دانلود رایگان مقاله LA-CWSN: یک شبکه حسگر بی سیم شناختی مبتنی بر اتوماتای یادگیر

Abstract

Cognitive networking deals with using cognition to the entire network protocol stack to achieve stack-wide, as well as network-wide performance goals; unlike cognitive radios that apply cognition only at the physical layer to overcome the problem of spectrum scarcity. Adding cognition to the existing Wireless Sensor Networks (WSNs) with a cognitive networking approach brings about many benefits. To the best of our knowledge, almost all the existing researches on the Cognitive Wireless Sensor Networks (CWSNs) have focused on spectrum allocation and interference reduction, which are related to the physical layer optimization. In this paper, an inference and learning model for CWSNs, named LA-CWSN, is proposed. This model uses learning automata to bring cognition to the entire network protocol stack, with the aim of providing end-to-end goal. Learning automata are assigned to the parameters of the important network protocols. Each automaton has a finite set of possible values of the corresponding parameter, and it tries to learn the best one, which maximize the network performance. Each node in the network has its own group of learning automata, which act independently, however all nodes receive the same feedbacks from the environment. To clarify the proposed model a traffic control scenario in WSN is considered. Using the network simulator ns-2.35, we test the proposed inference and learning model for traffic control in a WSN. The results show that learning automata approach works well to apply cognition in WSNs.

7. Conclusion

In this study, adding cognition to the common WSNs and the properties of the CWSNs have been discussed; then, a learning automata-based model, which called LA-CWSN, has been proposed. In LA-CWSN, learning automata have been used to tune the networks controllable parameters. Each learning automaton is assigned to one controllable parameter and it chooses one possible value to adjust the parameter. Each learning automaton receives its own payoff from the network environment, and updates its internal information using the payoff and the probability vector of the actions. Over time, learning automata learn the suitable values of the parameters, corresponding with the current situation of the network. All the nodes in the network have this set of learning automata to dynamically configure the network protocol stack by itself; indeed, LA-CWSN is a distributed and intelligent model to implement a CWSN. Finally, the proposed LA-CWSN has successfully been tested. The results have represented the superior results compared with a basic WSN and also the simulated annealing based CWSN. Cognitive networks are popular within the areas of communication networks and AI. The authors yearn to continue their investigations in this field, by using other machine learning mechanisms such as Particle Swarm Optimization (PSO) and Bayesian Networks (BNs). In addition, other important scenarios in WSNs, such as target tracking, topology control, and energy aware routing are interesting research topics, which can be considered in CWSNs and will be the subject of the authors’ next investigations.