Abstract-Vehicular Delay-Tolerant Networks (VDTNs) are an application of the Delay-Tolerant Network (DTN) concept, where the movement of vehicles and their message relaying service is used to enable network connectivity under unreliable conditions. To address the problem of intermittent connectivity, long-term message storage is combined with routing schemes that replicate messages at transfer opportunities. However, these strategies can be inefficient in terms of network resource usage. Therefore, efficient scheduling and dropping policies are necessary to improve the overall network performance. This work presents a performance analysis, based on simulation, of the impact of different scheduling and dropping policies enforced on Epidemic and Spray and Wait routing schemes. This paper evaluates these policies from the perspective of their efficiency in reducing the message's end-to-end delay. In our scenario, it is shown that when these policies are based on the message's lifetime criteria, the message average delay decreases significantly and the overall message delivery probability also increases for both routing protocols. Further simulations show that these results outperform the MaxProp and PRoPHET routing protocols that have their own scheduling and dropping mechanisms.
Due to the diversity of network services and the unpredictability of their behaviors, there is an increasing need for tools that can aid in the global management of IP networks. Being able to predict network data can be very useful to anticipate network upgrading decisions or changes on the network functional operation. This paper proposes a practical approach, based on neural networks, that is able to predict network traffic in a specific network link. In order to improve the prediction capabilities of the different neural network models, sliding window and multitask learning mechanisms are introduced and tested. By applying this prediction framework to different network links, it will be possible to predict the evolution of the global network traffic and use this information for network security, management and planning purposes. The results obtained by applying the proposed model to realistic network scenarios show that this concept can achieve excellent performance in the prediction of the network traffic on the selected links. The prediction is accurate even when there are significant changes in the number of users and their respective profiles. Moreover, the proposed prediction approach is generic and can be used to predict different network data with a very satisfactory accuracy, even with simple and small NN models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.