# Smoothed Bernstein Online Aggregation for Day-Ahead Electricity Demand Forecasting

arXiv: https://arxiv.org/abs/2107.06268 · HTML: https://mlsanity.com/paper/2107.06268/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [Optimal learning with Bernstein Online Aggregation](https://mlsanity.com/paper/1404.1356/) (2014)
- [Efficient online algorithms for fast-rate regret bounds under sparsity](https://mlsanity.com/paper/1805.09174/) (2018)
- [Iteratively reweighted adaptive lasso for conditional heteroscedastic time series with applications to AR-ARCH type processes](https://mlsanity.com/paper/1502.06557/) (2015)
- [Lasso estimation for GEFCom2014 probabilistic electric load forecasting](https://mlsanity.com/paper/1603.01376/) (2016)
- [Changes in electricity demand pattern in Europe due to COVID-19 shutdowns](https://mlsanity.com/paper/2004.14864/) (2020)
- [Forecasting wind power - Modeling periodic and non-linear effects under conditional heteroscedasticity](https://mlsanity.com/paper/1606.00546/) (2016)
- [tsrobprep - an R package for robust preprocessing of time series data](https://mlsanity.com/paper/2104.12657/) (2021)

## Built on by (most cited first, 5 of 5)

- [The Rise of Diffusion Models in Time-Series Forecasting](https://mlsanity.com/paper/2401.03006/) (2024)
- [Hierarchical transfer learning with applications for electricity load forecasting](https://mlsanity.com/paper/2111.08512/) (2021)
- [Multivariate Probabilistic CRPS Learning with an Application to Day-Ahead Electricity Prices](https://mlsanity.com/paper/2303.10019/) (2023)
- [High-Resolution Peak Demand Estimation Using Generalized Additive Models and Deep Neural Networks](https://mlsanity.com/paper/2203.03342/) (2022)
- [Efficient mid-term forecasting of hourly electricity load using generalized additive models](https://mlsanity.com/paper/2405.17070/) (2024)

## Abstract (arXiv)

We present a winning method of the IEEE DataPort Competition on Day-Ahead Electricity Demand Forecasting: Post-COVID Paradigm. The day-ahead load forecasting approach is based on online forecast combination of multiple point prediction models. It contains four steps: i) data cleaning and preprocessing, ii) a holiday adjustment procedure, iii) training of individual forecasting models, iv) forecast combination by smoothed Bernstein Online Aggregation (BOA). The approach is flexible and can quickly adopt to new energy system situations as they occurred during and after COVID-19 shutdowns. The pool of individual prediction models ranges from rather simple time series models to sophisticated models like generalized additive models (GAMs) and high-dimensional linear models estimated by lasso. They incorporate autoregressive, calendar and weather effects efficiently. All steps contain novel concepts that contribute to the excellent forecasting performance of the proposed method. This holds particularly for the holiday adjustment procedure and the fully adaptive smoothed BOA approach.