Forecasting the energy demand in Malaysia using genetic algorithm
Energy is the building block of achieving sustainable socio-economic development and environmental goals of human development. Thus, each nation is keen on complete energy planning and management for the purpose of sustainable development. In Malaysia, statistics show that the energy consumption per...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/50838/25/SayyedMohsenHashemiEsmaeilAbadiMFKM2014.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Energy is the building block of achieving sustainable socio-economic development and environmental goals of human development. Thus, each nation is keen on complete energy planning and management for the purpose of sustainable development. In Malaysia, statistics show that the energy consumption per capita from year 2000 as 1.26 ton of oil equivalent (toe)/person has increased steadily to 1.47 toe/person in 2010. One of the issues is establishing appropriate policy and managing the energy to support such a huge increase in energy demand. Two broad categories of energy management are supply-side and demand-side management. In recent decades, demand-side management has been on the focus for a number of reasons. One of the most important features of demand-side management is having a reliable outlook of the energy consumption in order to minimize the gap between the supply and demand of energy. In harmony with this need, the objectives of this study are to develop an energy demand model and forecast the entire energy demand of Malaysia. The model implements different macroeconomic indicators including gross domestic product (GDP), import and export statistics and population to estimate the total energy consumption in all sectors of Malaysia over a period of ten years. Through the review of literature and considering the current circumstances of the case study the most appropriate model and methodology to solve the problem is selected. The selected model is a causal regression model. The tool to solve this model is Genetic Algorithm (GA) and MATLAB software is used to develop and run the model. Finally, the results are compared with a similar study, a sensitivity analysis is done and it is discusses how the study has reached its objectives accordingly. |
|---|