Abstract

The inflexibility and rigidity of the current networking systems in light of the growing number of computing devices that connected to the Internet has led to the need of a new generation of computer networks. In this context, software-defined network has recently emerged as one of the most recognisable solutions to facilitate the network management and decrease the complexity through detaching the control layer from network appliances. Since, each new technology accompanied with new issues and concerns, one of the main challenges that facing the SDNs is the fault tolerance and resilience. Although there are a numerous of studies that have discussed this issue, the after failure repair scenario is remained unclear and have not addressed well yet. For this reason, we specify this paper as a step forward to address the issue of routing changes, which is important for utilising the optimal paths after failure repair. We produced a new network model as well as a compatible framework with SDN architecture to fulfil the routing changes activity. The consequence is estimated based on an analytical model and finally, a case study example is provided in order to conceptualise the concept. Document type: Part of book or chapter of book

Abstract

With the expected surge in the global IP traffic, service providers would need to adapt accordingly to operate disruption and loss free networks supported with the developing IP infrastructure. With the disposal of the hierarchical network structure, radio access networks are moving towards a flat-IP architecture and novel topological set-ups in the backhaul. Hence, a routing paradigm that employs suitable Traffic Engineering (TE) techniques aligned with the developing nature of future access networks must be applied. In this paper, Multi-Plane Routing (MPR) that consolidates various aspects in all-IP infrastructure is remodelled in consistent with this development. We propose a MPR-based TE approach considering two different scenarios to reflect the evolution in the architectural design of access network structures under a realistic traffic scenario with a varying range of internal/external traffic. Accordingly, a practical performance evaluation testing the validity of the aforementioned scenarios is presented. Our simulation results demonstrate a better achieved performance under the flat-IP structure in addition to MPR-based methods' superiority over legacy OSPF/Invcap. Performance degradation is observed with the rise in the internal traffic distribution for the different scenarios studied. Moreover, a new optimization framework for the offline and online TE mechanisms of MPR have been proposed.

Abstract

In this era of ubiquitous computing, coupled with the emergence of big data and internet of things, there have been constant changes in every aspect of cloud data center communications - its network connectivity, data storage, data transfer, and architectural design. As a result of this, the amount of data transferable, and the frequency of data transfer have tremendously increased; causing device failures and traffic congestions. To cope with these changes so that performance can be sustained amidst device failures and traffic congestion, the design of fault tolerant cloud data center is important. A fault tolerant cloud data center network should be able to provide alternative paths from source to destination during failures so that there will not be abrupt fall in performance. But still with the ongoing researches in this regard, there has not been a robust cloud data center design that can boast of being suitable for alleviating the poor fault tolerance of cloud data center. In this paper, we proposed the improved versions of fat-tree interconnection hybrid designs derived from the structure called Z-fat tree; to address the issues of fault tolerance. Then, we compared these designs with single fat tree architecture with the same amount of resources for client server communication pattern such as Email application in a cloud data center. The simulation results obtained based on failed switches and links, show that our proposed hybrid designs outperformed the single fat tree design as the inter arrival time of the packets reduces.

Abstract

This article discusses the results of supporting transition towards fully automated driving with remote operator support via the novel V2X channels. Automated passenger cars are equipped with multiple sensors (radars, cameras, LiDARs, inertia, GNSS, etc.), the operation of which is limited by weather, detection range, processing power and resolution. The study explores the use of a dedicated network for supporting automated driving needs. The MEC server latencies and bandwidths are compared between the Tampere, Finland test network and studies conducted in China to support remote passenger car operation. In China the main aim is to evaluate the network latencies in different communication planes, whereas the European focus is more on associated driving applications, thus making the two studies mutually complementary.5G revolutionizes connected driving, providing new avenues due to having lower and less latency variation and higher bandwidths. However, due to higher operating frequencies, network coverage is a challenge and one base station is limited to a few hundred meters and thus they deployed mainly to cities with a high population density. Therefore, the transport solutions are lacking so-called C-V2X (one form of 5G RAT) to enable data exchanges between vehicles (V2V) and also between vehicles and the digital infrastructure (V2I). The results of this study indicate that new edge-computing services do not cause a significant increase in latencies $(\\lt 100$ ms), but that latency variation (11 - 192 ms) remains a problem in the first new network configurations.