Browsing by Author "Kichonge, Baraka"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Analysis of Tanzanian Energy Demand Using Artificial Neural Network and Multiple Linear Regression
    (2014-12) Kichonge, Baraka; Tesha, Thomas; Mkilaha, Iddi; John, Geoffrey
    Analysis of energy demand is of a vital concern to energy systems analysts and planners in any nation. This paper present artificial neural network-multilayer perceptron (ANNMLP) and multiple linear regression (MLR) techniques for the analysis of energy demand in Tanzania. The techniques were employed to analyze the influence of economic, energy and environment indicators models in predicting the energy demand in Tanzania. Statistical performance indices were used to evaluate the prediction ability of economic, energy and environment indicators models using ANN-MLP and MLR techniques. Predicted responses values of ANN-MLP and MLR techniques were then compared to determine their closeness with actual data values for determining the best performing technique. The results from ANN-MLP and MLR techniques showed the best model for predicting the energy demand in Tanzania were from energy indicators as opposed to economic and environmental indicators. The ANN-MLP prediction values had a correlation coefficient (CC) of 0.9995 and mean absolute percentage error (MAPE) of 0.67% outperforming the MLR technique whose CC and MAPE values were 0.9993 and 0.83% respectively. ANN-MLP technique graphical presentation of actual against predicted values showed close relationship between actual and predicted values as opposed to the MLR technique whose predicted values deviated much from actual values. Analysis of results from both techniques conclude that ANN-MLP outperform MLR technique in predicting energy demand in Tanzania.
  • Thumbnail Image
    Item
    Modeling Future Energy Demand for Tanzania
    (2013-12) Kichonge, Baraka; John, Geoffrey; Mkilaha, Iddi; Hameer, Sameer
    This paper present modelling of long-term energy demand forecast in the main economic sectors of Tanzania. The forecast of energy demand for all economic sectors is analyzed by using the Model for Analysis of Energy Demand (MAED) for a study period from 2010-2040. In the study three scenarios namely business as usual (BAU), low economic consumption (LEC) and high economic consumption scenario (HEC) were formulated to simulate possible future long-term energy demand based on socio-economic and technological development with the base year of 2010. Results from all scenario suggests an increased energy demand in consuming sectors with biomass being a dominant energy form in service and household sectors in a study period. Predicted energy demand is projected to increase at a growth rate of 4.1% and reach 74 MTOE in 2040 under BAU scenario. The growth rates for LEC and HEC are projected at 3.5% and 5.1% reaching 62 MTOE and 91 MTOE in 2040 respectively. Electricity demand increases at a rate of 8.5% to reach 4236 kTOE in 2040 under BAU scenario while electricity demand under LEC and HEC increases to 3693 kTOE and 5534 kTOE in 2040 respectively. Sectrorial predicted demand results under both scenarios determines high demand of biomass for service and household sectors with decreasing demand of biomass in industry sector. Transport sectors predicted energy demand pattern suggests an increased demand in passenger transport than freight transport in both scenarios. Final energy demand per capita in both scenario show an increased trend with lower growth in LEC scenario while there is a decrease in energy intensity throughout study period.
  • Thumbnail Image
    Item
    Modelling energy supply options for electricity generations in Tanzania
    (2015-07) Kichonge, Baraka; John, Geoffrey; Mkilaha, Iddi
    The current study applies an energy-system model to explore energy supply options in meeting Tanzania's electricity demands projection from 2010 to 2040. Three economic scenarios namely; business as usual (BAU), low economic consumption scenario (LEC) and high economic growth scenario (HEC) were developed for modelling purposes. Moreover, the study develops dry weather scenario to explore how the country's electricity system would behave under dry weather conditions. The model results suggests: If projected final electricity demand increases as anticipated in BAU, LEC and HEC scenarios, the total installed capacity will expand at 9.05%, 8.46% and 9.8% respectively from the base value of 804.2MW. Correspondingly, the model results depict dominance of hydro, coal, natural gas and geothermal as least-cost energy supply options for electricity generation in all scenarios. The alternative dry weather scenario formulated to study electricity system behaviour under uncertain weather conditions suggested a shift of energy supply option to coal and natural gas (NG) dominance replacinghydro energy. The least cost optimization results further depict an insignificant contribution of renewable energy technologies in terms of solar thermal, wind and solar PV into the total generation shares. With that regard, the renewable energy penetration policy option (REPP), as an alternative scenario suggests the importance of policy options that favour renewable energy technologies inclusion in electricity generation. Sensitivity analysis on the discount rate to approximate theinfluence of discount rate on the future pattern of electricity generation capacity demonstrated that lower values favourwind and coal fired power plants, while higher values favour the NG technologies. Finally, the modelling results conclude the self-sufficiency of the country in generating future electricity using its own energy resources.
  • Thumbnail Image
    Item
    Prediction of Tanzanian Energy Demand using Support Vector Machine for Regression (SVR)
    (2015-01) Kichonge, Baraka; John, Geoffrey; Tesha, Thomas; Mkilaha, Iddi
    This study discusses the influences of economic, energy and environment indicators in the prediction of energy demand for Tanzania applying support vector machine for regression (SVR). Economic, energy and environment indicators were applied to formulate models based on time series data. The experimental results showed the supremacy of the polynomial-SVR kernel function and the energy indicators model in providing the transformation, which achieved more accurate prediction values. The energy indicators model had a correlation coefficient (CC) of 0.999 as equated to 0.9975 and 0.9952 with PUKF-SVR kernels for economic and environment indicators model. The energy indicators model closeness of predicted values as compared to actual values was the best as compared to economic and environment indicators models. Furthermore, root mean squared error (RMSE), mean absolute error (MAE), root relative squared error (RRSE) and relative absolute error (RAE) of energy indicators model were the lowest. Long-run sustainable development of the energy sector can be achieved with the use of SVR-algorithm as prediction tool of future energy demand.