Power data mining in smart grid environment

The power grid is the foundation of the development of the national industry. The rational and efficient distribution of power resources plays an important role in economic development. The smart grid is the use of modern network information technology to realize the exchange of data information bet...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of intelligent & fuzzy systems 2021-01, Vol.40 (2), p.3169-3175
Hauptverfasser: Liu, Ying, Wang, Guoshi, Guo, Wei, Zhang, Yingbin, Dong, Weiwei, Wang, Yan, Zeng, ZhiXiang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The power grid is the foundation of the development of the national industry. The rational and efficient distribution of power resources plays an important role in economic development. The smart grid is the use of modern network information technology to realize the exchange of data information between grid devices. The construction of smart grids has accumulated a huge amount of data resources. At present, the demand for power companies to “use data management enterprises and use the information to drive services” is increasingly urgent. Power big data has become the basis for grid companies to make decisions, but the accumulation of pure data does not bring benefits to grid companies. Therefore, making full use of these actual data based on the grid, in-depth analysis, and discovering and using the hidden information is of great significance for guiding the power companies to make correct decisions. This paper first analyzes the differences between smart grids and traditional grids and provides an overview of data mining techniques, including the association rules commonly used in association analysis. Then the application scenarios of data mining in the smart grid are put forward, and data mining technology is applied to power load forecasting. The experimental results show that the data mining method and actual results of the power load forecasting in the smart grid environment proposed in this paper are within a reasonable range. Therefore, the results of load forecasting in this paper are still of practical value.
ISSN:1064-1246
1875-8967
DOI:10.3233/JIFS-189355