{"id":{"repo_id":"venda","oai_identifier":"oai:univendspace.univen.ac.za:11602/3213"},"canonical_url":"https://search.dev.ndltd.org/etd/venda/oai:univendspace.univen.ac.za:11602/3213","repository":{"repo_id":"venda","name":"University of Venda","base_url":"https://univendspace.univen.ac.za/server/oai/request"},"display":{"title":"Modelling Extreme Forecast Errors in Wind Energy Using South African Wind Farms","abstract":"Accurate wind energy forecasting has become crucial for preserving grid stability and guaranteeing a consistent power supply in the light of South Africa’s expanding shift to renewable energy. As they have a direct impact on scheduling, dispatch choices, and reserve allocation, extreme prediction errors in particular cause serious operational and financial issues. This study uses data from a collection of wind farms in South Africa to model shortterm extreme forecast mistakes in wind energy generation. The blended generalised extreme value (bGEV) distribution and extremal mixture models are two sophisticated extreme value modelling frameworks whose predictive accuracy is compared in this study. An additive quantile regression (AQR) model is used to derive wind energy forecast residuals. Both modelling techniques were then used to identify tail behaviour associated with extreme under- or over-prediction. The findings demonstrate that, in comparison to extremal mixture models, the bGEV model o!ers more accurate, dependable, and well-calibrated predictions of severe forecast errors. These results emphasise how crucial strong and adaptable extreme value models are to enhancing operational wind energy forecasting in South Africa. By showing how better modelling of extreme errors will enhance power system planning, lower uncertainty, and facilitate more e!ective integration of wind energy into the national grid, the study further advances the renewable energy industry. To improve prediction accuracy and deepen system-level insights, future research should take into account geographically disaggregated data from individual wind farms.","abstract_html":"Accurate wind energy forecasting has become crucial for preserving grid stability and guaranteeing a consistent power supply in the light of South Africa’s expanding shift to renewable energy. As they have a direct impact on scheduling, dispatch choices, and reserve allocation, extreme prediction errors in particular cause serious operational and financial issues. This study uses data from a collection of wind farms in South Africa to model shortterm extreme forecast mistakes in wind energy generation. The blended generalised extreme value (bGEV) distribution and extremal mixture models are two sophisticated extreme value modelling frameworks whose predictive accuracy is compared in this study. An additive quantile regression (AQR) model is used to derive wind energy forecast residuals. Both modelling techniques were then used to identify tail behaviour associated with extreme under- or over-prediction. The findings demonstrate that, in comparison to extremal mixture models, the bGEV model o!ers more accurate, dependable, and well-calibrated predictions of severe forecast errors. These results emphasise how crucial strong and adaptable extreme value models are to enhancing operational wind energy forecasting in South Africa. By showing how better modelling of extreme errors will enhance power system planning, lower uncertainty, and facilitate more e!ective integration of wind energy into the national grid, the study further advances the renewable energy industry. To improve prediction accuracy and deepen system-level insights, future research should take into account geographically disaggregated data from individual wind farms.","abstract_has_math":false,"creators":["Mushadu, Vhonani"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Ravele, T.","Sigauke, C.","Ndogmo, J. C."],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-19","date_published":"2026-05-19","updated_at":"2026-07-27T21:57:55Z","subjects":["bGEV distribution","extreme value theory","extremal mixture models","forecast errors","quantile regression","South African wind farms","Wind energy forecasting","UCTD"],"languages":["en"],"rights":["University of Venda"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://univendspace.univen.ac.za/handle/11602/3213","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ravele, T.","Sigauke, C.","Ndogmo, J. C."]