This article is intended to compare the behavior of a model to predict demand quantity of electricity in the country, Thailand. By the way, this article is gathered, including linear regression (Linear Multiple Regression MLR) multiples artificial neural network (ANN Artificial Neural Network) theory of grey (GREY MODEL GM), the Seasonal Autoregressive Integrated Moving Average (SARIMA and ARMA (Autoregressive Integrated model Movin.G Average) also summarizes the advantages and constraints, including the forecast of each model, and compare the performance of a method in research. It would be a good model for the analysis of the results of the analysis must be the least error and what is indispensable is to be. Define independent variables, and the appropriate for each particular model can predict prognosis, both as a point (Point Forecast) and the interval (Interval Forecast) forecast ahead of time how many intervals. But it's not normal to predict ahead of time because it has several ranges of values to predict that differ from the actual values so. When the actual value at the next interval, then it should be brought up at the time to the equation to predict to find the most appropriate.
การแปล กรุณารอสักครู่..