Search

This paper provides a theoretical performance analysis of different classes of multicast routing algorithms, namely the Shortest Path Tree, the Steiner Tree, compact routing and greedy routing. Our motivation is to determine the routing scheme which would yield the best trade-off between the stretch of the multicast routing paths, the memory space required to store the routing information and routing table as well as the communication cost. For this purpose, we also confront these results to those obtained by simulation on the CAIDA map of the Internet topology comprising 32k nodes.

The real-world node deployment aspect is investigated, while considering cost minimization for resolving the energy hole around the sink, which represents a serious problem in typical sensor networks with uniform distribution. A novel strategy is proposed that is based on the use of two sinks and a few extra relay nodes close to the sinks' areas. The traffic is then alternatively sent to the sinks in every other cycle. As a second contribution, an efficient data collection mechanism has been developed to determine the optimal data rate that meets delay requirements of individual sensor reports and improves the network lifetime. The comparison of the proposed node deployment strategy with uniform, non-uniform geometric and linear increase node distributions demonstrates that the cost of the proposed solution is very close to that of the uniform distribution and much lower than all the others, while achieving a load balancing at the same order of the state-of-the-art solutions.

We analyze the objective cost of SBVTs as a function of the traffic conveyed by IP/MPLS-over-flexgrid networks. Optimal results show that cost increment with respect to BVTs is related to the aggregation level.

High-radix hierarchical networks are cost-effective topologies for large scale computers. In such networks, routers are organized in super nodes, with local and global interconnections. These networks, known as Dragonflies, outperform traditional topologies such as multi-trees or tori, in cost and scalability. However, depending on the traffic pattern, network congestion can lead to degraded performance. Misrouting (non-minimal routing) can be employed to avoid saturated global or local links. Nevertheless, with the current deadlock avoidance mechanisms used for these networks, supporting misrouting implies routers with a larger number of virtual channels. This exacerbates the buffer memory requirements that constitute one of the main constraints in high-radix switches. In this paper we introduce two novel deadlock-free routing mechanisms for Dragonfly networks that support on-the-fly adaptive routing. Using these schemes both global and local misrouting are allowed employing the same number of virtual channels as in previous proposals. Opportunistic Local Misrouting obtains the best performance by providing the highest routing freedom, and relying on a deadlock-free escape path to the destination for every packet. However, it requires Virtual Cut-Through flow-control. By contrast, Restricted Local Misrouting prevents the appearance of cycles thanks to a restriction of the possible routes within super nodes. This makes this mechanism suitable for both Virtual Cut-Through and Wormhole networks. Evaluations show that the proposed deadlock-free routing mechanisms prevent the most frequent pathological issues of Dragonfly networks. As a result, they provide higher performance than previous schemes, while requiring the same area devoted to router buffers. This work has been supported by the Spanish Ministry of Science under contracts TIN2010-21291-C02-02, TIN2012-34557, and by the European HiPEAC Network of Excellence. The research leading to these results has received funding from the European Research Council under the European Union’s Seventh Framework Programme (FP/2007-2013) / ERC Grant Agreement n. ERC-2012-Adg-321253-RoMoL. M. Garc´ıa and M. Odriozola participated in this research work while they were affiliated with the University of Cantabria.

Network virtualization opens the door to novel infrastructure services offering connectivity and node manageability. In this letter, we focus on the cost-efficient embedding of on-demand virtual optical network requests for interconnecting geographically distributed data centers. We present a mixed integer linear programming formulation that introduces flexibility in the virtual-physical node mapping to optimize the usage of the underlying physical resources. Illustrative results show that flexibility in the node mapping can reduce the number of add-drop ports required to serve the offered demands by 40%.

