Issue |
E3S Web Conf.
Volume 551, 2024
International Conference on Electronics, Engineering Physics and Earth Science (EEPES 2024)
|
|
---|---|---|
Article Number | 02002 | |
Number of page(s) | 8 | |
Section | Renewable Energy and Green Technologies | |
DOI | https://doi.org/10.1051/e3sconf/202455102002 | |
Published online | 17 July 2024 |
Knowledge discovery from energy consumption data
1 Democritus University of Thrace, Department of Physics, 64003 Kavala, Greece
2 Hellenic Electricity Distribution Network Operator S.A., Kavala area, Greece
* Corresponding author: ifantidi@physics.duth.gr
The acquisition of information and thus, the knowledgeextraction from large databases, is a constantly developing modernscientific field, and a particularly important aspect of InformationTechnology. Different techniques and methodologies have been applied incombination with different types of data for obtaining the optimal result.This paper is a continuation of the effort to discover knowledge, in theform of correlations, from data concerning electricity consumption. Theinnovative part of this attempt is, the way that data was associated withtime, and moreover, the combination of the used methods. Specifically,analytical consumption data was used, which were taken at a frequency ofhalf an hour, throughout the year 2023. This consumption, which covers anentire city, concerning the indications of the distribution transformersfound in different areas of the city of Kavala, in Greece. The data, wasfurther combined with the time subdivisions of the whole year with theaim, to draw conclusions about the variation and association ofconsumption in relation to the hours, days and seasons of the year. In orderto carry out the process, both statistical methods, such as factor analysis,normalization, and data mining techniques, such as cluster analysis wereimplemented. The final conclusion of the above process is that the methodsused cooperate perfectly with each other. Furthermore, the analysis revealsthat consumption is greatly influenced by certain periods of time during theyear and this result seems strongly reasonable.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.