Electrical Load Forecasting for Small Scale Power System Using Fuzzy Logic

Electrical load forecasting is an essential activity and important function in power
plant generation planning. It helps the plant involved to make appropriate decision on
planning like shutdown or turnaround, decision on purchasing and generating electric
power, load switching and infrastructure development. This report discusses the
approach for short term load forecasting using fuzzy logic model. A background
study concerning the importance of load forecasting in Gas District Cooling of
Universiti Teknologi PETRONAS is portrayed. Literature review written consists of
brief explanation of forecasting as well as few factors that affect the forecasting such
as day type of forecast day, weather condition and previous load of the demand.
These factors contribute great impact to distinguish weekly electricity load behavior.
In order to achieve minimum error of forecasting, a suitable method which is using
fuzzy logic approach is proposed. The fuzzy TECH software is used in developing a
week to week ahead load forecasting model, together with Microsoft Excel. The
model was tested and gives the results of satisfactory forecasting error. The model
used is improved in order to obtain higher accuracy of load forecasting when it is
testing with the actual data.