Spectrum Hole Prediction for Cognitive Radios: An Artificial Neural Network Approach

Transcription

1 International Journal of Information Processing, 10(1), 52-66, 2016 ISSN : IK International Publishing House Pvt. Ltd., New Delhi, India Spectrum Hole Prediction for Cognitive Radios: An Artificial Neural Network Approach V Balaji a, Chittaranjan Hota a, P S Deshpande b a Department of Computer Science and Information Systems, Birla Institute of Technology and Science Pilani, Hyderabad India, p @hyderabad.bits-pilani.ac.in, hota@hyderabad.bits-pilani.ac.in b Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science Pilani, Goa India, Contact:graghu@goa.bits-pilani.ac.in Spectrum sensing is the key mechanism in enabling spectrum awareness in Cognitive Radio (CR). By sensing and monitoring the available spectrum, unlicensed cognitive radio users, or secondary users (SUs), can intelligently adapt to the most suitable available communication links in the licensed bands. By exploiting the spectrum holes, they are able to share the spectrum with the licensed primary users (PUs), operating whenever the PUs are idle. In this paper, we present a Cooperative Spectrum Sensing (CSS) algorithm for Cognitive Radios (CR) based on IEEE Wireless Regional Area Network (WRAN) standard. The core objective is to improve cooperative sensing efficiency which specifies how fast a decision can be reached in each round of cooperation (iteration) to sense an appropriate number of channels/bands (i.e., 86 channels of 7MHz bandwidth as per IEEE ) within a time constraint (channel sensing time). To meet this objective, we have developed CSS algorithm using machine learning scheme. The algorithm is divided into two phases: local sensing phase for energy detection and CSS phase using Perceptron learning module. We carried out 500 iterations where the position of SU changes arbitrarily during each iteration. The noise model formulated is independent and identically distributed to all SUs. We considered several simulation scenarios that can be used to evaluate spectrum sensing by single SU unit (local sensing) and multiple SUs in a cooperative setup. The detection accuracy and performance of the proposed algorithms are described using performance metrics called probability of detection and probability of false-alarm through extensive simulations using Matlab. The target false alarm rate is set to 0.1 for all iterations. Keywords : Cooperative communication, Cognitive capability, Dynamic spectrum access, Perceptron learning. 1. INTRODUCTION Frequency spectrum is a limited resource for wireless communications and may become congested owing to a need to accommodate the diverse types of air interface used in next generation wireless networks. To meet these growing demands, the Federal Communications Commission (FCC) has expanded the use of the unlicensed spectral band. However, since traditional wireless communications systems also utilize the frequency bands allocated by the regulatory bodies (i.e., FCC, TRAI) in a static manner, they lack adaptability. Many studies show that while some frequency bands in the spectrum are heavily used, other bands are largely unoccupied most of the time. These potential spectrum holes result in underutilization of the available frequency bands. As the demand for wireless service become more and more ubiquitous, the wireless devices must find a way to transmit within extremely constrained radio resources. Numerous studies, such as those done by the Federal Communication Commission (FCC) [1] in the United States, have shown that the licensed spectrum remains unoccupied for large periods 52

2 Spectrum Hole Prediction for Cognitive Radios: An Artificial Neural Network Approach 63 Figure 6. Estimation of Signal Energy using Periodogram Figure 9. Channel Availability Results of Band 1 during (a) iteration 6; (b) iteration 83 Figure 8. Local Observation Results of SU9 cisions by maintaining the target probability of error rate as 0.1. The FC decides the final availability of channel information using perceptron learning module with low error rate. The simulation result of FC is shown in Figure 11. The perceptron module in FC uses 70% of local sensing energy vectors as training set to meet the desired target output. The output obtained from the perceptron model is called the network output. To determine the performance of perceptron learning on CSS scheme, we consider network output versus target output. The target output determines the probability of error rate. Figure 11 shows the comparison of the network output with the target output. The highlighted section (marked by arrow) shows the mismatch between the target output and network output and that is an error instance. As we can see for 500 iterations (different secondary user positions), we have less than 10% error rate. Here, we have depicted the performance for only Channel 1 and Channel 2. The network output of our proposed algorithm meets the target false-alarm rate of 0.1 for all the simulation conducted. 6. CONCLUSIONS Learning ability is important for cognitive radios for effective decision making. Learning algorithms are implicitly built into spectrum knowledge acquisitions and decision-making algorithms in the sense that they convert information(current and past observations) into decisions and actions. In this paper, we have developed a cooperative spectrum sensing al-

