An efficient hour-ahead electrical load forecasting method based on innovative features. (15th June 2020)

• Record Type: Journal Article
• Authors: Rafati, Amir; Joorabian, Mahmood; Mashhour, Elaheh
• Is Part Of: Energy. Volume 201(2020)
• Publication Date: 2020-06-15
• Subjects: Hour-ahead load forecasting -- Feature selection -- Neural networks -- Deregulated energy system; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2020.117511
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Deregulation of electric power market and aggregation of renewable resources raise the need for new hour-ahead load forecasting models. This paper proposes a new hybrid data-driven method for hour-ahead electrical load forecasting based on innovative features that represents the nonlinear and dynamic characteristics of electrical load. These features predict hourly load changes and improve the accuracy and performance of STLF. These innovative features first construct the pool of features along with historical load variables. Then, a feature selection method called RReliefF is used for choosing most relevant features and finally, a multi-layer perceptron neural network is employed as a forecasting engine—due to its advantages such as self-organization, fault tolerance and ease of integration in existing technologies. The efficiency of the proposed model is evaluated through various comparative experiments and compared with benchmark models using the three years' real energy market data from New England ISO by four evaluation criteria. The results demonstrate the superiority of proposed method in forecasting performance for the period of analysis including 12 test months as well as special days. Highlights: Proposes a STLF method based on innovative features, feature selection and NN. Innovative features efficiently identify the dynamic characteristics of load data. The model is also suitable for STLF in holidays and special days. The results clearly confirm the accuracy of method using four evaluation criteria.