Medium Term Load Forecasting Using Statistical Feature Self Organizing Maps (SOM)

Nik Ibrahim, Nik Nur Atira (2017) Medium Term Load Forecasting Using Statistical Feature Self Organizing Maps (SOM). Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text (24 Pages) Medium Term Load Forecasting Using Statistical Feature Self Organizing Maps (SOM).pdf - Submitted Version Download (314kB)

Abstract

Load forecasting is an essential tool for power system activity and planning. With increasing in development and the expansion of power system, it is important for the electrical utility to make a decision in ensuring that there would be enough supply of electricity to deal with the increasing demand. This research presents the Medium Term Load Forecasting using the artificial neural networks: Kohonen‟s Self-organizing Maps. The main purpose of this project is to understand the ability Self-Organizing Maps in forecasting the load demand, and to train and test via Self-Organizing Maps method using the selected features (average temperature, K; holiday list; seasons). The data are provided by the Global Energy Forecasting Competition (GEFCom2012). This project will focus on the missing data from year 2005 and 2006 for the load forecasting. The total power and average temperature are calculated for each month in the year 2004, 2005 and 2006. The data from the year 2004 will be trained to test and forecast the data for the year 2005 while data from 2005 will be used to train for testing and forecasting the year 2006. The load data will be train, test and forecast using SOM Toolbox in MATLAB software. The accuracy of the forecasted data will be determined by calculating error of each forecasted data by comparing with the actual data. Then the Mean Absolute Percentage Error is compute to determine the accuracy of the results.

Actions (login required)

View Item