MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids

Guolong Liu; Yan Bai; Jinjie Liu; Huan Zhao; Gaoqi Liang; Junhua Zhao

doi:10.1109/EI259745.2023.10512658

MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids

Guolong Liu
, Yan Bai
, Jinjie Liu
, Huan Zhao
, Gaoqi Liang
, Junhua Zhao^*

^*Corresponding author for this work

The Chinese University of Hong Kong, Shenzhen
Nanyang Technological University
Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Smart grids have rapidly developed in recent years, and a large amount of data has been collected and become the basis for decision-making of power grid operation. To ensure the safe and stable operation of the power grid, how to improve the data quality of the collected data has become an important research topic. Therefore, an attention mechanism-based autoencoder is proposed in this paper for missing data recovery to improve data quality in smart grids. The proposed method named missing data recovery autoencoder (MDRAE) contains two parts of an encoder and a decoder, and the attention mechanism is integrated into the encoder part to better extract the key information of the data. The effectiveness of the proposed method is verified by conducting experiments on two datasets including industrial load data and residential load data. The experimental results show that the model performance of the proposed method is better than that of the two benchmarks, and the proposed method can recover the missing data accurately.

Original language	English
Title of host publication	2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5190-5195
Number of pages	6
ISBN (Electronic)	9798350345094
DOIs	https://doi.org/10.1109/EI259745.2023.10512658
State	Published - 2023
Externally published	Yes
Event	7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023 - Hangzhou, China Duration: 15 Dec 2023 → 18 Dec 2023

Publication series

Name	2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023

Conference

Conference	7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023
Country/Territory	China
City	Hangzhou
Period	15/12/23 → 18/12/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

MDRAE
attention mechanism
autoencoder
deep learning
missing data recovery
smart grid

Access to Document

10.1109/EI259745.2023.10512658

Cite this

Liu, G., Bai, Y., Liu, J., Zhao, H., Liang, G., & Zhao, J. (2023). MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids. In 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023 (pp. 5190-5195). (2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EI259745.2023.10512658

Liu, Guolong ; Bai, Yan ; Liu, Jinjie et al. / MDRAE : An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids. 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 5190-5195 (2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023).

@inproceedings{39d435493acc471182ea0ca2cc476fbe,

title = "MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids",

abstract = "Smart grids have rapidly developed in recent years, and a large amount of data has been collected and become the basis for decision-making of power grid operation. To ensure the safe and stable operation of the power grid, how to improve the data quality of the collected data has become an important research topic. Therefore, an attention mechanism-based autoencoder is proposed in this paper for missing data recovery to improve data quality in smart grids. The proposed method named missing data recovery autoencoder (MDRAE) contains two parts of an encoder and a decoder, and the attention mechanism is integrated into the encoder part to better extract the key information of the data. The effectiveness of the proposed method is verified by conducting experiments on two datasets including industrial load data and residential load data. The experimental results show that the model performance of the proposed method is better than that of the two benchmarks, and the proposed method can recover the missing data accurately.",

keywords = "MDRAE, attention mechanism, autoencoder, deep learning, missing data recovery, smart grid",

author = "Guolong Liu and Yan Bai and Jinjie Liu and Huan Zhao and Gaoqi Liang and Junhua Zhao",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023 ; Conference date: 15-12-2023 Through 18-12-2023",

year = "2023",

doi = "10.1109/EI259745.2023.10512658",

language = "英语",

series = "2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5190--5195",

booktitle = "2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023",

address = "美国",

}

Liu, G, Bai, Y, Liu, J, Zhao, H, Liang, G & Zhao, J 2023, MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids. in 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023. 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023, Institute of Electrical and Electronics Engineers Inc., pp. 5190-5195, 7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023, Hangzhou, China, 15/12/23. https://doi.org/10.1109/EI259745.2023.10512658

MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids. / Liu, Guolong; Bai, Yan; Liu, Jinjie et al.
2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 5190-5195 (2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MDRAE

T2 - 7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023

AU - Liu, Guolong

AU - Bai, Yan

AU - Liu, Jinjie

AU - Zhao, Huan

AU - Liang, Gaoqi

AU - Zhao, Junhua

PY - 2023

Y1 - 2023

N2 - Smart grids have rapidly developed in recent years, and a large amount of data has been collected and become the basis for decision-making of power grid operation. To ensure the safe and stable operation of the power grid, how to improve the data quality of the collected data has become an important research topic. Therefore, an attention mechanism-based autoencoder is proposed in this paper for missing data recovery to improve data quality in smart grids. The proposed method named missing data recovery autoencoder (MDRAE) contains two parts of an encoder and a decoder, and the attention mechanism is integrated into the encoder part to better extract the key information of the data. The effectiveness of the proposed method is verified by conducting experiments on two datasets including industrial load data and residential load data. The experimental results show that the model performance of the proposed method is better than that of the two benchmarks, and the proposed method can recover the missing data accurately.

AB - Smart grids have rapidly developed in recent years, and a large amount of data has been collected and become the basis for decision-making of power grid operation. To ensure the safe and stable operation of the power grid, how to improve the data quality of the collected data has become an important research topic. Therefore, an attention mechanism-based autoencoder is proposed in this paper for missing data recovery to improve data quality in smart grids. The proposed method named missing data recovery autoencoder (MDRAE) contains two parts of an encoder and a decoder, and the attention mechanism is integrated into the encoder part to better extract the key information of the data. The effectiveness of the proposed method is verified by conducting experiments on two datasets including industrial load data and residential load data. The experimental results show that the model performance of the proposed method is better than that of the two benchmarks, and the proposed method can recover the missing data accurately.

KW - MDRAE

KW - attention mechanism

KW - autoencoder

KW - deep learning

KW - missing data recovery

KW - smart grid

UR - https://www.scopus.com/pages/publications/85194169091

U2 - 10.1109/EI259745.2023.10512658

DO - 10.1109/EI259745.2023.10512658

M3 - 会议稿件

AN - SCOPUS:85194169091

T3 - 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023

SP - 5190

EP - 5195

BT - 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 15 December 2023 through 18 December 2023

ER -

Liu G, Bai Y, Liu J, Zhao H, Liang G, Zhao J. MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids. In 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 5190-5195. (2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023). doi: 10.1109/EI259745.2023.10512658

MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this