TY - JOUR
T1 - A novel smart meter data compression method via stacked convolutional sparse auto-encoder
AU - Wang, Shouxiang
AU - Chen, Haiwen
AU - Wu, Lei
AU - Wang, Jianfeng
N1 - Publisher Copyright:
© 2019 Elsevier Ltd
PY - 2020/6
Y1 - 2020/6
N2 - With the wide deployment of smart meters in distribution systems, a new challenge emerges for the storage and transmission of huge volume of power consumption data collected by smart meters. In this paper, a deep-learning-based compression method for smart meter data is proposed via stacked convolutional sparse auto-encoder (SCSAE). An efficient and lightweight auto-encoder structure is first designed by leveraging the unique characteristics of smart meter readings. Specifically, the encoder is designed based on 2D separable convolution layers and the decoder is based on transposed convolution layers. Compared with the existing auto-encoder method and traditional methods, the proposed structure is redesigned, and the parameters and reconstruction errors are efficiently reduced. In addition, cluster-based indexes are used to represent the regularity of power consumption behavior and the relationship between electricity consumption behavior and compression effect is studied. Case studies illustrate that the proposed method can attain significant enhancement in model size, computational efficiency, and reconstruction error reduction while maintaining the most abundant details. And grouping compression considering users’ electricity consumption rules can further improve the compression effect.
AB - With the wide deployment of smart meters in distribution systems, a new challenge emerges for the storage and transmission of huge volume of power consumption data collected by smart meters. In this paper, a deep-learning-based compression method for smart meter data is proposed via stacked convolutional sparse auto-encoder (SCSAE). An efficient and lightweight auto-encoder structure is first designed by leveraging the unique characteristics of smart meter readings. Specifically, the encoder is designed based on 2D separable convolution layers and the decoder is based on transposed convolution layers. Compared with the existing auto-encoder method and traditional methods, the proposed structure is redesigned, and the parameters and reconstruction errors are efficiently reduced. In addition, cluster-based indexes are used to represent the regularity of power consumption behavior and the relationship between electricity consumption behavior and compression effect is studied. Case studies illustrate that the proposed method can attain significant enhancement in model size, computational efficiency, and reconstruction error reduction while maintaining the most abundant details. And grouping compression considering users’ electricity consumption rules can further improve the compression effect.
KW - Auto-encoder
KW - Lossy compression
KW - Separable convolution
KW - Smart meter
UR - http://www.scopus.com/inward/record.url?scp=85076127887&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076127887&partnerID=8YFLogxK
U2 - 10.1016/j.ijepes.2019.105761
DO - 10.1016/j.ijepes.2019.105761
M3 - Article
AN - SCOPUS:85076127887
SN - 0142-0615
VL - 118
JO - International Journal of Electrical Power and Energy Systems
JF - International Journal of Electrical Power and Energy Systems
M1 - 105761
ER -