Browsing by Author "Agyen, Kwaku James"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Time series modeling and forecasting of the demand of some petroleum products in Ghana
    (2012) Agyen, Kwaku James
    The study is an application of Box-Jenkins ARIMA modelling and forecasting to petroleum products demand in Ghana. Monthly data on demand levels from January, 1999 to December, 2010 of petroleum products namely; Gas Oil, Liquefied Petroleum Gas (LPG) and Premix Fuel were analysed and forecasts made 12 months ahead. Thus, after stationarity was established through differencing of the data, the sample ACF and the sample Partial Autocorrelation Function (PACF) of the differenced data were considered to generate possible models after which the AIC, AICc and BIC of the candidate models under the various data were examined and those candidate models with the smallest AIC, AICc and BIC were chosen as the best-fit models among the candidate models and used for forecasting. The best fit model for the National Gas Oil demand, National LPG demand and National Premix demand levels were found to be ARIMA(1,1,3), ARIMA(2,1,3) and SARIMA(3,1,0)(2,0,0)[12] respectively.
  • Thumbnail Image
    Item
    Transportation Model for Waste Collection in the Kumasi Metropolis
    ( January 2011) Agyen, Kwaku James
    This thesis seeks to provide waste management companies, especially Kumasi Metropolitan Assembly-Waste Management Department (KMA-WMD) an alternative way of allocating limited collection trucks over the numerous collection points and to ensure minimum total cost. Data were collected from the KMA-WMD their contracted companies as regards to the waste generation levels of all the collection points in the metropolis, and how much of these refuse are collected to the two dump sites over a period of three months. The data gathered were modelled as linear programming problem with clear objective functions for each month under consideration subject to its associated constraints. These objective functions and constraints were minimized using a computer software solver, EXCEL, to generate an optimal solution. The objective function value represented the minimized cost for the period under consideration if the waste generation levels of all the collection points were constant within the data collection period.