Short-Term Load Forecasting using Interval Arithmetic Backpropagation Neural Network

Short-term load forecasting is necessary for the reliable and economical operation of power systems. Due to inherent spatial and temporal variability, influence of meteorological conditions and uncertainties, it is difficult to model and forecast short-term electric load. This paper describes a new neural network model based on interval arithmetic backpropagation for short-term load forecasting. The advantage of the model is that it can generate the prediction result in the form of interval values which represents an uncertainly measure for a prediction. The input data as well as the output data of the network can be represented and processed as a range of values. The prediction effectiveness of the proposed model is evaluated by applying it to a real power system to forecast the load one day ahead