Performance Evaluation of the Impact of Clustering Methods and Parameters on Adaptive Neuro-Fuzzy Inference System Models for Electricity Consumption Prediction during COVID-19

Stephen Oladipo (), Yanxia Sun () and Abraham Amole
Additional contact information
Stephen Oladipo: Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa
Yanxia Sun: Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa
Abraham Amole: Department of Electrical, Electronics and Telecommunication Engineering, College of Engineering, Bells University of Technology, Ota 112233, Nigeria

Energies, 2022, vol. 15, issue 21, 1-20

Abstract: Increasing economic and population growth has led to a rise in electricity consumption. Consequently, electrical utility firms must have a proper energy management strategy in place to improve citizens’ quality of life and ensure an organization’s seamless operation, particularly amid unanticipated circumstances such as coronavirus disease (COVID-19). There is a growing interest in the application of artificial intelligence models to electricity prediction during the COVID-19 pandemic, but the impacts of clustering methods and parameter selection have not been explored. Consequently, this study investigates the impacts of clustering techniques and different significant parameters of the adaptive neuro-fuzzy inference systems (ANFIS) model for predicting electricity consumption during the COVID-19 pandemic using districts of Lagos, Nigeria as a case study. The energy prediction of the dataset was examined in relation to three clustering techniques: grid partitioning (GP), subtractive clustering (SC), fuzzy c-means (FCM), and other key parameters such as clustering radius (CR), input and output membership functions, and the number of clusters. Using renowned statistical metrics, the best sub-models for each clustering technique were selected. The outcome showed that the ANFIS-based FCM technique produced the best results with five clusters, with the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Variation (RCoV), Coefficient of Variation of the Root Mean Square Error (CVRMSE), and Mean Absolute Percentage Error (MAPE) being 1137.6024, 898.5070, 0.0586, 11.5727, and 9.3122, respectively. The FCM clustering technique is recommended for usage in ANFIS models that employ similar time series data due to its accuracy and speed.

Keywords: adaptive neuro-fuzzy inference systems; fuzzy c-means; grid-partitioning; subtractive-clustering; artificial neural 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: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/15/21/7863/pdf (application/pdf)
https://www.mdpi.com/1996-1073/15/21/7863/ (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:15:y:2022:i:21:p:7863-:d:951126

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 ().