Enregistré dans:
Détails bibliographiques
Auteurs principaux: Brusaferri, Alessandro, Ballarino, Andrea, Grossi, Luigi, Laurini, Fabrizio
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2404.02722
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929380039589888
author Brusaferri, Alessandro
Ballarino, Andrea
Grossi, Luigi
Laurini, Fabrizio
author_facet Brusaferri, Alessandro
Ballarino, Andrea
Grossi, Luigi
Laurini, Fabrizio
contents Probabilistic electricity price forecasting (PEPF) is subject of increasing interest, following the demand for proper quantification of prediction uncertainty, to support the operation in complex power markets with increasing share of renewable generation. Distributional neural networks ensembles have been recently shown to outperform state of the art PEPF benchmarks. Still, they require critical reliability enhancements, as fail to pass the coverage tests at various steps on the prediction horizon. In this work, we propose a novel approach to PEPF, extending the state of the art neural networks ensembles based methods through conformal inference based techniques, deployed within an on-line recalibration procedure. Experiments have been conducted on multiple market regions, achieving day-ahead forecasts with improved hourly coverage and stable probabilistic scores.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02722
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On-line conformalized neural networks ensembles for probabilistic forecasting of day-ahead electricity prices
Brusaferri, Alessandro
Ballarino, Andrea
Grossi, Luigi
Laurini, Fabrizio
Machine Learning
Probabilistic electricity price forecasting (PEPF) is subject of increasing interest, following the demand for proper quantification of prediction uncertainty, to support the operation in complex power markets with increasing share of renewable generation. Distributional neural networks ensembles have been recently shown to outperform state of the art PEPF benchmarks. Still, they require critical reliability enhancements, as fail to pass the coverage tests at various steps on the prediction horizon. In this work, we propose a novel approach to PEPF, extending the state of the art neural networks ensembles based methods through conformal inference based techniques, deployed within an on-line recalibration procedure. Experiments have been conducted on multiple market regions, achieving day-ahead forecasts with improved hourly coverage and stable probabilistic scores.
title On-line conformalized neural networks ensembles for probabilistic forecasting of day-ahead electricity prices
topic Machine Learning
url https://arxiv.org/abs/2404.02722