Current inter-data-center connections are configured as static big fat pipes, which entails large bit rate over-provisioning and thus high operational costs for DC operators. On the other hand, network operators cannot share such connections between customers, because DC traffic varies greatly over time. Those connections are used to perform virtual machine migration and database synchronization among federated DCs, allowing elastic DC operations. To improve resource utilization and save costs, dynamic inter-DC connectivity is currently being targeted from a research point of view and in standardization form. In this article, we show that dynamic connectivity is not enough to guarantee elastic DC operations and might lead to poor performance provided that not enough overprovisioning of network resources is performed. To alleviate it to some extent, we propose using the flexgrid optical technology that enables finer spectrum granularity adaptation and the ability to dynamically increase and decrease the amount of optical resources assigned to connections. DCs can be interconnected through a flexgrid-based network controlled using a centralized software defined network, based on the architecture currently being proposed by the IETF; a cross-stratum orchestrator architecture coordinates DC and network elastically. Illustrative results show that dynamic elastic connectivity provides benefits by reducing the amount of overprovisioned network resources and facilitating elastic DC operations. The research leading to these results has received funding from the European Community’s Seventh Framework Pro- gramme FP7/2007-2013 under grant agreement no. 317999 IDEALIST project. Moreover, it was supported by the Span- ish science ministry through the TEC2011-27310 ELASTIC project.

Current literature defines the effective capacity of a wireless link as the maximum throughput that can be supported while meeting specific Quality of Service targets on packet delay. This metric can be harnessed for a wide variety of QoS control routines within wireless networks such as traffic optimisation and delay sensitive admission control and routing. However to date, no empirical evaluation of the effective capacity of 802.11 wireless links has been carried out. We present an empirical study of the effective capacity throughput of 802.11 wireless links under a number of network scenarios. We evaluate an analytical effective capacity model and compare the result with an empirical evaluation. We find that with an accurate measurement of the channel service delay, the effective capacity model can approximate the empirical measurement quite well. We also evaluate the relationship between the effective bandwidth of multimedia traffic and demonstrate that when the effective bandwidth exceeds the effective capacity threshold of a wireless link, the probability of QoS violations increases. We conclude that the effective capacity measurement is usable within an operational setting, and can lead to optimized utilization of bandwidth in a wide range of delay sensitive control operations.

The ever increasing IP traffic volume has finally brought to light the high inefficiency of current wavelength-routed rigid-grid networks in matching the client layer requirements. Such an issue results in the deployment of large-size, expensive and power-consuming IP/MPLS layers to perform the required grooming/aggregation functionality. To deal with this problem, the emerging flexgrid technology, allowing for reduced size frequency grids, usually referred to as frequency slot, has recently attracted great attention among network operators, component and equipment suppliers, and the research community. In this paper, we report the main contributions performed in the context of EU STRONGEST project regarding flexgrid optical networks.

Energy consumption of communication networks is growing very fast due to the rapidly increasing traffic demand. Consequently, design of green communication networks gained a lot of attention. In this paper we focus on optical Wavelength Division Multiplexing (WDM) networks, able to support this growing traffic demand. Several energy-aware routing and wavelength assignment (EA-RWA) techniques have been proposed for WDM networks in order to minimize their operational cost. These techniques aim at minimizing the number of active links by packing the traffic as much as possible, thus avoiding the use of lightly loaded links. As a result, EA-RWA techniques may lead to longer routes and to a high utilization on some specific links. This has a detrimental effect on the signal quality of the optical connections, i.e., lightpaths. In this study we quantify the impact of power consumption minimization on the optical signal quality. and address this problem by proposing a combined impairment and energy-aware RWA (IEA-RWA) approach. Towards this goal we developed a complete mathematical model that incorporates both linear and non-linear physical impairments together with an energy efficiency objective. The IEA-RWA problem is formulized as a Mixed Integer Linear Programming (MILP) model where both energy efficiency and signal quality considerations are jointly optimized. By comparing the proposed IEA-RWA approach with existing RWA (IA-RWA and EA-RWA) schemes, we demonstrate that our solution allows for a reduction of energy consumption close to the one obtained by EA-RWA approaches, while still guaranteeing a sufficient level of the optical signal quality.

Optical network infrastructures can be partitioned into multiple parallel, dedicated virtual networks for a physical infrastructure sharing purpose. However, different transport technologies may impact in both the amount and the characteristics of the different virtual instances that can be built on top of a single physical infrastructure. To analyse the impact of the transport technology in this regard, we present exact Integer Linear Programming (ILP) formulations that address the off-line problem of optimally allocate a set of virtual networks in two kind of substrates: wavelength switching and spectrum switching. Both formulations serve the purpose to provide opaque transport services from the virtual network point of view, where electronic terminations are assumed in the virtual network nodes. We carry out a series of experiments to validate the presented formulations and determine which is the impact of both substrates in the number of virtual networks that can be optimally allocated in the transport network.

