15-minutna rezolucija prognoze gubitaka u prijenosu električne energije metodom strojnog učenja

undergraduate thesis

• Title (english): 15-minute resolution of the forecast of losses in the transmission of electricity by the method of machine learning
• Author: Andro Radičević
• Mentor: Dubravko Sabolić (mentor)
• Committee member: Dubravko Sabolić (predsjednik povjerenstva)
• Committee member: Božidar Filipović-Grčić (član povjerenstva)
• Committee member: Bojan Franc (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu primjenjuju se postupci strojnog učenja na problem predviđanja gubitaka u
prijenosnoj mreži električne energije Republike Hrvatske. Obrazlaže se čitav postupak
pročišćavanja i filtriranja sirovih podataka, izrade značajki i primjene tri algoritma strojnog
učenja: SGD, ElasticNet i Lasso. Rezultati ova tri algoritma se uspoređuju, te se istražuje i
promjena preciznosti ovisno o tome koliko unaprijed se vrši predviđanje. Također je i
priložena diskusija o rezultatima te prijedlozi poboljšanja korištenog procesa.

Abstract (english)

In this paper the process of machine learning is applied to the problem of forecasting losses
in electric transmission grid of the Republic of Croatia. The whole process of cleaning and
filtering raw data, feature engineering and application of three machine learning algorithms
SGD, ElasticNet and Lasso is explained. The results of three algorithms are compared, and
the changes in accuracy due to forecasting further into future are analysed. The discussion
about results and suggestions for further improvements of the process are also included.

• Keywords: znanost o podatcima; strojno učenje; prijenosna mreža; predviđanje; python
• Keywords (english): data science; machine learning; transmission network; forecasting; python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:804825
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 11:06:45