# Online Hierarchical Forecasting for Power Consumption Data

arXiv: https://arxiv.org/abs/2003.00585 · HTML: https://mlsanity.com/paper/2003.00585/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [CRPS Learning](https://mlsanity.com/paper/2102.00968/) (2021)
- [Conformal Prediction for Hierarchical Data](https://mlsanity.com/paper/2411.13479/) (2024)
- [Hierarchical transfer learning with applications for electricity load forecasting](https://mlsanity.com/paper/2111.08512/) (2021)
- [Forecasting Electric Vehicle Charging Station Occupancy: Smarter Mobility Data Challenge](https://mlsanity.com/paper/2306.06142/) (2023)
- [Leveraging Graph Neural Networks to Forecast Electricity Consumption](https://mlsanity.com/paper/2408.17366/) (2024)
- [Forecasting time series with constraints](https://mlsanity.com/paper/2502.10485/) (2025)
- [Hierarchical forecasting for aggregated curves with an application to day-ahead electricity price auctions](https://mlsanity.com/paper/2305.16255/) (2023)
- [Multivariate Online Linear Regression for Hierarchical Forecasting](https://mlsanity.com/paper/2402.14578/) (2024)
- [Graph Neural Networks for Electricity Load Forecasting](https://mlsanity.com/paper/2507.03690/) (2025)
- [Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure](https://mlsanity.com/paper/2610.13588/) (2026)

## Abstract (arXiv)

We study the forecasting of the power consumptions of a population of households and of subpopulations thereof. These subpopulations are built according to location, to exogenous information and/or to profiles we determined from historical households consumption time series. Thus, we aim to forecast the electricity consumption time series at several levels of households aggregation. These time series are linked through some summation constraints which induce a hierarchy. Our approach consists in three steps: feature generation, aggregation and projection. Firstly (feature generation step), we build, for each considering group for households, a benchmark forecast (called features), using random forests or generalized additive models. Secondly (aggregation step), aggregation algorithms, run in parallel, aggregate these forecasts and provide new predictions. Finally (projection step), we use the summation constraints induced by the time series underlying hierarchy to re-conciliate the forecasts by projecting them in a well-chosen linear subspace. We provide some theoretical guaranties on the average prediction error of this methodology, through the minimization of a quantity called regret. We also test our approach on households power consumption data collected in Great Britain by multiple energy providers in the Energy Demand Research Project context. We build and compare various population segmentations for the evaluation of our approach performance.