.png){kind=icon}
.png){kind=icon}
Return
Human Spatial Dynamics for Electricity Demand Forecasting
.png){kind=icon}
PRE
AI
DOI：10.1109/TPWRS.2025.3648653.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate electricity demand forecasting is crucial for energy security and efficiency. In 2023, massive savings have been observed in Europe following an unprecedented global energy crisis. However, assessing the impact of such a crisis on electricity consumption behaviour is challenging. Moreover, standard statistical models based on meteorological and seasonal data have difficulty dealing with such sudden changes. Here, we show that mobility indices based on mobile network data reporting daily presence data significantly improve the performance of state-of-the-art models in electricity demand forecasting during France's government-pushed energy sobriety period. We start by introducing our mobility dataset, comparing it to others, and showing that adding mobility indices to models outperforms the state-of-the-art during winter 2022-2023. Then, we develop interpretable insights by characterizing how winter of 2022-2023 was atypical in terms of electricity demand and by showing how our mobile network data captures work dynamics. In effect, our results characterise the effect of employment-related behaviour patterns on electricity demand.
Keywords:
Electricity demand forecasting
energy crisis
mobile phone data
model adaption
time series
Journal
IF:
7.2
Papers:
1.1W
Citations:
5.0W