Short-term multiple power type prediction based on deep learning

Ran Wei (), Qirui Gan (), Huiquan Wang (), Yue You and Xin Dang ()
Additional contact information
Ran Wei: Tianjin Polytechnic University
Qirui Gan: Tianjin Polytechnic University
Huiquan Wang: Tianjin Polytechnic University
Yue You: State Grid Electronic Commerce Company, LTD
Xin Dang: Tianjin Polytechnic University

International Journal of System Assurance Engineering and Management, 2020, vol. 11, issue 4, No 12, 835-841

Abstract: Abstract This paper proposes a method based on a 4-layer deep neural network model by stacked denoising auto-encoders to analyze four types of power data: current (I), voltage (U), active power (P) and reactive power (Q). We collect 7 days of household power data. In the beginning, the prediction accuracy rate can reach 82.45% when 1-h historical data are used to predict the data for the following 5 min. In order to optimize the parameters of this model, data over a 3-month period are collected. The prediction accuracy rate is 95.52% when three-day historical data are used to predict the data for the next hour. Finally, supplemental experiments are added to verify that the current change has a greater impact on the model. The 3-month data set is used as the training set. Extract 2 weeks of data from 3 months of data, and the 2-week data is divided into two test sets. The effect of the model on the prediction accuracy from 7:00 in the morning to 24:00 in the evening, and from 0:00 in the evening to 7:00 in the morning is studied. The accuracy rates are 95.05% and 99.02%, respectively. It shows that the prediction accuracy of the model is higher for the period with a lower frequency of power consumption than the period with a higher frequency of power consumption, and that the change of the current has a greater impact on the prediction of the model. Finally, we prove that the effect of the 4-layer network is better than that of the 3-layer, 5-layer and 7-layer network models.

Keywords: Deep learning; Neural network; Stacked denoising auto-encoder; Power prediction (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1007/s13198-019-00885-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:ijsaem:v:11:y:2020:i:4:d:10.1007_s13198-019-00885-8

Ordering information: This journal article can be ordered from
http://www.springer.com/engineering/journal/13198

DOI: 10.1007/s13198-019-00885-8

Access Statistics for this article

International Journal of System Assurance Engineering and Management is currently edited by P.K. Kapur, A.K. Verma and U. Kumar

More articles in International Journal of System Assurance Engineering and Management from Springer, The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().