Long-term water-energy demand prediction using a regression model: a case study of Addis Ababa city
As part of sustainable urban planning, the demand for water and energy (WE) should also be addressed. The Waikato Environment for Knowledge Analysis (WEKA) modeling tool was employed to relate the historical WE consumptions with the population and economic growth scenarios using a linear regression...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IWA Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/5e556471a7da402a9c7b54209aaa8037 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | As part of sustainable urban planning, the demand for water and energy (WE) should also be addressed. The Waikato Environment for Knowledge Analysis (WEKA) modeling tool was employed to relate the historical WE consumptions with the population and economic growth scenarios using a linear regression model. The performance of the model was evaluated to properly identify the most influential drivers in each sector. The WE demand prediction was made for each year from 2016 up to 2050. Consequently, the long-term time interval for demand analysis is important rather than the consequent year for planning. The total electric energy demand including residential, street-lighting, commercial and industrial sectors was estimated to be around 14,000 and 53,000 Giga Watt hour (GWh) for the years 2030 and 2050, respectively. These years' forecasted petroleum demand was around 8840 and 30,140 for diesel, 13,860 and 52,700 for gasoline, and 1230 and 9890 GWh for kerosene and the water demand including residential, commercial and industrial sectors were 520 and 1600 million cubic meters (MCM). The proposed methodology can comfortably be used to predict the urban WE demand corresponding to economic (gross domestic product and per capita income) and population growth at different scenarios which could support policy makers. HIGHLIGHTS
Predicting long-term water-energy demand is important for planning.;
A linear regression model is used for long-term water-energy demand predicting.;
The water-energy demand in urban areas is increasing.;
Population and economic growth are the main factors which are highly affecting the urban water-energy demand.;
Identifying the most influential drivers on water-energy demand is important for water-energy supply planning.;
Technological factors (such as water loss, energy loss) are commonly considered in demand prediction.; |
|---|