LAPSE

LAPSE:2019.0405
Published Article
LAPSE:2019.0405
Deep Neural Network Based Demand Side Short Term Load Forecasting
Seunghyoung Ryu, Jaekoo Noh, Hongseok Kim
March 15, 2019
In the smart grid, one of the most important research areas is load forecasting; it spans from traditional time series analyses to recent machine learning approaches and mostly focuses on forecasting aggregated electricity consumption. However, the importance of demand side energy management, including individual load forecasting, is becoming critical. In this paper, we propose deep neural network (DNN)-based load forecasting models and apply them to a demand side empirical load database. DNNs are trained in two different ways: a pre-training restricted Boltzmann machine and using the rectified linear unit without pre-training. DNN forecasting models are trained by individual customer’s electricity consumption data and regional meteorological elements. To verify the performance of DNNs, forecasting results are compared with a shallow neural network (SNN), a double seasonal Holt⁻Winters (DSHW) model and the autoregressive integrated moving average (ARIMA). The mean absolute percentage error (MAPE) and relative root mean square error (RRMSE) are used for verification. Our results show that DNNs exhibit accurate and robust predictions compared to other forecasting models, e.g., MAPE and RRMSE are reduced by up to 17% and 22% compared to SNN and 9% and 29% compared to DSHW.
Keywords
deep learning, deep neural network, exponential smoothing, pre-training, rectified linear unit (ReLU), restricted Boltzmann machine (RBM), short-term load forecasting, smart grid
Suggested Citation
Ryu S, Noh J, Kim H. Deep Neural Network Based Demand Side Short Term Load Forecasting. (2019). LAPSE:2019.0405
Author Affiliations
Ryu S: Department of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, Korea
Noh J: Software Center, Korea Electric Power Corporation (KEPCO), 105 Munji Road, Yuseong-Gu, Daejeon 305-760, Korea
Kim H: Department of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, Korea [ORCID]
[Login] to see author email addresses.
Journal Name
Energies
Volume
10
Issue
1
Article Number
E3
Year
2016
Publication Date
2016-12-22
Published Version
ISSN
1996-1073
Version Comments
Original Submission
Other Meta
PII: en10010003, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2019.0405
This Record
External Link

doi:10.3390/en10010003
Publisher Version
Download
Files
[Download 1v1.pdf] (2.5 MB)
Mar 15, 2019
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
22
Version History
[v1] (Original Submission)
Mar 15, 2019
 
Verified by curator on
Mar 15, 2019
This Version Number
v1
Citations
Most Recent
This Version
URL Here
http://psecommunity.org/LAPSE:2019.0405
 
Original Submitter
Calvin Tsay
Links to Related Works
Directly Related to This Work
Publisher Version