Load forecasting is an essential part for the power system planning and operation. In this project modeling and design of artificial neural network, regression tree, multiple linear regression and curve fitting model for load forecasting is carried out in the BUET academic and residential area. These approaches help to reduce the problems associated with conventional method and has the advantage of learning directly from the historical data. The forecasting models here have used data such as past load, weather information like dew point and temperatures. Once the models are trained for the past set of data it can give a prediction of future load. This reduces the capital investment reducing the equipment to be installed. The actual data are taken from the BUET POWER PLANT. The data of load for the year 2005 is collected for a particular region and used to create an arbitrary dataset for 20 years. The main objective is to forecast the amount of electricity needed for better load distribution in the area.
The load forecasting techniques are categorized into three groups. The selection of a forecasting Method relies on several factors including the relevance and availability of historical data, the forecast horizon, the level of accuracy for weather data, desired prediction accuracy, and so forth. Accordingly, selecting the proper load forecasting approach primarily depends on the time horizon of the prediction. The categories of Load Forecasting Techniques are:
- Short Term Load Forecasting (STLF)
- Medium Term Load Forecasting (MTLF)
- Long Term Load Forecasting (LTLF)
Traditional forecasting technique includes methods like,
- Regression
- Multiple Regression
- Exponential Smoothing (Curve Fitting)
- Iterative Reweighted Least-Squares
Modified traditional technique have methods like,
- Adaptive Demand Forecasting
- Stochastic Time Series
- Support Vector Machine based Techniques
