Principal Component Analysis and Artificial Intelligence Approaches for Solar Photovoltaic Power Forecasting

Souhaila Chahboun and Mohamed Maaroufi

A chapter in Advances in Principal Component Analysis from IntechOpen

Abstract: In recent years, renewable energy sources have experienced remarkable growth. However, their spatial and temporal diversity makes their large-scale integration into the current power grids difficult, as the balance between the electricity output and the consumption must be maintained at all times. Therefore, it is important to focus on the resources forecast to enhance the integration of renewable energy sources, such as solar in this study. In this article, a comparative analysis of two main machine learning methods was conducted for the prediction of the hourly photovoltaic output power. Furthermore, since various factors, such as climate variables, can impact the solar photovoltaic power and complicate the prediction process, the principal component analysis was employed to investigate the interactions between the multiple predictors and minimize the dimensionality of the datasets. The prevalent factors were then used in the predictive models as inputs. This field research is very crucial because the higher the prediction accuracy, the greater the profit for energy dealers and the lower the costs for customers.

Keywords: photovoltaic power; machine learning; principal component analysis; prediction (search for similar items in EconPapers)
JEL-codes: C10 (search for similar items in EconPapers)
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.intechopen.com/chapters/81229 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ito:pchaps:256516

DOI: 10.5772/intechopen.102925

Access Statistics for this chapter

More chapters in Chapters from IntechOpen
Bibliographic data for series maintained by Slobodan Momcilovic ().