Modelling electricity demand in South Africa
| dc.contributor.advisor | Chikobvu, Delson | |
| dc.contributor.author | Sigauke, Caston | |
| dc.date.accessioned | 2015-11-10T11:59:26Z | |
| dc.date.available | 2015-11-10T11:59:26Z | |
| dc.date.copyright | 2014-01 | |
| dc.date.issued | 2014-01 | |
| dc.date.submitted | 2014-01 | |
| dc.description.abstract | English: Peak electricity demand is an energy policy concern for all countries throughout the world, causing blackouts and increasing electricity tariffs for consumers. This calls for load curtailment strategies to either redistribute or reduce electricity demand during peak periods. This thesis attempts to address this problem by providing relevant information through a frequentist and Bayesian modelling framework for daily peak electricity demand using South African data. The thesis is divided into two parts. The first part deals with modelling of short term daily peak electricity demand. This is done through the investigation of important drivers of electricity demand using (i) piecewise linear regression models, (ii) a multivariate adaptive regression splines (MARS) modelling approach, (iii) a regression with seasonal autoregressive integrated moving average (Reg-SARIMA) model (iv) a Reg-SARIMA model with generalized autoregressive conditional heteroskedastic errors (Reg-SARIMA-GARCH). The second part of the thesis explores the use of extreme value theory in modelling winter peaks, extreme daily positive changes in hourly peak electricity demand and same day of the week increases in peak electricity demand. This is done through fitting the generalized Pareto, generalized single Pareto and the generalized extreme value distributions. One of the major contributions of this thesis is quantification of the amount of electricity which should be shifted to off peak hours. This is achieved through accurate assessment of the level and frequency of future extreme load forecasts. This modelling approach provides a policy framework for load curtailment and determination of the number of critical peak days for power utility companies. This has not been done for electricity demand in the context of South Africa to the best of our knowledge. The thesis further extends the autoregressive moving average-exponential generalized autoregressive conditional heteroskedasticity model to an autoregressive moving average exponential generalized autoregressive conditional heteroskedasticity-generalized single Pareto distribution. The benefit of this hybrid model is in risk modelling of under and over demand predictions of peak electricity demand. Some of the key findings of this thesis are (i) peak electricity demand is influenced by the tails of probability distributions as well as by means or averages, (ii) electricity demand in South Africa rises significantly for average temperature values below 180C and rises slightly for average temperature values above 220C and (iii) modelling under and over demand electricity forecasts provides a basis for risk assessment and quantification of such risk associated with forecasting uncertainty including demand variability. | en_ZA |
| dc.description.abstract | Afrikaans: Spitselektrisiteitsaanvraag is vir alle lande regdeur die wˆereld ’n energiebeleidskwessie en veroorsaak verdonkerings en toenemende elektrisiteitstariewe vir allle verbruikers. Dit verg ladinginkortingstrategie¨e om ´of elektrisiteitsaanvraag tydens spitstye te herversprei ´of omdit te verminder. Di´everhandeling poog om hierdie probleem aan te spreek deur toepaslike inligting deur ’n frekwentistiese en Bayes-modelraamwerk vir daaglikse spitselektrisiteitsaanvraag te verskaf met behulp van Suid-Afrikaanse data. Die verhandeling word in twee dele verdeel. Die eerste gedeelte handel oor modellering van korttermyn daaglikse spitselektrisiteitsaanvraag. Dit word bereik deur die belangrike dryfvere van elektrisiteitsaanvraag te ondersoek met behulp van (i) stuksgewyse lineˆere regressiemodelle, (ii) ’nmeerveranderlike aanpassende regressielatmodelbenadering (MARS in Engels), (iii) ’n regressie met seisoenale outoregressiewe ge¨ıntegreerde bewegingsgemiddeld-model (Reg-SARIMA in Engels) en (iv) ’n Reg-SARIMA-modelmet veralgemeende outoregressiewe voorwaardelike heteroskedastiese foute (Reg-SARIMA-GARCH in Engels). Die tweede gedeelte van die verhandeling verken die gebruik van ekstreemwaardeteorie in die modellering van winterspitstye, ekstreem-daaglikse positiewe veranderinge in uurlikse spitselektrisiteitsaanvraag en selfde dag van die week verhogings in spitselektrisiteitsaanvraag. Dit word bereik deur die veralgemeende Pareto, veralgemeende enkel-Pareto en die veralgemeende ekstreemwaardeverdeling, in te pas. Een van die hoofbydraes van die verhandeling is die kwantifisering van die Opsomming aantal elektrisiteit wat na niespitstydperke toe geskuif moet word. Dit word bereik deur akkurate assessering van die vlak en herhaling van toekomsitge ladingvoorspellings. Di´emodelbenadering verskaf ’n beleidsraamwerk vir ladinginkorting en die bepaling van die aantal kritieke spitsdae vir krag-utiliteitsmaatskappye. Dit is, na ons beste wete, nie vir elektrisiteitsaanvraag in die Suid-Afrikaansekonteks gedoen nie. Die verhandeling brei verder die outoregressiewe bewegende gemiddelde eksponensiaal veralgemeende outoregressiewe voorwaardelike heteroskedastisiteitsmodel uit na ’n outoregressiewe bewegende gemiddelde eksponensiaal veralgemeende outoregressiewe voorwaardelike heteroskedastisiteit-veralgemeende enkel-Paretoverdeling. Die voordeel van hierdie hibriede model is in risikomodellering van onder-en ooraanvraagvoorspellings van spitselektrisiteitsaanvraag. Sommige van die hoofbevindinge van die verhandeling is dat (i) spitselektrisiteitsaanvraag be¨ınvloed word deur die waarskynlikheidsverdelings asook deur die gemiddelde, (ii) elektrisiteitsaanvraag in Suid-Afrika vir gemiddelide temperatuurwaardes onder 180C aansienlik vermeerder en vir gemiddelde temperatuurwaardes bo 220C effens vermeerder en (iii) modellering van onder-en ooraavraag-elektrisiteitsvoorspellings ’n basis vir risiko-assessering en kwantifisering van sulke risikos wat verband hou met voorspellingsonsekerheid, insluitend aanvraagveranderlikheid, verskaf. | af |
| dc.identifier.uri | http://hdl.handle.net/11660/1569 | |
| dc.language.iso | en | en_ZA |
| dc.publisher | University of the Free State | en_ZA |
| dc.rights.holder | University of the Free State | en_ZA |
| dc.subject | Temperature | en_ZA |
| dc.subject | Risk management | en_ZA |
| dc.subject | Peak electricity demand | en_ZA |
| dc.subject | Load management | en_ZA |
| dc.subject | Maximal data information prior | en_ZA |
| dc.subject | Frequentist | en_ZA |
| dc.subject | Extreme value theory | en_ZA |
| dc.subject | Bayesian inference | en_ZA |
| dc.subject | Bayesian statistical decision theory | en_ZA |
| dc.subject | Mathematical statistics | en_ZA |
| dc.subject | Electric power distribution -- South Africa | en_ZA |
| dc.subject | Electric power consumption -- South Africa | en_ZA |
| dc.subject | Thesis (Ph.D. (Mathematical Statistics and Actuarial Science))--University of the Free State, 2014 | en_ZA |
| dc.title | Modelling electricity demand in South Africa | en_ZA |
| dc.type | Thesis | en_ZA |