IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Stateless RD Network Services
Get PDFRate-Delay (RD) Network Services constitute a promising
differentiated-services architecture for multi-provider networks, by offering users a choice between high throughput or low queuing delay at
bottleneck links. An RD router provides service differentiation via transmission scheduling and by managing two FIFO queues. To ensure strict
delay bounds, an RD router tracks arrival times of packets in the D
service queue, and discards late packets at the queue head. However,
maintaining the per-packet state is undesirable for complexity and cost
reasons. In this paper, we present a Stateless RD (S-RD) router design
that provides low queuing delay to the D service exclusively via buffer
dimensioning, without requiring any per-packet state. After proving analytically that the S-RD design meets the delay guarantees, we use simulation to evaluate the performance of the stateless design, confirming
that S-RD routers preserve the delay bounds of RD network services.
As case studies, we consider Voice-over-IP (VoIP) and Web browsing as
particular examples of Internet applications. The extensive simulation
results demonstrate that S-RD Network Services significantly improve
VoIP quality and increase the goodput of short-lived Web flows, without
degrading the throughput of long-lived flows.TRUEpu
Eventual Leader Election with Weak Assumptions on Initial Knowledge, Communication Reliability, and Synchrony
Get PDFoai:dspace.networks.imdea.org:20.500.12761/150This paper considers the eventual leader election problem in asynchronous message-passing systems where an arbitrary number t of processes can crash (t < n, where n is the total number of processes). It considers weak assumptions both on the initial knowledge of the processes and on the network behavior. More precisely, initially, a process knows only its identity and the fact that the process identities are di®erent and totally ordered (it knows neither n nor t). Two eventual leader election protocols and a lower bound are presented. The ¯rst protocol assumes that a process also knows a lower bound ® on the number of processes that do not crash. This protocol requires the following behavioral properties from the underlying network: the graph made up of the correct processes and fair lossy links is strongly connected, and there is a
correct process connected to (n ¡ f) ¡ ® other correct processes (where f is the actual number of crashes in the considered run) through eventually timely paths (paths made up of correct processes and eventually timely links). This protocol is not communication-e±cient in the sense that each correct process has to send messages forever. The second protocol is communication-e±cient: after some time, only the ¯nal common leader has to send messages forever. This protocol does not require the processes to know ®, but requires stronger properties from the underlying network: each pair of correct processes has to be connected by fair lossy links (one in each direction), and there is a correct process whose n ¡ f ¡ 1 output links to the rest of correct processes have to be eventually timely. A matching lower bound result shows that any eventual leader election protocol must have runs with this number of eventually timely links, even if all processes know all the processes identities. In addition to being communication-e±cient, the second protocol has another noteworthy e±ciency property, namely, be the run ¯nite or in¯nite, all the local variables and message ¯elds have a ¯nite domain in the run.TRUEpu
Impact of Prefix Hijacking on Payments of Providers
Get PDFWhereas prefix hijacking is usually examined from security perspectives, this paper looks at it from a novel economic angle. Our study stems from an observation that a transit AS(Autonomous System) has a financial interest in attracting extra traffic to the links with its customers. Based on real data about the actual hijacking incident in the Internet, we conduct simulations in the real AS-level Internet topology with synthetic demands for the hijacked traffic. Then, we measure traffic on all inter-AS links and compute the payments of all providers. The analysis of our results from technical, business, and legal viewpoints suggests that hijacking-based traffic attraction is a viable strategy that can create a fertile ground for tussles between providers. In particular, giant top-tier providers appear to have the strongest financial incentives to hijack popular prefixes and then deliver the intercepted traffic to the proper destinations. We also discuss directions for future research in the area of hijacking-based traffic attraction.Telematics EngineeringUniversidad Carlos III de Madrid, Spainpu
HURP/HURBA: Zero-configuration hierarchical Up/Down routing and bridging architecture for Ethernet backbones and campus networks
Get PDFEthernet switched networks do not scale appropriately due to limitations inherent to the spanning tree protocol. Ethernet architectures based on routing over a virtual topology in which turns are prohibited offer improved performance over spanning tree, although in some cases suffer from excessive computational complexity. Up/Down routing is a turn prohibition algorithm with low computational complexity. In this paper we propose
HURBA, a new layer-two architecture that improves Up/Down routing performance due to an optimization based on the use of hierarchical addressing, while preserving the computational complexity of Up/Down. The resulting architecture requires zero-configuration, uses the same frame format as Ethernet, allows upgrades by software update, and is compatible with 802.1D bridges by means of encapsulation. HURP protocol builds automatically a core with the interconnected HURP routing bridges and the standard bridges get connected to the edges in standard spanning trees. Simulations show that the performance of HURP, evaluated over various combinations of network topology and size, is close to the one of shortest path, is consistently better than that of Up/Down, and is equal or better than Turn Prohibition, with the advantage of having a lower complexity.TRUEpu
Polar Coordinate Routing for Multiple Paths in Wireless Networks
No full textISBN: 978-1-4244-7264-2We propose Polar Coordinate Routing (PCR) to
create multiple paths between a source and a destination in
wireless networks. Our scheme creates paths that are circular
segments of different radii connecting a source and a destination. We propose a non−euclidean distance metric that allows
messages to travel along these paths. Using PCR it is possible to
maintain a known separation among the paths, which reduces the
interference between the nodes belonging to two separate routes.
