Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Revista Ingenierías Universidad de Medellín
Print version ISSN 1692-3324
Abstract
VILLA G., Fernán A.; VELASQUEZ H., Juan D. and SANCHEZ S., Paola A.. Overfitting control inside cascade correlation neural networks applied to electricity contract price prediction. Rev. ing. univ. Medellín [online]. 2015, vol.14, n.26, pp.161-176. ISSN 1692-3324.
Prediction of electricity prices is considered a difficult task due to the number and complexity of factors that influence their performance, and their relationships. Neural networks cascade correlation - CASCOR allows to do a constructive learning and it captures better the characteristics of the data; however, it has a high tendency to overfitting. To control overfitting in some areas regularization techniques are used. However, in the literature there are no studies that: i) use regularization techniques to control overfitting in CASCOR networks, ii) use CASCOR networks in predicting of electrical series iii) compare the performance with traditional neural networks or statistical models. The aim of this paper is to model and predict the behavior of the price series of electricity contracts in Colombia, using CASCOR networks and controlling the overfitting by regularization techniques
Keywords : time series forecast; cascade correlation; neural networks; electricity market of Colombia.