horizontal solar panel power output if irradiation is not present as an input.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 21, 2019
Accession Number
AD1077683

Entities

People

  • Christil K. Pasion

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Cloud Cover
  • Computer Programming
  • Data Mining
  • Data Science
  • Department Of Defense
  • Energy
  • Information Science
  • Machine Learning
  • Meteorology
  • Renewable Energy
  • Solar Cells
  • Solar Energy
  • Solar Panels
  • Solar Radiation
  • United States
  • United States Government

Readers

  • Atmospheric Remote Sensing.
  • Neural Network Machine Learning.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference