Social media data as a proxy for hourly fine-scale electric power consumption estimation

Chengbin Deng, Weiying Lin, Xinyue Ye, Zhenlong Li, Ziang Zhang, Ganggang Xu

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


Accurate forecasting of electric demand is essential for the operation of modern power system. Inaccurate load forecasting will considerably affect the power grid efficiency. Forecasting the electric demand for a small area, such as a building, has long been a well-known challenge. In this research, we examined the association between geotagged tweets and hourly electric consumption at a fine scale. All available geotagged tweets and electric meter readings were retrieved and spatially aggregated to each building in the study area. Comparing to traditional studies, the usage of geotagged tweets is to reflect human activity dynamics to some degree by considering human beings as sensors, which therefore can be employed at the building level. High correlation is found between the human activity indicator and the power consumption as supported by a correlation coefficient level over 0.8. To the best of our knowledge, rare studies placed an emphasis on hourly electric power consumption using social media data, especially at such a fine scale. This research shows the great potential of using Twitter data as a proxy of human activities to model hourly electric power consumption at the building level. More studies are warranted in the future to further examine the effectiveness of the proposed method in this research.

Original languageEnglish (US)
Pages (from-to)1553-1557
Number of pages5
JournalEnvironment and Planning A
Issue number8
StatePublished - Nov 1 2018
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Environmental Science (miscellaneous)


  • Social media
  • building-level prediction
  • electric load forecasting
  • electric power consumption
  • geotagged Twitter


Dive into the research topics of 'Social media data as a proxy for hourly fine-scale electric power consumption estimation'. Together they form a unique fingerprint.

Cite this