Adeyemi-Kayode, Temitope M. and Orovwode, H. E. and Adoghe, A. U. and Misra, Sanjay and Agrawal, Akshat (2023) Short-Term Load Demand Forecasting Using Artificial Neural Network. In: International Conference on Recent Innovations in Computing, 03 May 2023, Online.
![[img]](http://eprints.covenantuniversity.edu.ng/style/images/fileicons/application_pdf.png) |
PDF
Download (125kB) |
Abstract
This work proposes a short-term electrical load demand forecaster for the Nigerian power distribution firms in Abuja, Benin, and Enugu. Using artificial neural network, the forecaster is created. Hour of the day, calendar day, day of the week (Sunday-Saturday), load demand of the previous day, load demand of the previous week, and average load demand of the preceding 24 h are the inputs to the neural network. The historical load demand for 2017–2020 includes hourly resolved dates and load demand for Abuja, Benin, and Enugu distribution firms for training purposes, while data for 2020 was used for testing the algorithm. The results generated a mean average percentage error ranging from 0.16 to 0.35. This forecaster is essential to Nigeria's efforts to expand access to power in accordance with Sustainable Development Goal 7.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Uncontrolled Keywords: | Short-term forecasting Artificial neural network ANN Day-ahead forecasting |
| Subjects: | T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science Faculty of Engineering, Science and Mathematics > School of Engineering Sciences |
| Depositing User: | nwokealisi |
| Date Deposited: | 07 Aug 2023 09:56 |
| Last Modified: | 07 Aug 2023 09:56 |
| URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/17245 |
Actions (login required)
 |
View Item |
