Load forecasting using a multivariate meta-learning system
| Autor: | Johan A. K. Suykens, Slavko Krajcar, Marin Matijaš |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Multivariate statistics
SISTA Meta learning (computer science) Computer science business.industry 020209 energy Load forecasting Model selection General Engineering Univariate 02 engineering and technology Demand forecasting Machine learning computer.software_genre Computer Science Applications electricity consumption prediction energy expert systems industrial applications short-term electric load forecasting meta-learning power demand estimation Artificial Intelligence Component (UML) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Probabilistic forecasting business computer Technology forecasting |
| Zdroj: | Expert Systems with Applications |
| ISSN: | 0957-4174 |
| DOI: | 10.1016/j.eswa.2013.01.047 |
| Popis: | Although over a thousand scientific papers address the topic of load forecasting every year, only a few are dedicated to finding a general framework for load forecasting that improves the performance, without depending on the unique characteristics of a certain task such as geographical location. Meta-learning, a powerful approach for algorithm selection has so far been demonstrated only on univariate time-series forecasting. Multivariate time-series forecasting is known to have better performance in load forecasting. In this paper we propose a meta-learning system for multivariate time-series forecasting as a general framework for load forecasting model selection. We show that a meta-learning system built on 65 load forecasting tasks returns lower forecasting error than 10 well-known forecasting algorithms on 4 load forecasting tasks for a recurrent real-life simulation. We introduce new metafeatures of fickleness, traversity, granularity and highest ACF. The meta-learning framework is parallelized, component-based and easily extendable. © 2013 Elsevier Ltd. All rights reserved. ispartof: Expert Systems with Applications vol:40 issue:11 pages:4427-4437 status: published |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect