- Title
- Statistical tools for consolidation of energy demand forecasts
- Creator
- Motsomi, Abel Pholo
- Subject
- Power resources -- Forecasting
- Subject
- Energy conservation -- Standards
- Subject
- Electric utilities
- Date Issued
- 2012
- Date
- 2012
- Type
- Thesis
- Type
- Masters
- Type
- MSc
- Identifier
- vital:10573
- Identifier
- http://hdl.handle.net/10948/d1011578
- Identifier
- Power resources -- Forecasting
- Identifier
- Energy conservation -- Standards
- Identifier
- Electric utilities
- Description
- The electricity market in the South African economy uses specialised instruments in forecast-ing the energy load to be delivered. The current status quo operates with several forecasters from different offices, departments or businesses predicting for different purposes. This be-comes a challenge to derive a consolidated forecast. This study has attempted to develop a consolidating instrument that will merge all the forecasts from different offices, departments or businesses into one so-called ‘official forecast’. Such an instrument should be able to predict with accuracy the anticipated usage or demand. Article [18] examined patterns across G7 countries and forecasters to establish whether the present bias reflects the inefficient use of information, or whether it reflects a rational re- sponse to financial, reputation and other incentives operating for forecasters. This bias is particularly true for any electricity utility as forecasting is undertaken by different divisions; therefore each division has its own incentives. For instance, the generation division will tend to overstate their forecasts so as that there is no possibility of a shortage, whereas distri- bution (sales) might understate so as to give the impression of being profitable when more units are sold to consumers. Thus, the study attempts to rectify this bias by employing statistical tools in consolidating these forecasts. The results presented in this paper propose a newly developed procedure of consolidating energy demand forecasts from different users and accounting for different time horizons. Predicting for the short-term and long-term involves different measuring tools, which is one aspect of prediction this paper tackles.
- Format
- x, 72 leaves
- Format
- Publisher
- Nelson Mandela Metropolitan University
- Publisher
- Faculty of Science
- Language
- English
- Rights
- Nelson Mandela Metropolitan University
- Hits: 572
- Visitors: 715
- Downloads: 164
Collections
NMMU School of Computer Science, Mathematics, Physics and Statistics
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCEPDF | 866 KB | Adobe Acrobat PDF | View Details Download |