Our extensive simulations show that while PCR achieves a known
separation between the routes, it does so with a small increase in
overall hop count. Moreover, we demonstrate that the variances
of average separation and hop count are lower for the paths
created using PCR compared to existing schemes, indicating a
more reliable system. Existing multi−path routing schemes in
wireless networks do not perform well in areas with obstacles
or low node density. To overcome adverse areas in a network,
we integrate PCR with simple robotic routing, which lets a
message circumnavigate an obstacle and follow the trajectory
to the destination as soon as the obstacle is passedTRUEpu
Dynamic Random Replication for Data Centric Storage
Get PDFThis paper presents a novel framework for Data Centric
Storage in a wireless sensor and actor network that enables
the use of a randomly-selected set of data replication nodes
which also change over the time. This allows reducing the
average network traffic and energy consumption by adapt-
ing the number of replicas to applications' traffic, while bal-
ancing energy burdens by varying their location. To that
end we propose and validate a simple model to determine
the optimal number of replicas, in terms of minimizing av-
erage traffic/energy consumption, from the measured ap-
plications' production/consumption traffic. Simple proto-
cols/mechanisms are proposed to decide when the current
set of replication nodes should be changed, to enable new
applications and sensor nodes to efficiently bootstrap into a
working sensor network, to recover from failing nodes, and to
adapt to changing conditions. Extensive simulations demon-
strate that our approach can extend a sensor network's life-
time by at least a 60%, and up to a factor of 10x depending
on the lifetime criterion being considered.TRUEpu
Contribution to the Future Project Planning Meeting
No full textInstitute IMDEA Networks had a key role on the strong impact of the CARMEN project in the IEEE standardization body. One of the Working Groups of this body corresponds to the IEEE 802.21, LAN/MAN standard on Media Independent Handover Services.
This standard proposes several media abstraction ideas that were extended during the CARMEN project. In particular IMDEA researchers worked on the following key issues:
Study Group created to analyze Heterogeneous Wireless Backhaul Networks
IMDEA Networks together with UC3M, NEC and Fraunhoffer Institute worked for several years in explaining the concept Heterogeneous Wireless Backhauls and the possibility of using .21 as a media independent service layer offering mechanisms to abstract the specific technologies to the management plane.
Different contributions to IEEE 802.21
Within the study group, several contributions such as applicability use cases, new research on abstracting the parameters of the underlying technologies and contacts with different companies were performed.
Innovation leadership via participation in the Future Projects planning sessions
The IEEE 802.21 WG is now looking at new problems and standardization challenges to continue its work, since the base specification is finished and the three amendments planned are advancing as foreseen. In order to find new projects, the WG celebrates special sessions in the plenary meetings, called Future Projects planning sessions. IMDEA Networks and UC3M are leading partners in these meetings, providing new ideas and pushing for the development of new technologies.
Ongoing effort in IEEE 802.19.1 Coexistence of Wireless Networks in the TV White Space
Within the Future Planning sessions, one of the ideas that got a major support from the companies on the WG was the idea of using the MIHF defined in IEEE 802.21 as part of the upcoming IEEE 802.19.1, standard that analyses the coexistence of wireless technologies on the TV White Spaces spectrum. Researchers at IMDEA Networks contributed to defining this interaction between .21 and .19.1, which was submitted as contribution to this working group.IEEEpu
A peer-to-peer IPTV service architecture for the IP multimedia subsystem
No full textDuring these last years the Internet Protocol Television (IPTV) service and the different peer-to-peer (P2P) technologies have generated an increasing interest for the developers and the research community that find in them the solution to deal with the scalability problem of media streaming and reducing costs at the same time. However, despite of the benefits obtained in Internet-based applications and the growing deployment of commercial IPTV systems, there has been a little effort in combining them both. With the advent of the next-generation-network platforms such as the IP Multimedia Subsystem (IMS), which advocates for an open and inter-operable service infrastructure, P2P emerges as a possible solution in situations where the traditional streaming mechanisms are not possible or not economically feasible.
In this paper, we propose an IPTV service architecture for the IMS that combines a centralized control layer and a distributed, P2P-like, media layer that relies on the IMS devices or peers located in the customers' premises to act as streaming forwarding nodes. We extend the existing IMS IPTV standardization work that has already been done in 3GPP and ETSI TISPAN in order to require a minimum number of architectural changes. The objective is to obtain a system with a similar performance to the one in currently deployed systems and with the flexibility of P2P. One of the main challenges is to achieve comparable response times to user actions such as changing and tuning into channels, as well as providing a fast recovery mechanism when streaming nodes leave. To accomplish this we introduce the idea of foster peers as peers having inactive multimedia sessions and reserved resources. These peers are on stand-by until their functionality is required and at that moment, they are able to accept downstream peers at short notice for events requiring urgent treatment like channel changing and recovery.TRUEpu
Secure data collection in wireless sensor networks using randomized dispersive routes
Get PDFCompromised-node and denial-of-service are two key attacks in wireless sensor networks (WSNs). In this paper, we study routing mechanisms that circumvent (bypass) black holes formed by these attacks. We argue that existing multi-path routing approaches are vulnerable to such attacks, mainly due to their deterministic nature. So once an adversary acquires the routing algorithm, it can compute the same routes known to the source, and hence endanger all information sent over these routes. In this paper, we develop mechanisms that generate randomized multipath routes. Under our design, the routes taken by the “shares”
of different packets change over time. So even if the routing algorithm becomes known to the adversary, the adversary still cannot pinpoint the routes traversed by each packet. Besides randomness, the routes generated by our mechanisms are also highly dispersive and energy-efficient, making them quite capable of bypassing black holes at low energy cost. Extensive simulations are conducted to verify the validity of our mechanisms.TRUEpu