Assessment of an Adaptive Load Forecasting Methodology in a Smart Grid Demonstration Project

Ricardo Vazquez, Hortensia Amaris, Monica Alonso, Gregorio Lopez, Jose Ignacio Moreno, Daniel Olmeda and Javier Coca
Additional contact information
Ricardo Vazquez: Department of Electrical Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Hortensia Amaris: Department of Electrical Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Monica Alonso: Department of Electrical Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Gregorio Lopez: Department of Telematic Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Jose Ignacio Moreno: Department of Telematic Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Daniel Olmeda: Department of Electrical Engineering, University Carlos III of Madrid, Avda de la Universidad 30, 28911 Madrid, Spain
Javier Coca: Unión Fenosa Distribución, Avda. San Luis 77, 28033 Madrid, Spain

Energies, 2017, vol. 10, issue 2, 1-23

Abstract: This paper presents the implementation of an adaptive load forecasting methodology in two different power networks from a smart grid demonstration project deployed in the region of Madrid, Spain. The paper contains an exhaustive comparative study of different short-term load forecast methodologies, addressing the methods and variables that are more relevant to be applied for the smart grid deployment. The evaluation followed in this paper suggests that the performance of the different methods depends on the conditions of the site in which the smart grid is implemented. It is shown that some non-linear methods, such as support vector machine with a radial basis function kernel and extremely randomized forest offer good performance using only 24 lagged load hourly values, which could be useful when the amount of data available is limited due to communication problems in the smart grid monitoring system. However, it has to be highlighted that, in general, the behavior of different short-term load forecast methodologies is not stable when they are applied to different power networks and that when there is a considerable variability throughout the whole testing period, some methods offer good performance in some situations, but they fail in others. In this paper, an adaptive load forecasting methodology is proposed to address this issue improving the forecasting performance through iterative optimization: in each specific situation, the best short-term load forecast methodology is chosen, resulting in minimum prediction errors.

Keywords: short-term load forecasting; smart grids; Machine-to-Machine (M2M) communications; time series; distribution networks (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.mdpi.com/1996-1073/10/2/190/pdf (application/pdf)
https://www.mdpi.com/1996-1073/10/2/190/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:10:y:2017:i:2:p:190-:d:89745

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().