IIIT Hyderabad Publications |
|||||||||
|
Dempster-Shafer Theory Based Cooperative Energy Detection Under Noise Uncertainties In Cognitive Radio NetworksAuthor: Prakash Gohain Date: 2017-12-14 Report no: IIIT/TH/2017/88 Advisor:Sachin Chaudhari AbstractObtaining awareness about the state of the spectrum via sensing is crucial in many systems including cognitive radio (CR), cognitive radars, automotive sensing and communication where spectrum sharing is required. In the context of CR, spectrum sensing is a key enabler for obtaining spectrum awareness, which detects the activity of a licensed user or primary user (PU) in a particular band of interest to provide opportunistic usage of spectrum to the secondary users (SUs). In this thesis, we focus on cooperative energy detection (CED) in a CR network. CED is a distributed detection scheme where all the SUs employing energy detector (ED), collaborate to perform spectrum sensing to identify spectrum holes. A centralized soft combining approach is considered such that the SUs sends the energy value, calculated from the received signal, to the fusion center (FC). Using sum fusion rule and Neyman-Pearson (NP) criterion, the FC makes the global decision of whether the frequency band is occupied by the PU or not. However, implementing CED requires knowledge of noise variance (noise power) for setting the threshold. But in real world scenario, noise variance may change due to several reasons such as temperature, external interference, etc. As a result, slight change or deviation of noise variance from the assumed value leads to unpredictable performance in CED. Moreover, in the presence of noise uncertainty (NU), CED suers from performance limitation in the form of signal-to-noise-ratio (SNR) wall. SNR wall phenomenon in CED has been well investigated in literature but only considering homogeneous CR nodes having same NU parameters. In this thesis, we extend the concept of SNR wall in CED to a more general case by considering that all the participating SUs have dierent NU parameters. The generalized SNR expression for this case is derived and a new terminology called \SP wall" is dened to explain the concept of SNR wall in this heterogeneous CR network. Handling NU in CED using traditional probabilistic methods have not borne any fruits beyond certain thresholds, which forced us to look for concepts and theories beyond standard Bayesian approach. In this context, Dempster-Shafer theory (DST) (also called evidence theory) provides a new dimension to the picture. It enables us to include uncertainty or ignorance as a quantity in the fusion process. The theory has the ability to quantify our lack of knowledge or how much we are uncertain about something, instead of ignoring them altogether. Using the tools of evidence theory, we forged a new CED algorithm for spectrum sensing under NU. In the proposed scheme, the SUs sends basic mass assignment (BMA) values or belief values to the FC, instead of the energy values. A novel method to compute the BMA values based on energy of the received signal is proposed. The uncertainty in noise variance is accounted by discounting the BMA values of each SU by the amount of trust associated with the SU, where the trust factor is inversely proportional to the amount of NU present in the SU. At the FC, Dempster combination rule is applied to fuse these discounted BMA values. Even in this case, NP criterion is employed for designing the detector at the FC. The nal test statistic is compared with the predened threshold (based on NP criterion) to make the global decision. Extensive simulation results have shown that the proposed DST based CED scheme is able to surpass the traditional soft combining based CED scheme and is also successful in lowering the SNR/SP wall barrier of CED. Full thesis: pdf Centre for Communications |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |