Cognition in Wireless Sensor Networks: A Perspective

Dept. of Electr. & Comput. Eng., Queen's Univ., Kingston, ON, Canada
IEEE Sensors Journal (Impact Factor: 1.85). 04/2011; DOI: 10.1109/JSEN.2010.2052033
Source: IEEE Xplore

ABSTRACT Wireless Sensor Networks are believed to be the enabling technology for Ambient Intelligence. They hold the promise of delivering to a smart communication paradigm which enables setting up an intelligent network capable of handling applications that evolve from user requirements. Cognitive agents capable of making proactive decisions based on learning, reasoning and information sharing when interspersed in sensor networks, may help achieve end-to-end goals of the network even in the presence of multiple constraints and optimization objectives. Cognitive radio at the physical layer of such agents may enable the opportunistic use of the heterogeneous wireless environment. However, research efforts have been discrete and cognitive techniques have focused on improving specific aspects of the network or benefiting specific applications. The main contribution of this paper is providing the vision and advantage of a holistic approach to cognition in sensor networks, which can be achieved by incorporating learning and reasoning in the upper layers, and opportunistic spectrum access at the physical layer. Rather than providing an ostensive survey of cognitive architectures applicable to sensor networks, this paper provides the reader with a framework based on knowledge and cognition that can help achieve end-to-end goals of application-specific sensor networks.

1 Follower
  • [Show abstract] [Hide abstract]
    ABSTRACT: Currently, working in the overcrowded shared unlicensed spectrum band, leads to a reduction in the quality of communications in wireless networks. This makes a considerable increase in packet loss caused by collisions that necessitates packets retransmissions. In the case of wireless sensor networks (WSN), a large amount of energy of sensor nodes will be wasted by these retransmissions. Cognitive radio technology makes it possible for sensor nodes, to opportunistically use licensed bands with better propagation characteristics and less congestion. In this paper a routing method for cognitive radio wireless sensor networks (CR-CEA) is presented, that is based on a cross-layer design that jointly considers route and spectrum selection. The CR-CEA method has two main phases: next hop selection and channel selection. The routing is performed hop-by-hop with local information and decisions, which are more compatible with sensor networks. Primary user activity and prevention from interference with them, is considered in all spectrum decisions. It uniformly distributes frequency channels between adjacent nodes, which lead to a local reduction in collision probability. This clearly affects energy consumption in all sensor nodes. In CR-CEA, route selection is energy-aware and a learning-based technique is used to reduce the packet delay in terms of hop-count. The simulation results reveal that by applying cognitive radio technology to WSNs and selecting a proper operating channel, we can consciously decrease collision probability. This saves energy of sensor nodes and improves the network lifetime.
    Wireless Networks 10/2014; 20(7):2037-2052. DOI:10.1007/s11276-014-0728-8 · 1.06 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In recent times, Cognitive radio (CR)-based wireless sensor networks (WSNs) have been widely used for opportunistic access of the shared spectrum. In WSNs, deployment of sensor nodes (SN) may be random or it may follow an optimized approach-based upon the application where it is to be used. Energy efficient route selection for transferring data from a SN to base station (BS) is the key issue to increase the lifetime of WSN. Therefore, hierarchical cluster-based data transmission from a SN to BS using multi-hop communication may be one of the effective solutions in this direction, as transmission operation consumes more energy as compared to sensing or computation. Several mechanisms have been proposed in the literature for the improvement of network lifetime. Motivated from the above, in this paper, we suggest a Distance-Based Multihop Clustering and Routing (DB-MCR)protocol for heterogeneous environment to improve stability and network lifetime of WSNs. By fixing the node densities, network region is segmented into different subregions with a specific shape. Boundaries of the segmented regions are estimated using the node densities. Segment-wise data transmissions are used for data collection at BS which provides separate bands for the nodes lying in different regions. A distance-based algorithm is used for election of cluster heads (CH) in which a conditional weighted election probability (WEP) is computed to reduce the interference among the nodes. The performance of the proposed scheme is evaluated using extensive simulations with respect to network lifetime and stability. The results obtained at initial energy and BS is located at corner show that DB-MCR improves the lifetime by 13% & 17% and stability improved by 8% & 16% with respect to MCR and SEP respectively.
    Pervasive and Mobile Computing 02/2015; DOI:10.1016/j.pmcj.2015.01.005 · 1.67 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Using the theory of machine learning to spectrum cognition and management is a necessary requirement of realizing cognitive radio technology. In order to evaluate the performance of wireless channel spectrum sensing strategy effectively, the statistical mean value is put forward as evaluation criteria for the cognitive user with fixed rate service. Study shows that, for the objective license channel vacancy and occupancy state time with exponentially distribution as well as the same distribution parameter, vacancy state probability follows uniform distribution. Then, the paper analyses how the channel time detection threshold have an influence on throughput. With the increasing of sample size, the estimate of throughput converges in probability to its statistical mean value. Simulation indicates that the spectrum sensing throughput performance of the cognitive user with fixed rate service based on machine learning achieves better performance compared with random spectrum sensing. Ultimately, the channel time detection threshold is achieved when maximizing the statistical mean throughput.
    Procedia Engineering 12/2012; 29:4181-4185. DOI:10.1016/j.proeng.2012.01.640