Modeling Electricity Consumption using Modified Newton's Method

P., Ozoh and S., Abd-Rahman and Jane, Labadin and M., Apperley (2013) Modeling Electricity Consumption using Modified Newton's Method. International Journal of Computer Applications, 86 (13). ISSN 0975 – 8887

[img]
Preview
PDF
Modeling Electricity Consumption using Modified Newton’s Method (abstract).pdf

Download (623kB) | Preview
Official URL: http://dx.doi.org/10.5120/15046-3414

Abstract

In this paper we present modified Newton’s model (MNM) to model electricity consumption data. A previous method to model electricity consumption data was done using forecasting technique (FT) and artificial neural networks (ANN). A drawback to previous techniques is that computations give less reliable results when compared to MNM. A comparative analysis is carried out for FT, ANN and MNM to investigate which of these methods is the most reliable technique. The results indicate that MNM model reduced mean absolute percentage error (MAPE) to 0.93%, while those of FT and ANN were 3.01% and 3.11%, respectively. Based on these error measures, the study shows that the three methods are highly accurate modeling techniques, but MNM was found to be the best technique when mining information. Experimental results indicate that MNM is the most accurate when compared to FT and ANN and thus has the best competitive performance level.

Item Type: Article
Uncontrolled Keywords: Efficiency, modified newton’s method, forecasting technique, artificial neural networks, reliability, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Depositing User: Karen Kornalius
Date Deposited: 04 Aug 2015 01:28
Last Modified: 04 Aug 2015 01:28
URI: http://ir.unimas.my/id/eprint/8467

Actions (For repository members only: login required)

View Item View Item