Jaudelice Cavalcante de Oliveira

Proactive versus reactive routing in low power and lossy networks: Performance analysis and scalability improvements

In this paper, the classical debate on suitability of proactive versus reactive routing approaches is revisited, however in the context of their application in Low-Power Lossy Networks (LLNs) as opposed to pure Mobile Ad Hoc Networks (MANETs). We argue that LLNs differ from traditional ad hoc networks not only due to node capacity, but also in the nature of traffic generation and routing requirements. This study aims at a fair comparison between two protocols proposed at the IETF, namely RPL (IPv6 Routing Protocol for Low-Power and Lossy Networks) - the proactive candidate, and LOADng (LLN On-demand Ad-hoc Distance vector routing protocol - next generation) - the reactive candidate, making use of real traffic scenarios and topology deployments of varied size, as well as random topologies in the particular case of metrics relating to scalability. Several metrics of interest are investigated, including metrics that have not been paid much attention in the existing MANET literature. In the course of this investigation, we also uncovered non-optimal protocol behavior for the case of large networks and proposed new mechanisms that are shown to improve control plane congestion, as a result improving network lifetime for large scale LLNs. We also derive bounds on control overhead for the two protocols, which indicate that RPL incurs an overhead that is lower than O(N^2) and reduces to @Q(Nlog(N)) for a balanced tree structure, whereas LOADng has a total control overhead of @Q(N^2), irrespective of topology.

Preemption rates for a parallel link loss network

We consider a two parallel link network supporting K call classes, where a class k call may preempt if necessary any calls of classes k+1,...,K, and may in turn be preempted by any calls of class 1,...,k-1. The two links are a (preferred) primary link (PL) and a backup link (BL). The preemption policy permits both preemption from the PL to the BL (a transfer) if possible, and eviction from either link if necessary. We characterize the rates of an arriving class k call causing preemption of an active lower priority call, and of an active class k call being preempted by an arriving higher priority call. When all classes share a common service rate, we express the preemption rates for each class in terms of the Erlang-B blocking probability equation. Simple expressions for the preemption rates are obtained in the heavy traffic limit. When classes have individual service rates, we approximate the preemption rates for each class using nearly completely decomposable (NCD) Markov chain techniques. The accuracy of the approximation improves with increasing timescale separation between classes.

Decoupling Policy from Routing with Software Defined Interdomain Management: Interdomain Routing for SDN-Based Networks

In this paper, we review why BGP is a poor candidate to facilitate the next generation of Software Defined Networks (SDN) and propose the Interdomain Management Layer (IML) architecture, a framework for facilitating interdomain resource sharing between these networks. IML uses a concept we call horizontal slicing, that allows SDN networks to become autonomous peers with other ASes, while maintaining centralized, operator-facing policy control and end-to- end flow control across interdomain boundaries.

Dynamic traffic engineering for mixed traffic on international networks

In this paper, a novel distributed dynamic traffic engineering (Dynamic TE) mechanism is proposed. The mechanism periodically updates bandwidth reservation and selects the optimum path (resizing and rerouting) for each TE-LSP according to its computed traffic load, leading to path reoptimization and better network utilization. Different resizing policies are investigated and their effect on QoS is analyzed. Detailed performance analysis is then undertaken using simulations on conditions similar to an international transit network. A mixed load of voice and data traffic originating in different timezones is used on a realistic network where all the links have an independent probability of failure. The simulation results show significant performance improvement using Dynamic TE for several metrics of interest and give insight into several scenarios that could benefit from its deployment.

Adoption of Bundled Services with Network Externalities and Correlated Affinities

The goal of this article is to develop a principled understanding of when it is beneficial to bundle technologies or services whose value is heavily dependent on the size of their user base, that is, exhibits positive exernalities. Of interest is how the joint distribution, and in particular the correlation, of the values users assign to components of a bundle affect its odds of success. The results offer insight and guidelines for deciding when bundling new Internet technologies or services can help improve their overall adoption. In particular, successful outcomes appear to require a minimum level of value correlation. Categories and Subject Descriptors (2012): Networks -- Network Algorithms -- Network economics; Networks -- Network properties -- Network dynamics; Information systems -- Information systems applications -- Collaborative and social computing systems and tools; Security and privacy -- Human and societal aspects of security and privacy; Human-centered computing -- Collaborative and social computing theory, concepts and paradigms

