A novel smart meter data compression method via stacked convolutional sparse auto-encoder. (June 2020)

• Record Type: Journal Article
• Authors: Wang, Shouxiang; Chen, Haiwen; Wu, Lei; Wang, Jianfeng
• Is Part Of: International journal of electrical power & energy systems. Volume 118(2020)
• Publication Date: 2020-06
• Subjects: Smart meter -- Lossy compression -- Separable convolution -- Auto-encoder; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2019.105761
• Languages: English
• ISSNs: 0142-0615

Abstract

Highlights: An efficient and lightweight DNN for smart meter data compression is proposed. The reconstruction error and computation time is significantly reduced. The lightweight model is suitable for running on embedded devices. Grouping compression is proposed to further improve the compression effect. Abstract: 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.