Forecasting hourly electricity demand in South Africa using machine learning models

Simple item page
dc.contributor.advisorSigauke, Caston
dc.contributor.advisorBere, Alphonce
dc.contributor.authorThanyani, Maduvhahafani
dc.date.accessioned2020-10-05T12:46:16Z
dc.date.available2020-10-05T12:46:16Z
dc.date.issued2020-08-12
dc.descriptionMSc (Statistics)en_ZA
dc.descriptionDepartment of Statistics
dc.description.abstractShort-term load forecasting in South Africa using machine learning and statistical models is discussed in this study. The research is focused on carrying out a comparative analysis in forecasting hourly electricity demand. This study was carried out using South Africa’s aggregated hourly load data from Eskom. The comparison is carried out in this study using support vector regression (SVR), stochastic gradient boosting (SGB), artificial neural networks (NN) with generalized additive model (GAM) as a benchmark model in forecasting hourly electricity demand. In both modelling frameworks, variable selection is done using least absolute shrinkage and selection operator (Lasso). The SGB model yielded the least root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) on testing data. SGB model also yielded the least RMSE, MAE and MAPE on training data. Forecast combination of the models’ forecasts is done using convex combination and quantile regres- sion averaging (QRA). The QRA was found to be the best forecast combination model ibased on the RMSE, MAE and MAPE.en_ZA
dc.description.sponsorshipNRFen_ZA
dc.format.extent1 online resource (xiii, 74 leaves : color illustrations)
dc.identifier.apacitationThanyani, M. (2020). <i>Forecasting hourly electricity demand in South Africa using machine learning models</i>. (). . Retrieved from http://hdl.handle.net/11602/1595en_ZA
dc.identifier.chicagocitationThanyani, Maduvhahafani. <i>"Forecasting hourly electricity demand in South Africa using machine learning models."</i> ., , 2020. http://hdl.handle.net/11602/1595en_ZA
dc.identifier.citationThanyani, Maduvhahafani (2020) Forecasting hourly electricity demand in South Africa using machine learning models. University of Venda, South Africa.<http://hdl.handle.net/11602/1595>.
dc.identifier.ris TY - Dissertation AU - Thanyani, Maduvhahafani AB - Short-term load forecasting in South Africa using machine learning and statistical models is discussed in this study. The research is focused on carrying out a comparative analysis in forecasting hourly electricity demand. This study was carried out using South Africa’s aggregated hourly load data from Eskom. The comparison is carried out in this study using support vector regression (SVR), stochastic gradient boosting (SGB), artificial neural networks (NN) with generalized additive model (GAM) as a benchmark model in forecasting hourly electricity demand. In both modelling frameworks, variable selection is done using least absolute shrinkage and selection operator (Lasso). The SGB model yielded the least root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) on testing data. SGB model also yielded the least RMSE, MAE and MAPE on training data. Forecast combination of the models’ forecasts is done using convex combination and quantile regres- sion averaging (QRA). The QRA was found to be the best forecast combination model ibased on the RMSE, MAE and MAPE. DA - 2020-08-12 DB - ResearchSpace DP - Univen KW - Electricity demand forecasting KW - Machine learning KW - Lasso KW - Neutral networks KW - Support vector regression KW - Forecasting KW - Forecast combination LK - https://univendspace.univen.ac.za PY - 2020 T1 - Forecasting hourly electricity demand in South Africa using machine learning models TI - Forecasting hourly electricity demand in South Africa using machine learning models UR - http://hdl.handle.net/11602/1595 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11602/1595
dc.identifier.vancouvercitationThanyani M. Forecasting hourly electricity demand in South Africa using machine learning models. []. , 2020 [cited yyyy month dd]. Available from: http://hdl.handle.net/11602/1595en_ZA
dc.language.isoenen_ZA
dc.rightsUniversity of Venda
dc.subjectElectricity demand forecastingen_ZA
dc.subjectUCTDen_ZA
dc.subjectLassoen_ZA
dc.subjectNeutral networksen_ZA
dc.subjectSupport vector regressionen_ZA
dc.subjectForecastingen_ZA
dc.subjectForecast combinationen_ZA
dc.subject.ddc333.7930968
dc.subject.lcshElectricity -- South Africa
dc.subject.lcshElectrification -- South Africa
dc.subject.lcshElectric power distribution -- South Africa
dc.subject.lcshElectric power consumption -- South Africa
dc.subject.lcshElectric power production -- South Africa
dc.subject.lcshRenewable energy resources -- South Africa
dc.titleForecasting hourly electricity demand in South Africa using machine learning modelsen_ZA
dc.typeDissertationen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dissertation - Thanyani, m.-.pdf
Size:
589.03 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Theses and Dissertations
Theses and Dissertations