A new system for controlled testing of sensor network applications: architecture, prototype and experimental evaluation

In this paper we first argue the case for a system which can accurately reproduce sensed input or stimuli for fair evaluation of wireless sensor network applications. It is shown, with a simple example, that consistent input is crucial in the evaluation of applications, and that the lack of such rigor may lead to wrong conclusions, and therefore a biased choice of what seems to be the best application. We present an architecture for a system that utilizes sensor nodes to provide the required stimuli and can exercise control over other sensor nodes that are executing the application under test. In our architecture, each sensor node executing the application under test is paired with a modified sensor node called the control node. We showcase a prototype implementation of the architecture using the MICAz hardware platform and TinyOS operating system software. Evaluation results for the prototype in a network setting are then presented. Our architecture, to the best of our knowledge, is the first to provide the benefits of both hardware-based and software-based approaches to enable controlled testing of sensor network applications. We also provide an optimization formulation for finding the least number of nodes through which control packets can be disseminated to every control node in the network.

Admission control and preemption policy design of multi-class computer networks

The subject of optimal admission control for maximizing revenue in multiclass loss networks has been well studied. Preemption policies, employed in the Differentiated Services network architecture, serve as an additional type of loss network control, where active low priority calls may be selectively preempted upon the arrival of a high priority call. This paper studies the joint use of admission control and preemption for a two class loss link where per-class revenues are earned per unit time for each active call, and an instantaneous preemption cost is incurred whenever the preemption mechanism is employed. Our main result is if the preemption cost is not too high then the system revenue under the optimal preemption policy with no admission control (complete sharing) exceeds that of the optimal admission control policy with no preemption. That is, preemption control is superior to admission control provided the preemption cost is not too high. Results are established via dynamic programming.

Performance analysis of a parallel link network with preemption

Preemption can be used to provide improved availability and reliability to high priority traffic on a congested network, or when the network experiences link or node failures and traffic needs to be rerouted. The use of preemption permits improved blocking probabilities and traffic alignment on shortest paths for high priority traffic at the expense of performance degradation for low priority traffic. Such policies have been deployed in a variety of scenarios and are very attractive for a service provider. For instance, the Internet Engineering Task Force (IETF) traffic engineering working group (tewg) pointed out the need for priority and preemption parameters as traffic engineering attributes in a multiprotocol label switching (MPLS) network. In this paper we analyze a simple two parallel link network supporting two service classes, where the high priority (HP) class has hard preemptive priority over the low priority (LP) class. This simple two link topology can be thought of as an abstraction of a (more desirable) primary route and a (less desirable) secondary route connecting a given source destination pair in a large network. The preemption policy permits both preemption from the primary link to the secondary link (a transfer) if possible, and eviction from either link if necessary. Analysis of the system is trivial for HP streams, and quality of service (QoS) is captured by the admission probabilities on the primary and secondary links (which are independent of the LP traffic). For the LP streams, however, the QoS is specified both by admission rates on both links as well as preemption rates from both links. We are able to analyze the preemption and departure rates of LP streams in this system in terms of the Erlang-B blocking probability equation for an M/M/c/c queue. Numerical and simulation results show very good agreement and demonstrate some interesting behavior.

Guest Editorial Trading Rate for Delay at the Application and Transport Layers

The 19 papers in this special issue present a representative sample from the diverse collection of viewpoints and approaches regarding the relationship between rate and delay in reliable network communication.

CAM05-5: Bandwidth Constraint Models: A Performance Study with Preemption on Link Failures

Bandwidth constraint models have been a topic of intense discussions at the IETF meetings. Three conventional methods have been described in informational IETF RFCs and their performance on a single link has been analyzed and discussed in the literature. In this article, we take a further step into analyzing their performance and optimal bandwidth constraint setting for a real network scenario. A new model is proposed and compared to existing ones when failure events may cause preemption of traffic trunks in a network. Our simulations results provide great insight on the benefits of the methods.