Prediktivni modeli potrošnje električne energije

undergraduate thesis

• Author: Josip Bubalo
• Mentor: Hrvoje Pandžić (mentor)
• Committee member: Hrvoje Pandžić (predsjednik povjerenstva)
• Committee member: Mateo Beus (član povjerenstva)
• Committee member: Juraj Havelka (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-02, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je izrada prediktivnih modela strojnog učenja za potrošnju električne energije u kućanstvu. Nakon prikupljanja podataka nad njima je napravljena analiza u kojoj su otklonjene stršeće vrijednosti i popunjene rupe. S kompletiranim podatcima izrađeno je tri vrste modela predviđanja, osnovni baseline modeli, modeli linearne regresije i model slučajne šume. Na kraju, napravljena je usporedba uspješnosti predviđanja te tri vrste modela.

Abstract (english)

The topic of this thesis is the development of predictive machine learning models for household electricity consumption. After collecting the data, an analysis was made, in which outliers were removed and holes were filled. Three types of prediction models were created with the completed data: basic baseline models, linear regression models and random forest models. Finally, a comparison of the prediction performance of those three types of models was made.

• Keywords: Strojno učenje; analiza podataka; predviđanje; Linearna regresija; Random forest
• Keywords (english): Machine learning; data analysis; prediction; Linear regression; Random forest
• Language: croatian
• URN:NBN: urn:nbn:hr:168:334332
• 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: 2024-10-12 20:12:55