ISSN : 2347 - 8446 (Online) ISSN : 2347 - 9817 (Print) www.ijarcst.com International Journal of Advanced Research in Computer Science & Technology (IJARCST 2014) © 2014, IJARCST All Rights Reserved 162 Vol. 2 Issue Special 1 Jan-March 2014 Effcient Spectrum Sensing Pattern Using Intelligent Matrix in Cognitive Radio Network I K.Leelarani, II D.Abitha Kumari I PG Student, Dept. of CSE, Sethu Institute of Technology, Affiliated to Anna University, Kariapatti, Tamilnadu, India II Assistant Professor, Dept. of CSE, Sethu Institute of Technology, Affiliated to Anna University, Kariapatti, Tamilnadu, India I. Introduction Cognitive radio network (CRN) concept has been developed to mitigate the lack of frequency resources for the ever- growing spectrum demand by allowing secondary users (SUs) to opportunistically share the spectrum with licensed primary users (PUs) [1]. To this end, sensing capability is exploited in the CRNs’ nodes, which enables them to fnd some temporarily available transmission opportunities called white spaces also called Spectrum Holes (SH). The average throughput of the SUs is one of the most important performance metrics, which depends on the candidate primary channels for sensing and transmission. In practice, the unlicensed users, also called secondary users (SUs), need to continuously monitor the activities of the licensed users, also called primary users (PUs), to fnd the spectrum holes (SHs), which is defned as the spectrum bands that can be used by the SUs without interfering with the Pus [6]. This procedure is called spectrum sensing. There are two types of SHs, namely temporal and spatial SHs, respectively. A temporal SH appears when there is no PU transmission during a certain time period and the SUs can use the spectrum for transmission. A spatial SH appears when the PU transmission is within an area and the SUs can use the spectrum outside that area. To determine the presence or absence of the PU transmission, different spectrum sensing techniques have been used, such as matched fltering detection, energy detection, and feature detection. However, the performance of spectrum sensing is limited by noise uncertainty, multipath fading, and shadowing, which are the fundamental characteristics of wireless channels. To address this problem, cooperative spectrum sensing (CSS) has been proposed by allowing the collaboration of SUs to make decisions. Based on the sensing results, SUs can obtain information about the channels that they can access. However, the channel conditions may change rapidly and the behavior of the PUs might change as well. To use the Spectrum bands effectively after they are found available, spectrum sharing and allocation techniques are important. As PUs have priorities to use the spectrum when SUs co-exist with them, the interference generated by the SU transmission needs to be below a tolerable threshold of the PU system. Thus, to manage the interference to the PU system and the mutual interference among SUs, power control schemes should be carefully designed. In this paper, an intelligent spectrum sensing sequences setting is proposed, which does not need any prior information and presumptions about the wireless media as well as PUs’ data traffcs. More specifcally, a multilayer feed forward (MFF) neural network [9] is exploited to replace the mathematical modeling by learning the actual impact of the design parameters, i.e., the various permutations of elements in the sensing sequences, on the CRN average throughput. Then, a Kennedy-Chua (KC) neural network [10] is used to optimally fnd the SS of each SU. II. System Model A fully synchronized time slotted secondary and primary networks with Ns SUs, equipped with narrowband sensing capability, and Np PUs, each having one channel, and are assumed. Each SU sequentially senses the channels based on its SS provided by the CRN coordinator, i.e., the SU senses the frst channel assigned in its SS for a predetermined time duration (channel sensing time), and then changes its sensing circuitry, which takes a constant time τho, and senses the second channel if and only if the frst channel is sensed to be busy. This procedure will continue until a transmission opportunity is found. Sensing matrix (SM) is defned as a matrix with the dimensions of Ns × Np, in which the i-th row contains the SS for the i-th SU [8]. Average SU throughput is maximized through fnding the optimal SM elements, specifcally, if r represents the average throughput of the SUs, the optimization problem can be formulated as [8]: S*= arg max r s 1,1,s 1,2,……..,S Ns ,Np III. Local Spectrum Sensing Spectrum sensing enables SUs to identify the SHs, which is a Abstract Cognitive radio (CR) can successfully deal with the growing demand and scarcity of the wireless spectrum. To exploit limited spectrum effciently, CR technology allows unlicensed users to access licensed spectrum bands. Since licensed users have priorities to use the bands, the unlicensed users need to continuously monitor the licensed users’ activities to avoid interference and collisions. How to obtain reliable results of the licensed users’ activities is the main task for spectrum sensing. Based on the sensing results, the unlicensed users should adapt their transmit powers and access strategies to protect the licensed communications. One of the key effecting factors on the CR network throughput is the spectrum sensing sequence used by each secondary user. In this paper, secondary users’ throughput maximization through fnding an appropriate sensing matrix (SM) is investigated. The proposed intelligent learning and optimization cycle, based on neural networks, fnds the optimal sensing sequence for each secondary user without any prior knowledge about the wireless environment. The structure of the proposed scheme is discussed in detail, and its effciencies are verifed through numerical results. Keywords Cognitive radio, Sequential spectrum sensing, Neural networks, Sensing sequence, Spectrum holes