Stochastic Time Series Learning Scheme for Throughput Prediction in Cognitive Radio System

Abstract

Cognitive Radios are smart radio which can reconfigure and adapt according to the requirement of end user. Cognitive Engine greatly contributes to the intelligent radio. Learning is an essential phase in the Cognitive engine, enabling forecasting of different functional factors. This paper proposes stochastic time series based learning outline which can be used for Cognitive Radio towards forecast of key parameters of throughput and data rates. The learning outline is capable to prediction up to 99% with minimum Root Mean Square Error. These learning schemes can be valuable inputs for Dynamic Spectrum Allocation. Subsequently, these outlines will form part of Cognitive Engine and can be utilized to perform allocation of spectrum resulting in a futuristic wise radio