AN APPLICATION OF FUZZY LOGIC FOR SHORT-TERM LOAD FORECAST OF MALAYSIA LOAD DEMAND

This final year project report presents an approach for short-term load forecast
problem, based on fuzzy logic technique. As depicted in Chapter 1, in order for all
generating stations to operate at maximum efficiency and minimum operating costs,
National Load Dispatch Centre must be able to forecast the load demanded by
customers. In addition, based on the literature reviews in Chapter 2, conventional
methods have several limitations such as require complex mathematical formulation
and very time consuming. Apart from that, there are several factors that affect shortterm
load forecast such as time factors and weather conditions. 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 day forecasted load. The iuzzyTECH
software is used to develop a one-day-ahead load forecasting model together with
Microsoft Excel as the data interface. The test results, as shown 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 to below
3%. 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 ofthe National Load Dispatch Centre in Bangsar, Kuala Lumpur.