An application of different approaches to missing data for electric load forecasting by using an advanced gene expression programming algorithm
[ X ]
Tarih
2021
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Nova Science Publishers, Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
More recently, electric load forecasting has become a crucial tool in planning and management of modern electric power systems owing to the fact that it provides insights acquired by employing data analytics along with artificial intelligence for the forthcoming internet of energy era. The ubiquity of missing data is frequently encountered in the load forecasting applications and several imputation approaches have been carried out in the literature. Meanwhile, the use of artificial intelligence-based techniques is required to deal with the nonlinear nature of electric loads which is originated from seasonal and other effects. Furthermore, gene expression programming is one of the proven artificial intelligence-based techniques which produces simple equations between explanatory variables and target variable. In this study, an application of different approaches to missing data for short-term electric load forecasting by using an advanced gene expression programming algorithm is comprehensively introduced through a case study. Consequently, impacts of each imputation approach and the advanced gene expression programming algorithm on forecasting process are discussed, and the results of the study are presented in details. © 2021 by Nova Science Publishers, Inc. All rights reserved.
Açıklama
Anahtar Kelimeler
Artificial intelligence, Electric load forecasting, Gene expression programming, Imputation, Missing data
Kaynak
Advances in Engineering Research. Volume 44