},{"key":"dc:creator","label":"Author","values":["Mushadu, Vhonani"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-06-17T21:55:11Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-17T21:55:11Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-05-19"]},{"key":"dc:relation","label":"Dc Relation","values":["PDF"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["bGEV distribution","extreme value theory","extremal mixture models","forecast errors","quantile regression","South African wind farms","Wind energy forecasting","UCTD"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["University of Venda"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://univendspace.univen.ac.za/handle/11602/3213"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.Sc. in Statistics","Department of Statistics"]},{"key":"dc:description.abstract","label":"Abstract","values":["Accurate wind energy forecasting has become crucial for preserving grid stability and guaranteeing a consistent power supply in the light of South Africa’s expanding shift to renewable energy. As they have a direct impact on scheduling, dispatch choices, and reserve allocation, extreme prediction errors in particular cause serious operational and financial issues. This study uses data from a collection of wind farms in South Africa to model shortterm extreme forecast mistakes in wind energy generation. The blended generalised extreme value (bGEV) distribution and extremal mixture models are two sophisticated extreme value modelling frameworks whose predictive accuracy is compared in this study. An additive quantile regression (AQR) model is used to derive wind energy forecast residuals. Both modelling techniques were then used to identify tail behaviour associated with extreme under- or over-prediction. The findings demonstrate that, in comparison to extremal mixture models, the bGEV model o!ers more accurate, dependable, and well-calibrated predictions of severe forecast errors. These results emphasise how crucial strong and adaptable extreme value models are to enhancing operational wind energy forecasting in South Africa. By showing how better modelling of extreme errors will enhance power system planning, lower uncertainty, and facilitate more e!ective integration of wind energy into the national grid, the study further advances the renewable energy industry. To improve prediction accuracy and deepen system-level insights, future research should take into account geographically disaggregated data from individual wind farms."]},{"key":"dc:title","label":"Title","values":["Modelling Extreme Forecast Errors in Wind Energy Using South African Wind Farms"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ravele, T.","Sigauke, C.","Ndogmo, J. C."],"dc:creator":["Mushadu, Vhonani"],"dc:date":["2026"],"dc:date.accessioned":["2026-06-17T21:55:11Z"],"dc:date.available":["2026-06-17T21:55:11Z"],"dc:date.issued":["2026-05-19"],"dc:description":["M.Sc. in Statistics","Department of Statistics"],"dc:description.abstract":["Accurate wind energy forecasting has become crucial for preserving grid stability and guaranteeing a consistent power supply in the light of South Africa’s expanding shift to renewable energy. As they have a direct impact on scheduling, dispatch choices, and reserve allocation, extreme prediction errors in particular cause serious operational and financial issues. This study uses data from a collection of wind farms in South Africa to model shortterm extreme forecast mistakes in wind energy generation. The blended generalised extreme value (bGEV) distribution and extremal mixture models are two sophisticated extreme value modelling frameworks whose predictive accuracy is compared in this study. An additive quantile regression (AQR) model is used to derive wind energy forecast residuals. Both modelling techniques were then used to identify tail behaviour associated with extreme under- or over-prediction. The findings demonstrate that, in comparison to extremal mixture models, the bGEV model o!ers more accurate, dependable, and well-calibrated predictions of severe forecast errors. These results emphasise how crucial strong and adaptable extreme value models are to enhancing operational wind energy forecasting in South Africa. By showing how better modelling of extreme errors will enhance power system planning, lower uncertainty, and facilitate more e!ective integration of wind energy into the national grid, the study further advances the renewable energy industry. To improve prediction accuracy and deepen system-level insights, future research should take into account geographically disaggregated data from individual wind farms."],"dc:identifier.uri":["https://univendspace.univen.ac.za/handle/11602/3213"],"dc:language.iso":["en"],"dc:relation":["PDF"],"dc:rights":["University of Venda"],"dc:subject":["bGEV distribution","extreme value theory","extremal mixture models","forecast errors","quantile regression","South African wind farms","Wind energy forecasting","UCTD"],"dc:title":["Modelling Extreme Forecast Errors in Wind Energy Using South African Wind Farms"],"dc:type":["Dissertation"]},"updated_at":"2026-07-27T21:57:55Z"}