Wind Profile Prediction using a Meta-cognitive Fully Complex- valued Neural Network Sathish.E # ,Mrs.Sivachitra.M * , Ramasamy Savitha^ &Mrs.Vijayachitra.S # # PG Student M.E (C&I) * AssistantProfessor (SLG), Department of EEE ^Research Fellow, School of Computer Engineering,NTU,Singapore. # Professor, Department of EIE # Kongu Engineering College,Perundurai. 1 esathish5@gnmail.com 2 sivachitra@kongu.ac.in 3 savi0001@e.ntu.edu.sg 4 svijayachitra@kongu.ac.in ABSTRACT This paper applies the recently developed Meta-cognitive Fully Complex- valued Radial Basis Function (Mc-FCRBF) network for predicting the speed and direction of wind. Mc-FCRBF network contains two components: a cognitive component and a meta-cognitive component. A Fully Complex- valued Radial Basis Function (FC-RBF) network is the cognitive component and a self- regulatory learning mechanism is its meta- cognitive component. In each epoch of the training, when the sample is presented to the Mc-FCRBF network, the meta-cognitive component decides what to learn, when to learn, and how to learn based on the knowledge acquired by the FC-RBF network and the new information contained in the sample. Performance comparison of the meta- cognitive fully complex-valued RBF network (Mc-FCRBF) applied for wind speed prediction shows better prediction of wind profile (Speed) characteristics when compared to a real-valued extreme learning machine and FC-RBF network. Keywords: Neural Networks, Extreme Learning machine, Wind speed prediction, Wind Profile prediction, FC-RBF and Mc- FCRBF. I.Introduction The problem of environmental pollution has gained a large attention, hence, Utilization of renewable energy sources and reduction of pollution has become very important [27]. Wind energy has been considered as valuable source of conventional energy. A large number of potential wind farms are available throughout the world. Of these, all the sites do not have the wind turbine generators. The existing wind farms show that some of the wind power plants have failed completely or performed poorly mainly because the installed wind turbine generation system do not match with the direction and speed of the wind. Hence there arises a need for a systematic approach towards the problem of matching the WTG (Wind Turbine Generator) at a particular site. Therefore, it is important to predict the wind speed and direction for the proper operation of the wind turbine generation system A genetic neural network and a radial basis function network have been applied to wind speed