Power Demand and Probability Density Forecasting Based on Deep Learning

Kaile Zhou () and Lulu Wen ()
Additional contact information
Kaile Zhou: Hefei University of Technology
Lulu Wen: Hefei University of Technology

Chapter Chapter 5 in Smart Energy Management, 2022, pp 101-134 from Springer

Abstract: Abstract Highly accurate power demand forecasting is important for power system planning and operational decision making. In this chapter, a deep learning (DL) model consisting of multiple hidden layers is used for short-term power demand forecasting. The results are compared with those of some widely used machine learning models, including random forest (RF) and gradient boosting machines. Then, feature engineering is employed to find the most influential factors. Finally, a probability density forecasting method based on quantile regression and DL is established. Three case studies are presented using daily electricity consumption data of three cities of China. The results show that the DL-based approach has higher power demand forecasting accuracy than RF and gradient boosting models. Also, the presented method can obtain high-quality prediction intervals via probability density forecasting.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:sprchp:978-981-16-9360-1_5

Ordering information: This item can be ordered from
http://www.springer.com/9789811693601

DOI: 10.1007/978-981-16-9360-1_5

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().