Short-term residential load forecasting based on resident behaviour learning

Weicong Kong; Zhao Yang Dong; David J. Hill; Fengji Luo; Yan Xu

doi:10.1109/TPWRS.2017.2688178

Short-term residential load forecasting based on resident behaviour learning

Weicong Kong
, Zhao Yang Dong
, David J. Hill
, Fengji Luo
, Yan Xu

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

576 Citations (Scopus)

Abstract

Residential load forecasting has been playing an increasingly important role in modern smart grids. Due to the variability of residents' activities, individual residential loads are usually too volatile to forecast accurately. An LSTM based deep learning forecasting framework with appliance consumption sequences is proposed to address such volatile problem. It is shown that the forecasting accuracy can be notably improved by including appliance measurements in the training data. The effectiveness of the proposed method is validated through extensive comparison studies on a real-world dataset. © 2018 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

Original language	English
Article number	7887751
Journal	IEEE Transactions on Power Systems
Volume	33
Issue number	1
DOIs	https://doi.org/10.1109/TPWRS.2017.2688178
Publication status	Published - 2018
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Deep learning
Meter-level load forecasting
Recurrent neural network
Short-Term load forecasting

Access Output

10.1109/TPWRS.2017.2688178

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{f29cff597deb4314b7a9ab39a7b993bb,

title = "Short-term residential load forecasting based on resident behaviour learning",

abstract = "Residential load forecasting has been playing an increasingly important role in modern smart grids. Due to the variability of residents' activities, individual residential loads are usually too volatile to forecast accurately. An LSTM based deep learning forecasting framework with appliance consumption sequences is proposed to address such volatile problem. It is shown that the forecasting accuracy can be notably improved by including appliance measurements in the training data. The effectiveness of the proposed method is validated through extensive comparison studies on a real-world dataset. {\textcopyright} 2018 Institute of Electrical and Electronics Engineers Inc. All rights reserved.",

keywords = "Deep learning, Meter-level load forecasting, Recurrent neural network, Short-Term load forecasting",

author = "Weicong Kong and Dong, \{Zhao Yang\} and Hill, \{David J.\} and Fengji Luo and Yan Xu",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2018",

doi = "10.1109/TPWRS.2017.2688178",

language = "English",

volume = "33",

journal = "IEEE Transactions on Power Systems",

issn = "0885-8950",

publisher = "IEEE",

number = "1",

}

TY - JOUR

T1 - Short-term residential load forecasting based on resident behaviour learning

AU - Kong, Weicong

AU - Dong, Zhao Yang

AU - Hill, David J.

AU - Luo, Fengji

AU - Xu, Yan

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2018

Y1 - 2018

N2 - Residential load forecasting has been playing an increasingly important role in modern smart grids. Due to the variability of residents' activities, individual residential loads are usually too volatile to forecast accurately. An LSTM based deep learning forecasting framework with appliance consumption sequences is proposed to address such volatile problem. It is shown that the forecasting accuracy can be notably improved by including appliance measurements in the training data. The effectiveness of the proposed method is validated through extensive comparison studies on a real-world dataset. © 2018 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

AB - Residential load forecasting has been playing an increasingly important role in modern smart grids. Due to the variability of residents' activities, individual residential loads are usually too volatile to forecast accurately. An LSTM based deep learning forecasting framework with appliance consumption sequences is proposed to address such volatile problem. It is shown that the forecasting accuracy can be notably improved by including appliance measurements in the training data. The effectiveness of the proposed method is validated through extensive comparison studies on a real-world dataset. © 2018 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

KW - Deep learning

KW - Meter-level load forecasting

KW - Recurrent neural network

KW - Short-Term load forecasting

UR - https://www.scopus.com/pages/publications/85046692362

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85046692362&origin=recordpage

U2 - 10.1109/TPWRS.2017.2688178

DO - 10.1109/TPWRS.2017.2688178

M3 - RGC 21 - Publication in refereed journal

SN - 0885-8950

VL - 33

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

IS - 1

M1 - 7887751

ER -

Short-term residential load forecasting based on resident behaviour learning

Abstract

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this