Network traffic has traditionally exhibited temporal locality in the header field of packets. Such locality is intuitive and is a consequence of the semantics of network protocols. However, in contrast, the locality in the packet payload has not been studied in significant detail. In this work we study temporal locality in the packet payload. Temporal locality can also be viewed as redundancy, and we observe significant redundancy in the packet payload. We investigate mechanisms to exploit it in a networking application. We choose Intrusion Detection Systems (IDS) as a case study. An IDS like the popular Snort operates by scanning packet payload for known attack strings. It first builds a Finite State Machine (FSM) from a database of attack strings, and traverses this FSM using bytes from the packet payload. So temporal locality in network traffic provides us an opportunity to accelerate this FSM traversal. Our mechanism dynamically identifies redundant bytes in the packet and skips their redundant FSM traversal. We further parallelize our mechanism by performing the redundancy identification concurrently with stages of Snort packet processing. IDS are commonly deployed in commodity processors, and we evaluate our mechanism on an Intel Core i3. Our performance study indicates that the length of the redundant chunk is a key factor in performance. We also observe important performance benefits in deploying our redundancy-aware mechanism in the Snort IDS[32].

© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Channel assignment has been extensively researched for multi-radio wireless mesh networks, but it is still very challenging when it comes to its implementation. In this paper we propose a semi-dynamic and distributed channel assignment mechanism called SICA that uses game theory. To the best of our knowledge this is the first game formulation of channel assignment which takes the co-channel interference into account. SICA is an interference aware, distributed channel assignment which preserves the network connectivity without relying on a common channel nor central node for coordination between mesh routers. SICA applies an on-line learner algorithm which assumes that nodes do not have perfect information. We have simulated SICA and compared against another interference-aware channel assignment mechanism proposed in the literature called Urban-X. Simulation results show that SICA outperforms Urban-X, even using fewer radio interfaces per node.

A great part of core network operators’ gross profit comes from the provisioned connectivity services. In this work, we analyze the provisioning of differentiated services in current Shared Path Protection (SPP) environments. This analysis concludes that, with current resource assignment policies, only a very poor grade of service can be provided to the carried best effort traffic. Hence, we propose diff-WS, a resource partitioning scheme that differentiates those wavelengths supporting each class of service in the network. The benefits of diff-WS in front of current resource assignment policies are afterwards evaluated from an economic perspective. To this goal, we define the NORMA problem as a revenue maximization problem. To solve NORMA, we introduce statistical models to obtain, for a given grade of service, the highest traffic intensity for each supported class of service and resource assignment scheme. From the numerical results, we show that diff-WS maximizes resource utilization in the network and, thus, network operator’s profit.

A one-to-one association between data and control channels has traditionally existed in transport networks. Being the control plane embedded in the data plane, the design of the former, as well as its resilience, has been addressed in the latter’s one. However, a main GMPLS architectural requirement is to provide a clean separation between control and data planes. In this sense, the control plane in GMPLS networks may describe a different topology than the data plane, even realized over a separated IP network. As a consequence of this, data and control network design become no more linked in such scenarios. To the best of our knowledge, no works in the literature have addressed an independent design of the control plane in GMPLS-enabled networks regardless of the data plane. In this paper, we provide a method to obtain the optimal GMPLS control plane design, minimizing the network Capital Expenditures (CAPEX) while matching specific resilience requirements. To this goal, the problem of finding an optimal control plane topology that ensures a certain resilience level is formulated as a non-linear combinatorial model. This model, however, does not scale properly for large backbone networks. In view of this, a constructive linear method is also presented and its optimality validated through simulations on several reference network scenarios. Furthermore, its benefits in terms of total execution time are also highlighted.

