No abstract

No abstract

Abstract-This article presents the review of the computing models applied for solving problems of midterm load forecasting. The load forecasting results can be used in electricity generation such as energy reservation and maintenance scheduling. Principle, strategy and results of short term, midterm, and long term load forecasting using statistic methods and artificial intelligence technology (AI) are summaried, Which, comparison between each method and the articles have difference feature input and strategy. The last, will get the idea or literature review conclusion to solve the problem of mid term load forecasting (MTLF).

Abstract-1 Load forecasting is very important for operation of electricity companies such as for operation, unit commitment, and planning. This research presents a comparison of mid term load forecasting between multiregional area model (6 neural network models of north, northeast, centre, east, south-east, south-west areas in Thailand) with the factors based on regional area and the whole country area with the factors based on whole country area. The data information composes of the peak load, energy consumption, humidity, rainfall, wind speed, consumer price index, and industrial index recorded from year 1997 to 2007 which are given from many resources in the country. This study shows the results in energy consumption demand forecasting and peak load demand forecasting, case study in Electricity Generating Authority of Thailand (EGAT). Artificial Neural network(ANN) is used with have feed forward back propagation algorithm and LM algorithm.. The experimental results show that the multi-regional area forecasting model can reduce the error and improve the forecast accuracy effectively more than that of the whole country area forecasting model in mid term load forecast.

No abstract