Speaker
Description
Naleli Jubert Matjelo1, Makhamisa Senekane2, Mhlambululi Mafu3, Sebota Mokeke1, Lerato Lerato4
1Department of Physics and Electronics, National University of Lesotho, Roma, Lesotho
2Institute for Intelligent Systems, University of Johannesburg, Johannesburg, South Africa
3Department of Physics and Astronomy, Botswana International University of Science and Technology, Palapye, Botswana
4Department of Mathematics & Computer Science, National University of Lesotho, Roma, Lesotho
Short-term power consumption forecasting is increasingly playing a crucial role in ensuring the optimal management of power systems. One approach that can be utilized for forecasting short-term power consumption involves using Machine Learning (ML) models. In this paper, we report the use of Machine Learning models to forecast one hour-ahead power consumption. Machine Learning models used include those based on Artificial Neural Networks (ANN) and those based on boosting. We then compared the performance results for both ANN-based and boosting-based techniques. The results obtained from the study reported in this paper underline the importance of using Machine Learning models for short-term power consumption.
Level for award;(Hons, MSc, PhD, N/A)?
N/A
| Apply to be considered for a student ; award (Yes / No)? | No |
|---|
