An Analysis of Data Quality and Time Resolution in Clustering Based on Polish Prosumer Real World Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10260636" target="_blank" >RIV/61989100:27240/25:10260636 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11169161" target="_blank" >https://ieeexplore.ieee.org/document/11169161</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EEEIC/ICPSEurope64998.2025.11169161" target="_blank" >10.1109/EEEIC/ICPSEurope64998.2025.11169161</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Analysis of Data Quality and Time Resolution in Clustering Based on Polish Prosumer Real World Data

Popis výsledku v původním jazyce

This study investigates the impact of data preprocessing techniques on the reliability and clustering outcomes of real-world electricity generation and consumption data from prosumers with PV installation, which are located in Poland. Utilizing a dataset spanning 2023, collected at threeminute intervals, key challenges such as missing data, inconsistencies, and quality issues were addressed. Missing measurements were handled through linear interpolation, and a novel time-difference metric was introduced to identify and exclude days with substantial data gaps. Weather data from an open-source API was integrated and aligned through timeaggregation methods. Clustering analyses, employing k-means, were conducted on datasets with 15 -minute and hourly resolutions, with the optimal number of clusters determined using the elbow method. Results highlighted discrepancies in energy records, underscoring the importance of preprocessing for enhanced data reliability and analysis. This work demonstrates that preprocessing steps significantly influence the clustering process and its outcomes, offering insights for improving data-driven energy management strategies.

Název v anglickém jazyce

An Analysis of Data Quality and Time Resolution in Clustering Based on Polish Prosumer Real World Data

Popis výsledku anglicky

This study investigates the impact of data preprocessing techniques on the reliability and clustering outcomes of real-world electricity generation and consumption data from prosumers with PV installation, which are located in Poland. Utilizing a dataset spanning 2023, collected at threeminute intervals, key challenges such as missing data, inconsistencies, and quality issues were addressed. Missing measurements were handled through linear interpolation, and a novel time-difference metric was introduced to identify and exclude days with substantial data gaps. Weather data from an open-source API was integrated and aligned through timeaggregation methods. Clustering analyses, employing k-means, were conducted on datasets with 15 -minute and hourly resolutions, with the optimal number of clusters determined using the elbow method. Results highlighted discrepancies in energy records, underscoring the importance of preprocessing for enhanced data reliability and analysis. This work demonstrates that preprocessing steps significantly influence the clustering process and its outcomes, offering insights for improving data-driven energy management strategies.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 IEEE International Conference on Environment and Electrical Engineering and 2025 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2025 : conference proceedings : 15-18 July 2025, Chania, Crete-Greece

ISBN

979-8-3315-9516-6

ISSN

2994-9440

e-ISSN

2994-9467

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Chania

Datum konání akce

15. 7. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—