Electrical Computer Engineering
Permanent URI for this collectionhttps://etd.hu.edu.et/handle/123456789/74
Browse
1 results
Search Results
Item Peak Load Forecasting on a Case Study of Ethiopian Electricity Demand(Hawassa University, 2018-10-27) Abebaw GashawLoad forecasting is a way of estimating what future electric load will be for a given forecast horizon based on the available information. Peak load forecasting is the procedure to predict future peak loading conditions. This thesis work is a study about Ethiopian peak load forecasting for the next 10 years. In this thesis Hybrid method used for the peak load forecasting, the method is the combination of two models: (i) econometric model, which uses the multiple regression techniques and (ii) end use model which use the data directly from the user demand. The econometric approach combines economic theory and statistical techniques for forecasting. The approach estimates the relationship between peak load (dependent variables) and load influencing factor. In this thesis the economic and demographic factors are considered. In other word Gross Domestic Product (GDP) of Ethiopia and population of Ethiopia are the selected factors. The econometric approach combines economic theory and statistical techniques for forecasting electricity demand. In the econometric model multiple regression technique is used for mathematical analysis. This analysis is further compared with ARMAX mathematical model. A raw data regarding load demand covering previous period of five years data is used for this study. In this work peak load is used. The GDP and population of previous data with load data are used to get coefficients .The Mean Forecasting Error (MFE) also calculated to reduce the error. Using this coefficients and error in the mathematical equations, the next ten years forecast result is found. The study also utilized c-sharp software and forecasted the Ethiopian ten years peak load demand and compared with the econometric method load forecasted data. End-use model focuses on the various uses of electricity in the users. These models are based on the principle that electricity demand is derived from customer demand. Thus end-use model explains load demand as a function of the number of users. I In this thesis the newly commenced load consumed sector is independently analyzed and data collected. The end-use modeling, econometric modeling, and their combinations are the most often used methods for long-term load forecasting. Long-term forecasts include the forecasts on the population changes, economic development, industrial construction, and technology development. Here finally this thesis combines the two models and the 10 years forecasted result found by adding the models result