Title :
Recurrent Wavelet Network with New Initialization and its Application on Short-Term Load Forecasting
Author :
Baniamerian, Amir ; Asadi, Meysam ; Yavari, Ehsan
Author_Institution :
Electr. Eng. Dept., AmirKabir Univ. of Technol., Tehran, Iran
Abstract :
A key issue in intelligent demand-side management is the accurate prediction of electricity consumption. This paper presents a dynamic model for short-term special days load forecasting which uses a recurrent wavelet network (RWN). However, initialization of this network encounters a major problem. Thus, a new initialization method is suggested based on orthogonal least square (OLS) technique. Finally, a RWN with the proposed initialization method is applied to experimental special days load data. Simulation results show that the proposed network is capable of handling the inherent complexity of load forecasting problem.
Keywords :
demand side management; least mean squares methods; load forecasting; power engineering computing; recurrent neural nets; electricity consumption; intelligent demand-side management; orthogonal least square technique; recurrent wavelet network; short-term load forecasting; Computational modeling; Computer networks; Energy consumption; Least squares methods; Load forecasting; Neural networks; Neurons; Predictive models; Recurrent neural networks; Weather forecasting; Initialization; Load Forecasting; Recurrent Wavelet Network;
Conference_Titel :
Computer Modeling and Simulation, 2009. EMS '09. Third UKSim European Symposium on
Conference_Location :
Athens
Print_ISBN :
978-1-4244-5345-0
Electronic_ISBN :
978-0-7695-3886-0
DOI :
10.1109/EMS.2009.41