Virtual networks: isolation, performance, and trends

Currently, there is a strong effort of the research community in rethinking the Internet architecture to cope with its current limitations and support new requirements. Many researchers conclude that there is no one-size-fits-all solution for all of the user and network provider needs and thus advocate for a pluralist network architecture, which allows the coexistence of different protocol stacks running at the same time over the same physical substrate. In this paper, we investigate the advantages and limitations of the virtualization technologies for creating a pluralist environment for the Future Internet. We analyze two types of virtualization techniques, which provide multiple operating systems running on the same hardware, represented by Xen, or multiple network flows on the same switch, represented by OpenFlow. First, we define the functionalities needed by a Future Internet virtual network architecture and how Xen and OpenFlow provide them. We then analyze Xen and OpenFlow in terms of network programmability, processing, forwarding, control, and scalability. Finally, we carry out experiments with Xen and OpenFlow network prototypes, identifying the overhead incurred by each virtualization tool by comparing it with native Linux. Our experiments show that OpenFlow switch forwards packets as well as native Linux, achieving similar high forwarding rates. On the other hand, we observe that the high complexity involving Xen virtual machine packet forwarding limits the achievable packet rates. There is a clear trade-off between flexibility and performance, but we conclude that both Xen and OpenFlow are suitable platforms for network virtualization.     

Routing Metrics and Protocols for Wireless Mesh Networks

WMNs are low-cost access networks built on cooperative routing over a backbone composed of stationary wireless routers. WMNs must deal with the highly unstable wireless medium. Therefore, the design of algorithms that consider link quality to choose the best routes are enabling routing metrics and protocols to evolve. In this work, we analyze the state of the art in WMN metrics and propose a taxonomy for WMN routing protocols. Performance measurements for a WMN, deployed using various routing metrics, are presented and corroborate our analysis.     

Improving the multiple access method of home networks over the electrical wiring

Data communications on domestic low-voltage powerlines benefit from an ubiquitous and already existent infrastructure. Nevertheless, high-speed communications on this environment faces obstacles such as attenuation and noise. The HomePlug standard defines Media Access Control (MAC)- and physical (PHY)-layer protocols for home electrical wiring networks. Its MAC protocol has introduced the deferral counter (DC) mechanism, which adapts the contention of the nodes for the medium according to the network load. This article proposes the Contention window Pro-active Increase (CPI) mechanism to enhance the performance of HomePlug. The CPI mechanism is based on DC and improves the HomePlug efficiency by faster increasing the contention window size. As a consequence, there are fewer collisions and the aggregated throughput increases. Under high network load, our simulation results show a tradeoff concerning throughput and jitter. CPI improves HomePlug throughput by up to 3% with no jitter increase and by up to 15% at the cost of additional jitter.     

The ad hoc return channel: a low-cost solution for Brazilian interactive digital TV

The upcoming terrestrial digital television technology brings a new class of services to traditional TV sets. A set-top box may, for example, access the Internet and send email. The interactive return channel makes these new services possible. This channel allows TV viewers to interact by sending data back to the TV broadcaster. In this article we analyze the viability of a wireless ad hoc network to implement the return channel. For this purpose, an ad hoc network is a low-cost and flexible solution. We evaluate the performance of an ad hoc return channel using the IEEE 802.11 wireless technology for different Brazilian geographical scenarios. The results show that ad hoc networking is a promising solution for the return channel of Brazilian interactive digital TV     

Reliability and Survivability Analysis of Data Center Network Topologies

The architecture of several data centers have been proposed as alternatives to the conventional three-layer one. Most of them employ commodity equipment for cost reduction. Thus, robustness to failures becomes even more important, because commodity equipment is more failure-prone. Each architecture has a different network topology design with a specific level of redundancy. In this work, we aim at analyzing the benefits of different data center topologies taking the reliability and survivability requirements into account. We consider the topologies of three alternative data center architecture: Fat-tree, BCube, and DCell. Also, we compare these topologies with a conventional three-layer data center topology. Our analysis is independent of specific equipment, traffic patterns, or network protocols, for the sake of generality. We derive closed-form formulas for the Mean Time To Failure of each topology. The results allow us to indicate the best topology for each failure scenario. In particular, we conclude that BCube is more robust to link failures than the other topologies, whereas DCell has the most robust topology when considering switch failures. Additionally, we show that all considered alternative topologies outperform a three-layer topology for both types of failures. We also determine to which extent the robustness of BCube and DCell is influenced by the number of network interfaces per server.     

A routing protocol suitable for backhaul access in wireless mesh networks

This work proposes the Wireless-mesh-network Proactive Routing (WPR) protocol for wireless mesh networks, which are typically employed to provide backhaul access. WPR computes routes based on link states and, unlike current routing protocols, it uses two algorithms to improve communications in wireless mesh networks taking advantage of traffic concentration on links close to the network gateways. WPR introduces a controlled-flooding algorithm to reduce routing control overhead by considering the network topology similar to a tree. The main goal is to improve overall efficiency by saving network resources and avoiding network bottlenecks. In addition, WPR avoids redundant messages by selecting a subset of one-hop neighbors, the AMPR (Adapted MultiPoint Relay), needed to reach all two-hop ones. We first analyze the proposed algorithms compared with the algorithms used by OLSR for the same tasks in terms of running time, optimality, and number of routing messages. Results show that the algorithms proposed by WPR are more efficient than the algorithms used by OLSR in running time and number of routing messages. In addition, we also perform simulations to evaluate the performance of WPR. Results reveal that the aggregated throughput of WPR outperforms OLSR by up to 27% using a combination of web and backbone internal traffic despite our design assumption of traffic convergence toward gateways.     

Impact of relative speed on node vicinity dynamics in VANETs

Communication protocols generally rely on the existence of very long multihop paths to reach distant nodes. They disregard, however, how often such paths indeed occur, and how long they persist, especially in highly dynamic mobile networks. In this direction, this paper evaluates quantitatively the influence of node relative speed on path establishment and maintenance, using real and synthetic vehicular network traces. We propose a methodology for vehicular network analysis where both relative speeds and hop distances are used as parameters to characterize node vicinity. Results show that contact opportunities highly depend on the relative speed and the hop distance between nodes. In sparser scenarios, the number of contacts between nodes separated by more than 3 hops or even between neighbors with relative speed above 40 km/h is negligible. This confirms the intuition that contacts at lower relative speeds and at few hop distances happen more often. In addition, contacts last longer as the number of hops between nodes decreases. Nevertheless, we can still find multihop paths able to transmit messages at high relative speeds, even though less often. We also demonstrate that relative speeds reduce the number of useful contacts more severely when compared to the hop distance. For last, we show that it is possible to increase the number of successful packet transmissions by simply applying the outcomes of this work, without any sophisticated model, avoiding the waste of resources, such as energy and bandwidth.

     

Measuring the capacity of in-car to in-car vehicular networks

A particular class of vehicular networks is the one that includes off-the-shelf end-user equipment (e.g., laptops and PDAs) running from the interior of vehicles: in-car nodes. They are subject to limited communication conditions when compared with nodes specifically designed to this context. Existing works either consider antennas installed on top of the vehicle roof or nodes that operate in infrastructure mode. In this article, we investigate through real experiments the characteristics of links formed by incar nodes running off-the-shelf wireless technologies such as IEEE 802.11(a/g) in ad hoc mode. We surprisingly observe that in-car nodes do show enough performance in terms of network capacity to be used in a number of applications, such as file transfer in peer-to-peer applications. Nonetheless, we identify some key performance issues and devise a number of configuration recommendations and future work directions.