Throughput prediction in cognitive Radio using Adaptive Neural Fuzzy Inference System

In today's engineering challenge intelligence is required to keep up with the rapid evolution of wireless communications, specifically managing and allocating the scarce, radio spectrum in the highly varying and disparate modern environments. The cognitive engine derives and enforces decisions to the software-based radio by constantly adjusting its parameters, observing and measuring the outcomes and taking actions to move the radio toward some desired operational state within the cognition cycle. For such a process, learning mechanisms which are capable of exploiting measurements are sensed from the environment, gathered experience and stored knowledge, are assessed for taking decisions and actions. A cognitive Radio system assures to handle this situation by utilizing intelligent software packages that enrich their transceiver with radio-awareness, capability and adaptability to learn. This paper introduces and assesses learning schemes which are based on artificial neural networks and can be used for predicting the capabilities (e.g. throughput) which can be achieved by a specific radio configuration.