Hybrid partial least squares and neural network approach for short-term electrical load forecasting
Shukang Yang1, Ming Lu1 Contact Information and Huifeng Xue1
(1)     College of Automation, Northwestern Polytechnical University, Xi’an Shaanxi, 710072, China

Received: 17 November 2006 Revised: 8 May 2007 Published online: 8 March 2008

Abstract Intelligent systems and methods such as the neural network (NN) are usually used in electric power systems for short-term electrical load forecasting. However, a vast amount of electrical load data is often redundant, and linearly or nonlinearly correlated with each other. Highly correlated input data can result in erroneous prediction results given out by an NN model. Besides this, the determination of the topological structure of an NN model has always been a problem for designers. This paper presents a new artificial intelligence hybrid procedure for next day electric load forecasting based on partial least squares (PLS) and NN. PLS is used for the compression of data input space, and helps to determine the structure of the NN model. The hybrid PLS-NN model can be used to predict hourly electric load on weekdays and weekends. The advantage of this methodology is that the hybrid model can provide faster convergence and more precise prediction results in comparison with abductive networks algorithm. Extensive testing on the electrical load data of the Puget power utility in the USA confirms the validity of the proposed approach.

Keywords Electric loads - Forecasting - Hybrid neural networks model
Shukang YANG was born in 1955, in Sichuan, China. He is now a professor of Center of Economy at the Northwestern Polytechnical University. His research interests are in the areas of economy and he is engaged in researching and teaching in this field now.
Ming LU was born in Xi’an, Shaanxi, China. He received his master’s degree from Xin Jiang University, Urumchi, China, in 2002. He is presently a Ph.D. candidate at the College of Automatic Control, Northwestern Polytechnical University, Xi’an, China. His research interests are in the areas of computational intelligence and electric power load forecasting, in particular in neural net and partial least squares algorithm. He is a member of IASTED.
Huifeng XUE was born in Wanrong, Shanxi, China. He is now a professor at the Northwestern Polytechnical University. He received his bachelor’s degree from Northwest University in 1986 and then his master’s degree from Northwest University in 1991, and his Ph.D. degree from Xi’an Engineering Institute in 1995. His research interests are in the areas of system engineering and intelligent system.

Contact Information     Ming Lu
Email: lu_ming_nwpu@yahoo.com.cn