| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Napovedovanje obremenitvenega profila električne energije s pomočjo metod strojnega učenja : magistrsko delo
Authors:ID Tepej, Urban (Author)
ID Beković, Miloš (Mentor) More about this mentor... New window
ID Černezel, Martin (Comentor)
Files:.pdf MAG_Tepej_Urban_2026.pdf (4,33 MB)
MD5: 81A9E8D28E542E2E94723E1428D0BC78
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Zanesljivo napovedovanje obremenitvenega profila električne energije je ključno za učinkovito delovanje elektroenergetskega sistema. V magistrskem delu obravnavamo kratkoročno napovedovanje z uporabo podatkovno vodenih pristopov. Razvit je model, ki temelji na skrbno izbranih značilnostih, pri čemer poseben poudarek namenjamo preprečevanju uhajanja informacij (data leakage) in zagotavljanju t. i. future-safe pristopa. Analizirali smo vpliv časovnih, zgodovinskih in vremenskih spremenljivk na natančnost napovedi. Model smo ovrednotili z metrikami RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) in MAPE (Mean Absolute Percentage Error). Rezultati potrjujejo, da ustrezna izbira značilnosti bistveno izboljša zanesljivost napovedi.
Keywords:napoved obremenitvenega profila, časovne vrste, strojno učenje, XGBoost, RMSE, MAE, MAPE
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[U. Tepej]
Year of publishing:2026
Number of pages:1 spletni vir (1 datoteka PDF (XV, 83 str.))
PID:20.500.12556/DKUM-97820 New window
UDC:611.311.15-047.72:004.85(043.2)
COBISS.SI-ID:282197507 New window
Publication date in DKUM:29.05.2026
Views:162
Downloads:18
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:16.04.2026

Secondary language

Language:English
Title:Forecasting of electric load profiles using machine learning methods
Abstract:Reliable forecasting of electrical load profiles is essential for the efficient operation of power systems. This master’s thesis addresses short-term load forecasting using data-driven approaches. A model is developed based on carefully selected features, with particular emphasis on preventing data leakage and ensuring a future-safe methodology. The impact of temporal, historical, and weather-related variables on forecasting accuracy is analyzed. The model is evaluated using the metrics RMSE (Root Mean Squared Error), MAE (Mean Absolute Error), and MAPE (Mean Absolute Percentage Error). The results confirm that appropriate feature selection significantly improves forecasting reliability.
Keywords:forecast of load profile, time series, machine learning, XGBoost, RMSE, MAE, MAPE


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica