Data-driven prediction for the number of distribution network users experiencing typhoon power outages

Typhoons have substantial impacts on power systems and may result in major power outages for distribution network users. Developing prediction models for the number of users going through typhoon power outages is a high priority to support restoration planning. This study proposes a data-driven mode...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IET generation, transmission & distribution Jg. 14; H. 24; S. 5844 - 5850
Hauptverfasser:	Hou, Hui, Yu, Jufang, Geng, Hao, Zhu, Ling, Li, Min, Huang, Yong, Li, Xianqiang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	The Institution of Engineering and Technology 18.12.2020
Schlagworte:	classification data‐driven model data‐driven prediction decision trees disasters distribution network users distribution networks geographical factors gradient boosting decision tree gradient methods linear regression machine learning regression algorithm meteorological factors pattern classification power engineering computing power grid factors power grids power system planning power system reliability power systems random forest random forests regression analysis regression tree restoration planning Special Issue: Advanced Data-Analytics for Power System Operation, Control and Enhanced Situational Awareness storms support vector machines support vector regression typhoon power outages regression tree distribution networks regression analysis linear regression random forests meteorological factors random forest power system reliability typhoon power outages power grids gradient methods geographical factors power grid factors power system planning pattern classification support vector machines distribution network users machine learning regression algorithm disasters data-driven model restoration planning classification power engineering computing gradient boosting decision tree support vector regression decision trees power systems storms data-driven prediction
ISSN:	1751-8687, 1751-8695
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!