Application of a new hybrid forecast engine with feature selection algorithm in a power system

To operate a power system effectively, an accurate prediction model is demanded. So, short-term load forecast is one of the major discussions in deregulated power markets. This prediction model needs a strong and accurate method to tackle the complexity, non-stationary and volatility of this signal. Hence, a new hybrid forecasting model is proposed in this paper, to solve the load forecast requirement. The proposed structure consists of a three-stage Neural Network-based forecast engine with different learning algorithms. Also, the input signal of this forecast engine is filtered by a new feature selection model to find the high relevancy and low redundancy of features. The proposed strategy is implemented and tested on real-world engineering data through a comparison with other techniques. The numerical results obtained demonstrate the validity of the proposed method.