Abstract:
Renewable storage device has built a significant place in energy sector. Recently this has achieved a vast development all around the world. With that motivation, this research is focused on forecasting the energy consumption of a BTS of the following day based on previous energy consumption model, and comparing the forecasting results with several popular Short Term Load Forecasting models.
Load forecasting is an important component for power system energy management. Precise load forecasting helps the electric utility to make unit commitment decisions, reduces spinning reserve capacity and schedule device maintenance plan properly. It also reduces the generation cost and increases reliability of power systems. In this work, an artificial neural network (ANN) for short term load forecasting is attempted along with support vector machine (SVM) and auto regressive integrated moving average (ARIMA). Time and load of same week day load are used as the independent variables for short term load forecasting. Based on the time and similar previous day load, ANN, ARIMA and SVM models are built, which are eventually used for the short term load forecasting. This comparison leads to the conclusion that, the forecasting performance of ANN gives more appropriate results than the other two techniques. ANN model forecasted the energy more accurately with increasing number of neurons. Using the curve fitting technique a mathematical model has been established from the data to independently measure the errors of the model. MATLAB SIMULINK package is used here in this work for system designing and simulation. Load data from different BTS is considered for the short term load forecasting.
