A Study on the Development of Machine-Learning Based Load Transfer Detection Algorithm for Distribution Planning

Jun-Hyeok Kim, Byung-Sung Lee and Chul-Hwan Kim
Additional contact information
Jun-Hyeok Kim: Department of Electrical and Electronic Engineering, Sungkyunkwan University, Suwon 16419, Korea
Byung-Sung Lee: Smart Power Distribution Laboratory, Korea Electric Power Corporation Research Institute, Daejeon 34056, Korea
Chul-Hwan Kim: Department of Electrical and Electronic Engineering, Sungkyunkwan University, Suwon 16419, Korea

Energies, 2020, vol. 13, issue 17, 1-12

Abstract: Distribution planning refers to the act of estimating the risks of distribution systems that may arise in the future and establishing investment plans to cope with them. Forecasted loads are one of the most typical variables used to analyze the risk of the distribution system, thus the efficiency of distribution planning may vary depending on its accuracy. For these reasons, a lot of studies are also being conducted to perform load prediction by incorporating the latest methods, such as machine learning (ML). However, the unchangeable fact is that no matter what prediction method is used, the accuracy and reliability of the predicted load can vary depending on the reliability of the data used. In particular, the detection of temporary load increases, due to load transfer that can occur frequently in the distribution system are essential for securing high-quality data. Therefore, in this study, a LSTM (Long Short-Term Memory) based load transfer detection model was proposed, and the appropriateness and reliability of the proposed method were analyzed by comparing actual planned load transfer data with the estimated load transfer results from the proposed model. It was also shown that the proposed model can improve the efficiency and reliability of the distribution planning by reasonably removing load variations, due to load transfer.

Keywords: load transfer; machine-learning; distribution planning; peak load (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1996-1073/13/17/4358/pdf (application/pdf)
https://www.mdpi.com/1996-1073/13/17/4358/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:13:y:2020:i:17:p:4358-:d:403158

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().