A Meta-Modeling Power Consumption Forecasting Approach Combining Client Similarity and Causality

Dimitrios Kontogiannis, Dimitrios Bargiotas, Aspassia Daskalopulu and Lefteri H. Tsoukalas
Additional contact information
Dimitrios Kontogiannis: Department of Electrical and Computer Engineering, School of Engineering, University of Thessaly, 38221 Volos, Greece
Dimitrios Bargiotas: Department of Electrical and Computer Engineering, School of Engineering, University of Thessaly, 38221 Volos, Greece
Aspassia Daskalopulu: Department of Electrical and Computer Engineering, School of Engineering, University of Thessaly, 38221 Volos, Greece
Lefteri H. Tsoukalas: AI Systems Lab, School of Nuclear Engineering, Purdue University, West Lafayette, IN 47907, USA

Energies, 2021, vol. 14, issue 19, 1-19

Abstract: Power forecasting models offer valuable insights on the electricity consumption patterns of clients, enabling the development of advanced strategies and applications aimed at energy saving, increased energy efficiency, and smart energy pricing. The data collection process for client consumption models is not always ideal and the resulting datasets often lead to compromises in the implementation of forecasting models, as well as suboptimal performance, due to several challenges. Therefore, combinations of elements that highlight relationships between clients need to be investigated in order to achieve more accurate consumption predictions. In this study, we exploited the combined effects of client similarity and causality, and developed a power consumption forecasting model that utilizes ensembles of long short-term memory (LSTM) networks. Our novel approach enables the derivation of different representations of the predicted consumption based on feature sets influenced by similarity and causality metrics. The resulting representations were used to train a meta-model, based on a multi-layer perceptron (MLP), in order to combine the results of the LSTM ensembles optimally. This combinatorial approach achieved better overall performance and yielded lower mean absolute percentage error when compared to the standalone LSTM ensembles that do not include similarity and causality. Additional experiments indicated that the combination of similarity and causality resulted in more performant models when compared to implementations utilizing only one element on the same model structure.

Keywords: power forecasting; energy; machine learning; neural networks; artificial intelligence; data analysis; feature engineering; ensemble neural networks; meta-modeling (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: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/19/6088/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/19/6088/ (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:14:y:2021:i:19:p:6088-:d:642323

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 ().