Research On Routing Algorithms Based On Bayesian Network In Vehicular Delay Tolerant Networks

Delay Tolerant Networks(DTN)are novel wireless mobile networks,which suffer from frequent disruption,highlatency,and the lack of a complete path from source to destination.Vehicular Delay Tolerant Network(VDTN)is a special type of DTNs with vehicles as nodes.Due to intermittent contact and disconnections,the node adopts the “store-carry-and-forward”mechanism to deliver messages.Node’s high-speed movement and topology’s frequent alteration result in the unstabitily of communication between nodes in VDTN,so traditional end-to-end routing protocols are not applicable.Considering that the movement of vehicles in VDTN is subject to human’s consciousness,and the consciousness is imperceptibly affected by human’s daily routine,so the vehicles in VDTN have certain movement patterns.However,traditional routing algorithms in DTNs do not take this characteristic into considerations very well,so it is necessary for researchers to propose more effective routing algorithms based on the characteristic of VDTN.Firstly,the related theoretical knowledge and technologies of VDTN have been described in this thesis.On this basis,the current research status of routing algorithms for delay tolerant networks has been analyzed with emphasis,and Bayesian network and simulation tools for delay tolerant networks have been described in detail.All above these provide a theoretical and technical basis for the design and simulation of the vehicular tolerant network routing algorithm.According to vehicular movement patterns and dynamic topology characteristics of VDTN,a new routing algorithm based on Bayesian Network(BN)is proposed to construct the prediction model,which intends to predict the movement patterns of nodes in the real VDTN scenarios.Firstly,a comprehensive BN model is established,where excellent attributes of nodes are selected to improve the accuracy of the model prediction.Then,considering the complexity of the structure learning problem of BN,a novel structure learning algorithm,K2 algorithm based on Genetic Algorithm(K2-GA),is proposed to search the optimal BN structure efficiently.At last,Junction Tree Algorithm(JTA)is adopted in the inference of BN.The simulation results show that the proposed VDTN routing algorithm based on the BN model can improve the delivery ratio with a minor forwarding overhead.Morever,considering the time-period characteristics of the node movement patterns,Vehicular Delay Tolerant Network Routing Algorithm Based on Optimized Multi-period BN is proposed to construct the prediction model,which improves the accuracy by constructing multi-period BN model.Firstly,more attributes of nodes are selected to improve the accuracy of the model prediction.And then,the dynamic reward mechanism for node classification is also improved with a new formula of encounter reward and delivery reward,which makes the reward allocation more reasonable.Finally,on the basis of K2-GA algorithm,binary K2-GA algorithm(B-K2GA)and simulated annealing K2-GA algorithm(SA-K2GA)are proposed to learn the time division of multi-period BN.B-K2 GA optimizes the time division and BN structure by binary greedy strategy,which has the advantages of simplicity and efficiency;SA-K2 GA combines SA algorithm and K2-GA algorithm,which can escape the local optimum and further optimize the performance of the solution.The research in this thesis can not only apply widely to the real world such as VDTN,but also provide ideas for the research of routing protocols in social-tolerant networks,which has a good theory value and application prospect.