A Multi-Agent Collaborative Model for Bayesian Opportunistic Channel Accessibility in Railway Cognitive Radio

Zhijie Yin
2017 International Journal of Performability Engineering  
Applying cognitive radio to railway communication systems is a cutting-edge research area. This paper aims to solve the optimization problem of the global channels opportunistic accessibility in railway cognitive radio environments. In particular, we propose an efficient cooperative model for multiple wayside base stations. This model consists of Bayesian inference to calculate the probability of successful transmission on a single station along with team collaboration to maximize network
more » ... mance within a group of base stations. Instead of only performing the traditional sensing and assigning, the base stations have an ability to learn from the interactions among others and the environment to gain prior knowledge. The base station agents further analyze prior knowledge and perform optimal channel assignment for global network performance. Using our cooperative model of channels opportunistic accessibility, we have shown that the model can also reduce the computational complexity in high-mobility communication environments. and feedback information, base stations can precisely assign channels to the secondary users (train) and thereby decrease the collision between primary users and secondary users. Many researchers have greatly contributed to addressing this issue in railway Cognitive Radio (rail-CR), such as spectrum sensing, management technique, licensed user activity prediction, and so on [5, 15, 21] . However, many methods on modeling channel accessibility or radio resource allocation consider only the performance of a single base station, such as [19, 27] . In [19] , multi-user opportunistic transmission scheduling is modeled, and at each time slot, the user chooses the best weighted channel. The weight of the channel reflects the long-term system fairness. By only considering the time varying property of the channel, the investigation does not seem to be comprehensive. Location information was considered in [6] and used to perform optimal sensing and power allocation. There is a lack of comprehensive research on multiple base station collaboration for global network performance. Also, the Bayesian Nash equilibrium model is given in [16] to provide the competitively optimal behavior for cognitive radio. [3] provides the Bayesian method in spectrum sensing. [28] shows the Bayesian way in licensed user prediction. Based on these investigations, this paper aims to provide a better communication network for the locomotive and the access points for urban scenarios in a rail-CR environment by establishing a comprehensive multi-agent collaboration model for the Bayesian opportunistic channel accessibility using priori context features. The rest of the paper is organized as follows. Section 2 presents a formulation of our problem in detail, in which a mathematic model for the channel opportunistic access is given. In section 3, the basic principle of the Bayesian Network is summarized, along with the Bayesian Network based channel accessibility model. In section 4, an example of the rail-CR is given to illustrate the inference of the proposed model. Section 5 concludes the paper. Related Work The growth of wireless communication has created higher demands on future wireless communication network of highspeed rails. Also, multiple sensors deployed along the railway used to monitor different environmental factors are now required for stable data transmission. At high speeds problems like the Doppler shift, lead to fast cell switching and penetration loss, consequently causing frequent spectrum handoffs and further lowering the global performance of network communication [1, 14, 17] . The rail-CR study faces different requirements and obstacles currently in railway communication. However, through our investigation of the literatures above, we could not find one which considers multiple factors in railway communication. Actually, modeling channel accessibility in railway for quantitative analysis is still a challenge. There are four explanations:
doi:10.23940/ijpe.17.04.p15.479489 fatcat:fzsx4cepazeljozx4dwimhv5lu