HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Master Thesis

Automatisation de l’extraction et de l’analyse de données électriques de centrales photovoltaïques

Abstract : This internship took place as part of my Master 1 in Information Systems Management at Grenoble IAE. It lasted 5 months (from April 6, 2021 to August 30, 2021) and took place within Ener-Pacte, a small company of 15 people which secures the photovoltaic assets of private customers. My objective during this internship was to automate two processes that are essential for the company: the extraction and the analysis of electrical data from photovoltaic power plants. The operational staff needs this data to observe the evolution of the power plants though years to quantify the possible production losses to act accordingly. I have developed Python programs that can extract data over several years in a few minutes automatically. This would have been very time consuming to do it "by hand" (even impossible for some web platforms). Once these data are extracted, I developed an algorithm that analyzes the performance of the solar plants. It is based on the Prophet package and detects trends, trend breaks, possible seasonality effects and allows to predict the future performance of the plants. This analysis method has the advantage of being automatic, objective and predicts future performance more accurately than a simple linear regression that was used until now (~25% more accurate on non-linear data, and equivalent on linear data). My programs allow operational staff to avoid spending time on long and tedious extraction tasks and analyze the data automatically and more accurately.
Document type :
Master Thesis
Complete list of metadata

https://dumas.ccsd.cnrs.fr/dumas-03546607
Contributor : Grenoble Iae Connect in order to contact the contributor
Submitted on : Friday, January 28, 2022 - 8:48:00 AM
Last modification on : Sunday, March 20, 2022 - 3:28:13 AM
Long-term archiving on: : Friday, April 29, 2022 - 6:16:26 PM

File

EL_MOURABIT_IZEM_memoire.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License

Identifiers

  • HAL Id : dumas-03546607, version 1

Citation

Izem El Mourabit. Automatisation de l’extraction et de l’analyse de données électriques de centrales photovoltaïques. Gestion et management. 2021. ⟨dumas-03546607⟩

Share

Metrics

Record views

24

Files downloads

13