Performance Analysis of Combined Similar Day and Day Ahead Short Term Electrical Load Forecasting using Sequential Hybrid Neural Networks

ABSTRACT

A novel method for short-term electrical load forecasting using back propagation neural networks (BPNNs) is proposed for reducing the forecasting error. Conventionally, BPNN for load forecasting will have a single network structure trained by either similar day (SD) or day ahead (DA) approach. A model trained using either similar day or day ahead can only learn the characteristics of either approach. Also, a single BPNN model that incorporates both will have high complexity in its structure. The proposed sequential hybrid neural network method employs BPNNs in two stages, utilizing both similar day and day ahead. The proposed method is compared against similar day and day ahead approaches. The models are tested using hourly electrical load data from the Electric Reliability Council of Texas, Texas in USA and the Global Energy Forecasting Competition of 2012. It is observed that the proposed method showed an improvement in forecasting accuracy over the BPNN and artificial neural network-particle swarm optimization models available in literature.

KEYWORDS:

• Artificial neural networks
• Day ahead
• Machine learning
• Multi-stage back propagation neural networks
• Short-term electrical load forecast
• Similar day

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by Science and Engineering Research Board (SERB), India [grant number SB/FTP/ETA-408/2012].

Notes on contributors

Rohit Rajan Eapen

Rohit Rajan Eapen received the bachelor of technology in electrical and electronics from the College of Engineering, Trivandrum, India in 2007, and master of technology in power electronics from the National Institute of Technology, Tiruchirappalli, India in 2013. He is presently working towards his PhD degree in the Department of Electrical and Electronics, National Institute of Technology, Tiruchirappalli, India.

Sishaj Pulikottil Simon

Sishaj Pulikottil Simon was born in India. He received the BEng degree in electrical and electronics engineering, the MEng degree in applied electronics both from Bharathiar University, Coimbatore, Tamil Nadu, India, in 1999 and 2001, respectively, and the PhD degree in power system engineering from Indian Institute of Technology (IIT), Roorkee, Uttarakhand, India, in 2006. Currently, he is an assistant professor with the Department of Electrical and Electronics Engineering, National Institute of Technology (NIT) (formerly Regional Engineering College), Tiruchirappalli, Tamil Nadu, India. His research interests include the area of power system operation and control, power system planning and reliability, artificial neural networks, fuzzy logic system, and application of meta-heuristics, and intelligent techniques to power system.

E-mail: [email protected]