Network operators are facing hard competition for opportunities in the telecommunications market, forcing network investments to be carefully evaluated before the decision-making process. A great part of core network operators’ revenues comes from the provisioned connectivity services. Taking this premise as our starting point, we first examine the provisioning of differentiated services in current shared-path protection (SPP) environments. This analysis reveals that current resource assignment policies are only able to provide a very poor grade of service to the supported best-effort traffic. Aiming to improve this performance, a novel resource partitioning scheme called diff-WS is proposed, which differentiates those wavelengths supporting each class of service in the network. As a major goal of this paper, the benefits of diff-WS over current resource assignment policies are assessed from an economic perspective. For this purpose, the network operator revenues maximization (NORMA) problem is presented to design the optical network such that the operator’s revenues are maximized. To solve NORMA, we derive statistical models to obtain, given a certain grade of service, the highest traffic intensity for each class of service and resource partitioning scheme. These models turn NORMA into a nonlinear problem, which is finally addressed as an iterative approach, solving an integer linear programming (ILP) subproblem at each iteration. The obtained numerical results on several network topologies illustrate that diff-WS maximizes resource utilization in the network and, thus, the network operator’s profit.

Compact routing schemes address the fundamental tradeoff between the memory space required to store the routing table entries and the length of the routing paths that these schemes produce. This paper introduces the first known name-independent, leaf-initiated dynamic compact routing scheme that allows the distribution of traffic from any source to any set of leaf nodes along a multicast routing path that defines a distribution tree. By means of the proposed scheme, a multicast distribution tree dynamically evolves according to the arrival of leaf-initiated join/leave requests. To evaluate the performance we consider the following metrics: the stretch of the produced routing paths, the size and the number of routing table entries, and the communication cost. The results obtained by simulation on synthetic power law graphs (modeling the Internet topology) show that our scheme can successfully handle leaf-initiated dynamic setup of multicast distribution trees. Two reference multicast routing schemes (the Shortest Path Tree and the Steiner Tree algorithm) are used to compare the performance of the proposed scheme. While increasing the communication cost compared to the Shortest Path Tree, the proposed scheme achieves considerable reduction of the routing table size compared to both reference schemes. Moreover, the stretch of the resulting multicast routing paths show limited deterioration compared to the minimum value obtained with Steiner Trees.

En los últimos años la adopción de MPLS se ha incrementado debido a las ventajas y la cantidad de aplicaciones que ofrece. En una red MPLS se asignan etiquetas a los paquetes según entran al dominio y son conmutados en base a ellas hasta que lo abandonan. Al igual que ocurre en redes IP convencionales, la ruta seguida por los paquetes (denominada LSP o Label Switched Path) puede variar debido a la naturaleza de los protocolos de encaminamiento y a la existencia de fallos en la red. Por lo tanto, conocer la ruta que seguirá el tráfico resulta interesante desde un punto de vista de gestión de red. Este proyecto tiene como objetivo el diseño e implementación de un sistema capaz de determinar el camino que seguirá un cierto patrón de tráfico a través de una red IP con funcionalidades MPLS. A alto nivel, la aplicación trata de reproducir la ruta que seguiría el tráfico. Para ello emula el proceso de decisión que realiza cada router a partir de las características del paquete y la información de encaminamiento de la que dispone. Esto requiere la adquisición de dicha información la cual se almacenará y procesará de forma eficiente. Por último, se necesitará un algoritmo que realice el cómputo de las trayectorias.

Differentiated services provision according to clients or applications is an added feature that network operators ambition to fully provide. One of the possible approaches is to map DiffServ into MPLS based network. However in an IP over WDM (Wavelength Division Multiplexing) network data flow traverse multiple layers and, therefore, Class-Type information from the MPLS DiffServ layer is eventually lost. Besides, with the implement of a Path Computation Element (PCE) on multi-layer and multi-domain networks, the bandwidth constraints used to differentiate services are no longer applied. This paper presents a proposal for a QoS DiffServ approach applied on PCE as a traffic grooming technique for WDM core networks and the problematic involved on the application of this technology on multilayer and multi-domain networks.