3 64 V Balaji, et al., Figure 10. Channel Scanning Results of FC gorithm using perceptron learning scheme for Cognitive radios. The received energy vectors of each SU are considered as feature input vectors of perceptron learning module. The received SNR of each SU varies based on distance coordinates. The mean value of SNR is considered as weight vector of perceptron module. The simulation scenario has been formulated to meet the requirements of IEEE WRAN standard. The proposed CSS scheme has the capability to learn from the radio environment to achieve cognitive tasks. Further, it is observed that the perceptron learning module improves the decision capability of FC and significantly reduces the error rate to meet the target false-alarm probability rate to 0.1. As future work, we plan to extend this to various cooperation scenarios to support different wireless standards and specifications which will help us to improve the cognition capability and cooperative sensing accuracy. REFERENCES Figure 11. Perceptron (a) Network Output Vs (b) Target Output 1. M Marcus, J Burtle, B Franca, A Lahjouji and N McNeil. Federal Communications Commission Spectrum Policy Task Force, Report of the Unlicensed Devices and Experimental Licenses Working Group, I F Akyildiz, W Y Lee, M C Vuran and S Mohanty. Next generation/dynamic Spectrum Access/Cognitive Radio Wireless Networks: A Survey, Computer Networks, 50(13): , J Mitola. Cognitive Radio-An Integrated Agent Architecture for Software Defined Radio, D P W Group. IEEE Standard Definitions and Concepts for Dynamic Spectrum Access: Terminology Relating to Emerging Wireless Networks, system functionality and spectrum management, Technical report, IEEE, Piscataway, Tech. Rep., S Haykin. Cognitive Radio: Brain-Empowered Wireless Communications, IEEE Journal on Selected Areas in Communications, 23(2): , B Wangand K Liu. Advances in Cognitive Radio Networks: A Survey. IEEE Journal of Selected Topics in Signal Processing, 5(1):5 23,

4 Spectrum Hole Prediction for Cognitive Radios: An Artificial Neural Network Approach D Cabric, S M Mishra and R W Brodersen. Implementation Issues in Spectrum Sensing for Cognitive Radios, in Proceedings of the 38th Asilomar Conference on Signals, Systems and Computers, pages , I F Akyildiz, B F Lo and R Balakrishnan. Cooperative Spectrum Sensing in Cognitive Radio Networks: A Survey, Physical communication, 4(1):40 62, W Wang, B Kasiri, J Cai and A S Alfa. Distributed Cooperative Multi-channel Spectrum Sensing based on Dynamic Coalitional Game, in Global Telecommunications Conference (GLOBECOM 2010), pages 1 5, V Balaji, P Kabra, P Saieesh, C Hota and G Raghurama. Cooperative Spectrum Sensing in Cognitive Radios using Perceptron Learning for IEEE wran, Procedia Computer Science, 54:14 23, A Ghasemi and E S Sousa. Spectrum Sensing in Cognitive Radio Networks: Requirements, Challenges and Design Trade-offs, Communications Magazine, IEEE, 46(4):32 39, D Bhargavi and C R Murthy. Performance Comparison of Energy, Matched-Filter and Cyclostationarity-Based Spectrum Sensing, in IEEE Eleventh International Workshop on Signal Processing and Advances in Wireless Communications (SPAWC), T Yücek and H Arslan. A Survey of Spectrum Sensing Algorithms for Cognitive Radio Applications, Communications Surveys and Tutorials, IEEE, 11(1): , L Lu, X Zhou, U Onunkwo and G Y Li. Ten years of Research in Spectrum Sensing and Sharing in cognitive Radio, EURASIP Journal on Wireless Communication and Networking, G Ganesan and Y Li. Cooperative Spectrum Sensing in Cognitive Radio Networks, in First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, pages , X Chen, H H Chen and W Meng. Cooperative Communications for Cognitive Radio Networks from Theory to Applications, Communications Surveys and Tutorials, IEEE, 16(3): , Z Quan, S Cui and A H Sayed. Optimal Linear Cooperation for Spectrum Sensing in Cognitive Radio Networks, IEEE Journal of Selected Topics in Signal Processing, 2(1):28 40, J Unnikrishnan and V V Veeravalli. Cooperative Sensing for Primary Detection in Cognitive radio, IEEE Journal of Selected Topics in Signal Processing,, 2(1):18 27, A Ghasemi and E S Sousa. Collaborative Spectrum Sensing for Opportunistic Access in Fading Environments, in First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, pages , W Y Lee and I F Akyildiz. Optimal Spectrum Sensing Framework for Cognitive Radio Networks, IEEE Transactions on Wireless Communications, 7(10): , W Zhang, R K Mallik and K Letaief. Optimization of Cooperative Spectrum Sensing with Energy Detection in Cognitive Radio Networks, IEEE Transactions on Wireless Communications, 8(12): , E Peh and Y C Liang. Optimization for Cooperative Sensing in Cognitive Radio Networks, in Wireless Communications and Networking Conference, Y Zou and Y D Yao. Spectrum Efficiency of Cognitive Relay Transmissions with Cooperative Diversity in Cognitive Radio Networks, in Second International Conference on Communication Systems, Networks and Applications (ICCSNA), pages 59 62, M Bkassiny, YLi andskjayaweera. ASurvey on Machine-Learning Techniques in Cognitive radios, Communications Surveys and Tutorials, IEEE, 15(3): , K M Thilina, K W Choi, N Saquib and E Hossain. Machine Learning Techniques for Cooperative Spectrum Sensing in Cognitive Radio Networks, IEEE Journal on Selected Areas in Communications, 31(11): , V I Kostylev. Energy Detection of a Signal with Random Amplitude, in IEEE International Conference on Communications, pages , H Urkowitz. Energy Detection of Unknown Deterministic Signals, Proceedings of the IEEE, 55(4): , H V Poor. An Introduction to Signal Detection and Estimation, S Atapattu, C Tellambura and H Jiang. Energy Detection Based Cooperative Spectrum Sensing in Cognitive Radio Networks, IEEE Transactions on Wireless Communications,

