Abstract
The ability to recognize the medium access control protocol employed by a network can facilitate the incorporation of a cognitive radio into an existing network by elucidating an integral aspect of network behavior. Since the way in which users access the electromagnetic spectrum is one of the most prominent distinctions between reservation based and contention based medium access control protocols, the first part of this work exploits the regular timing of transmissions from networks utilizing reservation based time-division multiple access (TDMA) protocols to differentiate between transmissions governed by TDMA and by contention based carrier sense multiple access (CSMA) protocols. Our approach leverages modular arithmetic to identify periodicity in transmission timings and an unsupervised $k$ -means algorithm to generate distinct TDMA and CSMA clusters. Several supervised machine learning algorithms are explored to build a protocol classifier. We then present a method of distinguishing between transmissions from multi-channel frequency division multiple access (FDMA) based networks and single channel networks. This method uses an automated machine learning clustering algorithm to obtain an estimate of the actual center frequencies of channels utilized by a network. Such information can be used to determine whether the network is employing an FDMA protocol to access the electromagnetic spectrum.
Highlights
I NCREASED use of the electromagnetic spectrum in recent years has led to the development of new technologies with the ability to assess spectrum usage and to adjust transmission parameters intelligently to take advantage of unused frequency bands
The metrics we develop to generate a machine learning feature set for medium access control (MAC) protocol identification result in accuracies of over 90% when used as inputs to SVM, k-NN and Naïve Bayes classifiers
time-division multiple access (TDMA)/carrier sense multiple access (CSMA) CLASSIFICATION 1) Dataset The dataset used to develop, evaluate, and refine the algorithm was composed of traces collected from a testbed of universal software radio peripherals (USRPs) and of traces generated by the extendable mobile ad-hoc network emulator (EMANE) software, which allows for real-time modelling of mobile network systems [24]
Summary
I NCREASED use of the electromagnetic spectrum in recent years has led to the development of new technologies with the ability to assess spectrum usage and to adjust transmission parameters intelligently to take advantage of unused frequency bands. For adaptive nodes to efficiently utilize vacant spectrum channels without causing unintended interference to other users, it is beneficial to determine how other networks are accessing a particular channel. If such information is known, a user can, for example, tailor transmitted packets to fit into a particular time slot. Lai et al [1] designed medium access protocols for cognitive users to opportunistically access the spectrum in the absence of primary users They focused on determining the probability that a channel is occupied during a given time slot. A number of authors have investigated the use of machine learning for improved MAC protocols, for primary user detection, and in cognitive radio networks [11]–[16]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