The mobile cellular systems are expected to support multiple services with guaranteed Quality of Service(QoS). But, the ability of wireless systems to accommodate expected growth of traffic load and broadband services is limited by available radio frequency spectrum. Call Admission Control (CAC) is one of the resource management functions, which regulates network access to ensure QoS provisioning. However, the decision for CAC is very challenging issue due to user mobility, limited radio spectrum, and multimedia traffic characteristics. To deal with these problems, we implemented a Fuzzy Admission Control System (FACS). We compared the performance of FACS with Shadow Cluster Concept (SCC). In another work, we extended FACS by considering the priority of the on-going connections. We called this system FACS-P. As priority parameter, we considered only one parameter (service request). In this work, we improve our previous system by adding different priorities. We call this system FACS-MP. We evaluate and compare the performance of implemented systems by simulations. From the simulations results, we conclude that the FACS-MP can differentiate better different services compared with previous systems.

The mobile cellular systems are expected to support multiple services with guaranteed Quality of Service(QoS). But, the ability of wireless systems to accommodate expected growth of traffic load and broadband services is limited by available radio frequency spectrum. Call Admission Control (CAC) is one of the resource management functions, which regulates network access to ensure QoS provisioning. However, the decision for CAC is very challenging issue due to user mobility, limited radio spectrum, and multimedia traffic characteristics. In our previous work, we proposed a fuzzy-based CAC system by considering the priority of the on-going connections. As priority parameter, we considered only one parameter (service request). In this work, we extend our work by adding different priorities. We call this system FACS-MP. We evaluate by simulations the performance of the proposed system. From the simulations results, we conclude that the FACS-MP can differentiate better different services compared with previous system.

A Mobile Ad hoc Network (MANET) is a collection of wireless mobile terminals that are able to dynamically form a temporary network without any aid from fixed infrastructure or centralized administration. In recent years, MANETs are continuing to attract the attention for their potential use in several fields such as military activities, rescue operations and time-critical applications. In this paper, we present the implementation and analysis of our implemented wireless multi-hop network testbed considering the Optimized Link State Routing (OLSR) protocol for wireless multi-hop networking. We investigate the effect of mobility and topology changing in MANET. We study the impact of best-effort traffic for non line of sight communication. In this work, we consider three models: stationary, mobility and non line of sight communication models. We assess the performance of our testbed in terms of throughput and packet loss. From the experimental results, we found that OLSR has not a good performance when the relay node is moving. Also, the performance deteriorates when the CBR is higher.

A connection spanning, for example, several countries crosses multiple optical backbone networks, each one controlled by different administrators or operators. In this context, the interworking of these networks is thus necessary to set up end-to-end optical connections. A key issue when delivering such optical services is the use of efficient and fast restoration strategies to recover a connection disruption. To this end, there are several issues and policies that a network operator should address, such as interdomain failure information exchange and the point of repair (PoR) placement problem. Upon a failure’s occurrence, exchanging interdomain failure information results is essential to attain both an efficient use of the network resources (i.e., wavelength channels) and a fast restoration time. In this regard, within the GMPLS (Generalized Multi-Protocol Label Switching) framework, interdomain information exchange remains unstandardized. Three network operator policies are proposed to yield different restoration mechanisms according to different interdomain failure exchanges. Additionally, three PoR strategies are pointed out and are qualitatively compared. Finally, selected policies and restoration strategies are experimentally validated and compared in terms of the restoration time. Experiments have been carried out over a multidomain optical network infrastructure connecting the GMPLS-based control planes of the UPC CARISMA and the CTTC ADRENALINE test beds.

The architecture definition, design, and validation of the interconnect networks is a key step in the design of modern on-chip systems. This paper proposes a mathematical formulation of the problem of simultaneously defining the topology of the network and the message routes for the traffic among the processing elements of the system. The solution of the problem meets the physical and performance constraints defined by the designer. The method guarantees that the generated solution is deadlock free. It is also capable of automatically discovering topologies that have been previously used in industrial systems. The applicability of the method has been validated by solving realistic size interconnect networks modeling the typical multiprocessor systems.

This paper presents a Cross-layer Network Management System (NMS) that allows Service Providers (SPs) to perform cost-effective network resource reservations with their Network Operators (NOs). The novelty of our NMS is that it offers a fresh and promising approach to use the endusers satisfaction level as the metric to perform the resource management. We show that our system is capable of achieving considerable reductions in the operational costs of SPs, while keeping proper bounds in the end-user satisfaction for the offered multimedia services.