5 66 V Balaji, et al., 10(4): , M K Simon and M S Alouini. Digital Communication over Fading Channels, A He, K K Bae, T R Newman, J Gaeddert, K Kim, R Menon, L Morales Tirado, J J Neel, Y Zhao, J H Reed. A Survey of Artificial Intelligence for Cognitive Radios, IEEE Transactions on Vehicular Technology, 59(4): , V Balaji is a full-time Ph.D Scholar at Department of Computer Science and Information Systems in BITS Pilani, Hyderabad Campus. He has five years of industrial and academic experience in various organizations and institutions. He received his ME Degree in Digital Communication and Networking from Kalasalingam college of Engineering affiliated with Anna University, Chennai in He did his BE in Electronics and Communication from National Engineering College, Tamilnadu in His research interests are in the area of Cognitive Radio, Cooperative Communication and Next Generation Wireless Communication Networks. Chittaranjan Hota is a Professor and Associate Dean (Admissions) at Birla Institute of Technology and Science-Pilani, Hyderabad, India. He is also responsible for managing the Information Processing Unit at BITS-Hyderabad that takes care of ICT needs of the entire institute. He was the founding Head of Department of Computer Science at BITS, Hyderabad. Prof. Hota did his Ph.D in Computer Science and Engineering from Birla Institute of Technology and Science, Pilani. He has been a visiting researcher and visiting professor at University of New South Wales, Sydney; University of Cagliari, Italy; Aalto University, Finland and City University, London over the past few years. His research work has been funded by University Grants Commission (UGC), New Delhi; Department of Electronics and Information Technology (DeitY), New Delhi; Tata Consultancy Services (TCS), India; and Progress Software, India. He has guided Ph.D students and currently guiding several in the areas of Internet of Things, Cyber Security and Big-Data Analytics. He is recipient of Australian Vice Chancellors Committee award, recipient of Erasmus Mundus fellowship from European commission and recipient of Certificate of Excellence from Kris Ramachandran Faculty Excellence Award from BITS, Pilani. He has published extensively in peer-reviewed journals and conferences and has also edited LNCS volumes. He is a member of IEEE, ACM, CSI, IE and ISTE. G Raghurama is a Senior Professor in the Department of Electrical and Electronics Engineering at BITS Pilani, KK Birla Goa Campus. He did his Masters from Indian Institute of Technology (IIT), Madras and Ph.D from Indian Institute of Science (IISc), Bangalore. After a brief post doctoral work at IISc, he joined BITS Pilani in the year At BITS, he teaches and guides research in the areas of Electronic Sciences, Communication Engineering, Telecommunications and Networks. He has Published more than 40 papers in reputed journals and conferences. He is recipient of a Research grant from Nokia in 2000, Faculty champion award from Microsoft in 2007 and has been recognized and felicitated by SkillTree Knowledge Consortium with the title SkillTree Education Evangelist of India He was also a member of the Technical Advisory Board of Cradle technologies, Pune in its initial years. Prof. Raghurama has rich experience in academic administration holding position such as Dean of Faculty Division, Dean of Admissions and Placement and Deputy Director (Academic) for several years. During , Prof. Raghurama was the Director of BITS Pilani, Pilani campus, during which time he made significant contributions to the growth of the Institute.