Details

Uporaba nenadzorovanega učenja za segmentacijo odjemalcev pri načrtovanju baterijskih hranilnikov
ID Trobevšek, Valentin (Author), ID Žlindra, Enej (Author), ID Meža, Matej (Author), ID Humar, Iztok (Author)

.pdfPDF - Presentation file, Download (873,66 KB)
MD5: 355E7A92D5DF9846BF3B3962D8E4B394
URLURL - Source URL, Visit https://erk.fe.uni-lj.si/2026/papers/trobevsek(uporaba_nenadzorovanega).pdf This link opens in a new window

Language:Slovenian
Keywords:nenadzorovano učenje, segmentacija odjemalcev, baterijski hranilniki energije
Typology:1.08 - Published Scientific Conference Contribution
Organization:FE - Faculty of Electrical Engineering
Publication status:Published
Year:2026
Number of pages:Str. 250-255
PID:20.500.12556/RUL-190815 This link opens in a new window
UDC:004.855:621.314:620.9
ISSN on article:2591-0442
COBISS.SI-ID:292926979 This link opens in a new window
Publication date in RUL:04.11.2026
Views:58
Downloads:20
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Record is a part of a proceedings

Title:Zbornik petintridesete mednarodne Elektrotehniške in računalniške konference ERK 2026
COBISS.SI-ID:292311811 This link opens in a new window

Record is a part of a journal

Title:Zbornik ... mednarodne Elektrotehniške in računalniške konference
Publisher:Slovenska sekcija IEEE, Fakulteta za elektrotehniko
ISSN:2591-0442
COBISS.SI-ID:291620352 This link opens in a new window

Secondary language

Language:English
Title:Unsupervised learning for customer segmentation in battery storage planning
Abstract:
When calculating custom energy savings for a consumer, inputting a detailed consumption history can become a problem. Instead, we can put the user into a class based on more easily obtainable broader information and use pre-set data for that class. We tackled the issue of creating classes by clustering different consumers based on their yearly power consumption timeseries using KMeans. Then we tested how accurately we can sort a consumer into its correct class based on different parameters (or features) using different methods. We found the best combination of features to be the quarterly maximum power consumption and the total energy consumption of each month. The best single feature was the total energy consumption of each month. The best method turned out to be Random Forest. This allows the user to input less data while at the cost of lower accuracy.

Keywords:unsupervised learning, customer segmentation, battery energy storage systems

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back