ANFIS Based Data Rate Prediction For Cognitive Radio

Abstract

Intelligence is needed to keep up with the rapid evolution of wireless communications, especially in terms of managing and allocating the scarce, radio spectrum in the highly varying and disparate modern environments. Cognitive radio systems promise to handle this situation by utilizing intelligent software packages that enrich their transceiver with radio-awareness, adaptability and capability to learn. A cognitive radio system participates in a continuous process, the ‘‘cognition cycle”, during which it adjusts its operating parameters, observes the results and, eventually takes actions, that is to say, decides to operate in a specific radio configuration (i.e., radio access technology, carrier frequency, modulation type, etc.) expecting to move the radio toward some optimized operational state. In such a process, learning mechanisms utilize information from measurements sensed from the environment, gathered experience and stored knowledge and guide in decision making. This thesis introduces and evaluates learning schemes that are based on adaptive neuro-fuzzy inference system (ANFIS) for predicting the capabilities (e.g. data rate) that can be achieved by a specific radio configuration in cognitive radio.
First a ANFIS based scheme is proposed. The work reported here is compare previous neural network based learning schemes. Cognitive radio is a intelligent emergent technology, where learning schemes are needed to assist in its functioning. ANFIS based scheme is one of the good learning Artificial intelligence method, that combines best features of neural network and fuzzy logic. Here ANFIS and neural networks methods are able to assist a cognitive radio system to help in selecting the best one radio configuration to operate in. Performance metric like RMSE, prediction accuracy of ANFIS learning has been used as performance index.