GDC-UTP ELECTRICITY FORECASTING USING FUZZY SYSTEM

This report represents the approach for short term load forecasting by using fuzzy logic
approach. As depicted in Chapter I, in order for Gas District Cooling to operate at
maximum efficiency and minimum generating costs, it must be able to forecast the load
demanded by the sole customer, University Teknologi PETRONAS. Based on the
literature review in Chapter 2, there are several fuctors that affect the forecasting such as
weather condition, the type offorecast day and history of the load demand. In Chapter 3
of this report, this project proposes a load forecasting method by using fuzzy logic
approach, based on similar days to obtain the next week's forecasted load. The
fuzzyTECH software is used to develop a week-week-ahead load forecasting model
together with Microsoft Excel as data interface. The test result, as shown in in Chapter
4, show that the proposed forecasting method could provide a considerable
improvement of the forecasting accuracy especially as it shows how to reduce forecast
error. Several recommendations for future improvements are included in Chapter 5. The
suitability of the proposed approach is illustrated through an application to actual load
data of the Gas District Cooling ofUniversity Teknologi PETRONAS.