# Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges

**Authors:** Yi Wang, Qixin Chen, Tao Hong, Chongqing Kang  
**arXiv:** [1802.04117](https://arxiv.org/abs/1802.04117)  
**Date:** 2018-02-09  
**Summary page:** https://www.summarizepaper.com/en/paper/1802.04117v2/

## Key points

- Smart meter data analytics is reviewed in this paper, focusing on its application in promoting efficiency and sustainability of the power grid.
- The widespread popularity of smart meters enables the collection of fine-grained electricity consumption data.
- Ongoing deregulation in the power industry creates opportunities for utilizing smart meter data.
- Three stages of analytics (descriptive, predictive, and prescriptive) are followed to identify key application areas: load analysis, load forecasting, and load management.
- Techniques and methodologies adopted or developed for each application area are reviewed.
- Emerging trends such as big data issues, novel machine learning technologies, new business models, energy system transitions, and data privacy and security concerns are explored.
- Two figures provide further context: Figure 1 shows a timeline of publications indexed by WoS from 2010 to 2017 with a rapid increase starting in 2012; Figure 2 ranks journals based on the number of relevant papers published since 2010 with IEEE Transactions on Smart Grid being the most popular journal.
- Existing review articles related to smart meter data analytics are mentioned but considered either beyond scope or not as comprehensive and up-to-date as this paper.
- The paper aims to provide a comprehensive overview of smart meter data analytics in wider applications over the past five years while including classical works published earlier.

## Summary

This paper provides a comprehensive review of smart meter data analytics, focusing on its application in promoting and enhancing the efficiency and sustainability of the power grid. The authors begin by discussing the widespread popularity of smart meters, which enables the collection of fine-grained electricity consumption data. They also highlight the ongoing deregulation of the power industry, particularly on the delivery side, which creates opportunities for utilizing smart meter data. The paper follows three stages of analytics - descriptive, predictive, and prescriptive - to identify key application areas for smart meter data analytics: load analysis, load forecasting, and load management. For each application area, the authors review the techniques and methodologies adopted or developed to address them. In addition to discussing current research and challenges in smart meter data analytics, the paper also explores emerging trends such as big data issues, novel machine learning technologies, new business models, energy system transitions, and data privacy and security concerns. To provide further context for their review, the authors present two figures. Figure 1 shows a timeline of publications indexed by WoS from 2010 to 2017. The number of publications increased rapidly starting in 2012. Figure 2 ranks journals based on the number of relevant papers published since 2010. IEEE Transactions on Smart Grid is identified as the most popular journal for smart meter data analytics articles. The paper also briefly mentions several existing review articles related to smart meter data analytics but highlights that they are either beyond the scope or not as comprehensive and up-to-date as this paper. Overall, this paper aims to provide a comprehensive overview of smart meter data analytics in wider applications over the past five years while including classical works published earlier. It emphasizes advancements in methodologies and applications within an emerging research field influenced by factors such as big data and market liberalization. Additionally mentioned is an open load dataset that may be relevant to future research in this area.