Wireless mobile networks and devices are becoming increasingly popular to provide users the access anytime and anywhere. We are witnessing now an unprecedented demand for wireless networks to support both data and real-time multimedia traffic. The wireless mobile systems are based on cellular approach and the area is covered by cells that overlap each other. In mobile cellular systems the handover is a very important process. Many handover algorithms are proposed in the literature. However, to make a better handover and keep the QoS in wireless networks is very difficult task. For this reason, new intelligent algorithms should be implemented to deal with this problem. In this paper, we carried out a comparison study of two handover systems based on fuzzy logic. We implement two Fuzzy-Based Handover Systems (FBHS) called FBHS1 and FBHS2. The performance evaluation via simulations shows that FBHS2 has better behavior than FBHS1 and can avoid ping-pong effect in all simulation cases.

Current service-level agreements (SLAs) offered by cloud providers make guarantees about quality attributes such as availability. However, although one of the most important quality attributes from the perspective of the users of a cloud-based Web application is its response time, current SLAs do not guarantee response time. Satisfying a maximum average response time guarantee for Web applications is difficult due to unpredictable traffic patterns, but in this paper we show how it can be accomplished through dynamic resource allocation in a virtual Web farm. We present the design and implementation of a working prototype built on a EUCALYPTUS-based heterogeneous compute cloud that actively monitors the response time of each virtual machine assigned to the farm and adaptively scales up the application to satisfy a SLA promising a specific average response time. We demonstrate the feasibility of the approach in an experimental evaluation with a testbed cloud and a synthetic workload. Adaptive resource management has the potential to increase the usability of Web applications while maximizing resource utilization.

Recently, performance evaluation of ad hoc network protocols is done using realistic mobility and traffic models, thus improving the validity and credibility of wireless simulation studies. In this paper we design and implement MixMobGen, a mobility generator for ad hoc vehicular applications, which takes into account mixed vehicular conditions. This is the first mobility model that takes into account, both, slow and fast vehicles. While speed for highway traffic has been modeled following a normal distribution, two studies on the mixed traffic show that speed follows a multimodal or bimodal distribution, instead. In this paper we a) design and implement MixMobGen, a realistic mobility generator that models mixed traffic conditions. b) evaluate protocol performance in 802.11 network protocols using NS 2 simulator.

Broadband satellite constellation networks will be required to carry all types of IP traffic, real time interactive traffic as well as non-real time traffic, warranting the need for appropriate QoS for these different traffic flows. In this paper we investigate the need for MPLS traffic engineering in GEO/MEO/LEO satellite networks to address QoS issues. We compare the service received by TCP and UDP flows when they share a link and when they are routed on explicit MPLS traffic trunks. Since MPLS traffic trunks allow non-shortest path links also to be used, the total network throughput goes up with proper traffic engineering. If UDP and TCP flows are mixed in a trunk, TCP flows receive reduced service as the UDP flows increase their rates. Also, we found that with MPLS traffic engineering we can protect real time traffic and VoIP traffic from packet loss and excessive jitter by separating them from other congestion unresponsive flows

The mobile cellular systems are expected to support multiple services with guaranteed quality of service (QoS). However, the ability of wireless systems to accommodate expected growth of traffic load and broadband services is limited by available radio frequency spectrum. Call admission control (CAC) is one of the resource management functions, which regulates network access to ensure QoS provisioning. However, the decision for CAC is very challenging issue due to user mobility, limited radio spectrum, and multimedia traffic characteristics. To deal with these problems, in this paper, we propose a fuzzy CAC system. We compare the performance of the proposed system with shadow cluster concept (SCC). We evaluate by simulation the performance of the proposed system. The proposed system has a good behavior on deciding the number of accepted connections while keeping the QoS for serving connections.

In order to support multimedia communication, it is necessary to develop routing algorithms which use for routing more than one QoS parameters. This is because new services such as video on demand and remote meeting systems require better QoS. Also, for admission control of multimedia applications different QoS parameters should be considered. In our previous work, we proposed an intelligent routing and CAC strategy using cooperative agents. In this paper, we propose and evaluate the performance of SSRA algorithm and a GA-based InterD agent. Performace evaluation shows that proposed agents have a good behavior