Research on Soft Computing Techniques for Cognitive Radio

Research on Soft Computing Techniques for Cognitive Radio

Subhashree Mishra (School of Electronics Engineering, KIIT University, Bhubaneswar, India), Sudhansu Sekhar Singh (KIIT University, Bhubaneswar, India), Bhabani Shankar Prasad Mishra (School of Computer Engineering, KIIT University, Bhubaneswar, India) and Prabin Kumar Panigrahi (KIIT University, Bhubaneswar, India)
DOI: 10.4018/IJMCMC.2016040104


Presently, the world of wireless communication is going under some crucial challenges, which attracts the attention of several researchers. Cognitive radio is defined as a multidimensional aware, autonomous radio system that learns from its experiences to reason, plan & decide future actions to meet user needs. Such a highly varied radio environment calls on intelligent management, allocation & usage of scarce resources. Issues like spectrum sensing & allocation, environmental learning i.e., adaptability & capability to learn attracts the attention of several soft computing learning & optimization techniques like neural networks, fuzzy logic, genetic algorithm & swarm intelligence. The cognitive engine behind the radio combines the sensing, learning, switching, and optimization algorithms to control & adapt the radio system from the physical layer to the top of the communication stack. This paper presents a critical review on different soft computing approaches applied over the cognitive radio issues & also points out different research directions over it.
Article Preview


According to the Federal Communications Commission (FCC) (FCC, 2002) report 70% of the licensed Radio Frequency (RF) spectrum seems to be idle for a specific geographical area with a given time. With the vast increase in number of applications, services and users, a scarcity of RF spectrum arose. In the year 1992, J Mitolla (Mitola, 1992) has proposed the concept of Cognitive Radio(CR) which is a collaborative approach of various research area like Cognitive science & Radio technology, Software Defined Radio (SDR), wireless communication concepts, signal processing, game theory, soft computing techniques are adopted to make the SDR truly cognitive and for efficient utilization of the limited radio spectrum. Further CR is a sole implementation of Dynamic Spectrum Allocation (DSA) in such a way that the interference expected due to spectrum sharing between primary user and secondary user must be minimised with 100% reliability.

Fixed Spectrum Access (FSA) policy, is adopted by FCC to achieve various wireless applications in a zero tolerance level. According to FSA, there two kinds of RF users exist: i) The Primary User (PU) and ii) the Secondary User (SU). For a licensed RF band, the user who keeps the license for that band is called as primary users and that frequency band is dedicated to that license holder only. Apart from the primary user, the entire user who wants to access a license or unlicensed RF band is called secondary user (SU) ex: cognitive radio (CR).

The main features of the CR (Akyildiz, Lee, Varun & Mohanty, 2006; Ghosh, Das, & Chatterjee, 2014) are:

  • Able to sense its wireless communication environment;

  • Independently and dynamically adjust the communication parameters to obtain quality of service for users.

So, a radio has to be intelligent enough to automatically adjust its communication parameter according to its environmental change and the services demanded by the corresponding user and observations.

The process of acquiring the radio environment information is very expensive and complex because it involves spectrum sensing, autonomous learning, user cooperation, modelling and reasoning. Depending on different cognitive capabilities, a cognitive radio may access the radio spectrum in two different ways like: Opportunistic Spectrum Access (OSA) and Concurrent Spectrum Access (CSA).

In the OSA model (Xu, Wang, Wu, Anpalagan & Yao, 2012; Salem, El-Kader, Ramdan & Abdel-Mageed, 2014), a CR node always search all available spectrum hole in its surrounding, once it finds the best one, performs its communication operation and change its communication parameter according to it. CR node has to continuously check whether the PU needs its spectrum so that the CR has to give up maintaining zero interference. On the other hand, in CSA model, the PU and CR both can share the licensed spectrum band with a condition that the interference due to SU should not cross the threshold level.

A Cognitive Radio cycle can be explained in Figure 1.

Figure 1.

A cognitive radio cycle

Major components of Cognitive Radio can be figured out in Figure 2.

Figure 2.

Major components of cognitive radio cycle

Broadly it can be figured out into two categories like: utilization of radio spectrum in proper way and High reliability.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 10: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing