Search

Autonomous network management is crucial for Fifth Generation (5G) and Beyond 5G (B5G) networks, where a constantly changing environment is expected and network configuration must adapt accordingly. Modeling tools are required to predict the impact on performance (packet and delay loss) when new traffic demands arrives and when changes in routing paths are applied in the network. Mathematical analysis and network simulators are techniques for modeling networks but both have limitations, as the former provides low accuracy and the latter requires high execution times. To overcome these limitations, Machine Learning (ML) algorithms, and more specifically, Graph Neural Networks (GNNs), are proposed for network modeling due to their ability to capture complex relationships from graph-like data while predicting network properties with high accuracy and low computational requirements. However, one of the main issues when using GNNs is their lack of generalization capability to larger networks, i.e., when trained in small networks (in number of nodes, paths length, links capacity), the accuracy of predictions on larger networks is poor. This paper addresses the GNN generalization problem by the use of fundamental networking concepts. Our solution is built from a baseline GNN model called RouteNet (developed by Barcelona Neural Networking Center - Universitat Polit`ecnica de Catalunya (BNN-UPC)) that predicts the average delay in network paths, and through a number of simple additions significantly improves the prediction accuracy in larger networks. The improvement ratio compared to the baseline model is 101, from a 187.28% to a 1.828%, measured by the Mean Average Percentage Error (MAPE). In addition, we propose a closed-loop control context where the resulting GNN model could be potentially used in different use cases.&nbsp

Data center networks (DCNs) connect hundreds and thousands of computers and, as a result of the exponential growth in their number of nodes, the design of scalable (compact) routing schemes plays a pivotal role in the optimal operation of the DCN. Traditional trends in the design of DCN architectures have led to solutions, where routing schemes and network topologies are interdependent, i.e., specialized routing schemes. Unlike these, we propose a routing scheme that is compact and generic, i.e., independent of the DCN topology, the word-metric-based greedy routing. In this scheme, each node is assigned to a coordinate (or label) in the word-metric space (WMS) of an algebraic group and then nodes forward packets to the closest neighbor to the destination in this WMS. We evaluate our scheme and compare it with other routing schemes in several topologies. We prove that the memory space requirements in nodes and the forwarding decision time grow sub-linearly (with respect to n, the number of nodes) in all of these topologies. The scheme finds the shortest paths in topologies based on Cayley graphs and trees (e.g. Fat tree), while in the rest of topologies, the length of any path is stretched by a factor that grows logarithmically (with respect to n). Moreover, the simulation results show that many of the paths remain far below this upper bound This work was supported in part by the Mexican Government under Grant CONACYT-SENER 2015-409697, in part by the Spanish Government under Grant TEC 2015-66412-R and Grant TEC 2015-71932-REDT, in part by the Catalan Government under Grant SGR-1469, and in part by the Flanders Government through the SMILE-IT Project—VLAIO

We study the problem of path computation in Cayley Graphs (CG) from an approach of word processing in groups. This approach consists in encoding the topological structure of CG in an automaton called Diff , then techniques of word processing are applied for computing the shortest paths. We present algorithms for computing the K -shortest paths, the shortest disjoint paths and the shortest path avoiding a set of nodes and edges. For any CG with diameter D , the time complexity of the proposed algorithms is O ( K D | Diff | ) , where | Diff | denotes the size of Diff . We show that our proposal outperforms the state of art of topology-agnostic algorithms for disjoint shortest paths and stays competitive with respect to proposals for specific families of CG. Therefore, the proposed algorithms set a base in the design of adaptive and low-complexity routing schemes for networks whose interconnections are defined by CG.

Some topology properties that determine the performance and robustness of parallel computer systems include fault-tolerance, latency, load-balancing and support for a high number of end points. This paper analyses the impact of graph symmetry on these properties. Through a comparison between Cayley Graphs (CGs) and classical topologies for parallel computer systems, we show that many families of CGs provide optimal values for the mentioned properties.

International audience; A wide range of social, technological and communication systems can be described as complex networks. Scale-free networks are one of the well-known classes of complex networks in which nodes degree follow a power-law distribution. The design of scalable, adaptive and resilient routing schemes in such networks is very challenging. In this article we present an overview of required routing functionality, categorize the potential design dimensions of routing protocols among existing routing schemes and analyze experimental results and analytical studies performed so far to identify the main trends/trade-offs and draw main conclusions. Besides traditional schemes such as hierarchical/shortest-path path-vector routing, the article pays attention to advances in compact routing and geometric routing since they are known to significantly improve the scalability in terms of memory space. The identified trade-offs and the outcomes of this overview enable more careful conclusions regarding the (in-)suitability of different routing schemes to large-scale complex networks and provide a guideline for future routing research.

We propose a network scheme with Admission Control AC for TCP flows, which can provide different minimum throughputs and isolation between flows. It is built with simple mechanisms without per-flow state, per flow signaling or per-flow processing in the core. The whole scheme uses a small set of packet classes, with a different discarding priority assigned to each one. The AC is implicit, edge-to-edge and based on per-aggregate throughput measurements. The out packets of the aggregation of accepted flows i.e., the packets that correspond to the flows' extra throughput act as a probing flow to test if the throughput in the network path is enough to satisfy the flow's request. Then signaling packets carry the per-aggregate throughput measurement from the egress to the ingress, where the AC decision is made. Through simulation we show that the scheme guarantees the requested minimum throughput to accepted flows and achieves a good utilization of resources.

TCP flows generated by applications such as the Web or FTP require a minimum network throughput and can also benefit from an extra throughput due to their rate-adaptive algorithms. To build a guaranteed minimum throughput service, the authors propose a scheme with Admission Control (AC) using a small set of packet classes in a core-stateless network. At the ingress of the network, each flow packet is marked as one of the set of classes, and within the network, each class is assigned a different discarding priority. The AC method is based on edge-to-edge per flow measurements and requires flows to be sent at a minimum rate. The scheme is able to provide different minimum throughput to different users and protection against nonresponsive sources. The authors evaluate the scheme through simulation using different traffic loads consisting of TCP flows that carry files of varying sizes. In the simulation, TCP uses a new algorithm that forces the source to keep the short-term sending rate above a desired minimum rate. The authors study the influence of several parameters on the performance of the scheme in different network topologies. The results show that the scheme guarantees the requested throughput to accepted flows and achieves a high utilization of network resources, similar to the ideal results of a classical hop-by-hop AC.

We propose a new scheme for a network service that guarantees a minimum throughput to flows accepted by admission control (AC). The whole scheme only uses a small set of packet classes in a core-stateless network. At the ingress of the network each flow packet is marked into one of the sets of classes, and within the network, each class is assigned a different discarding priority. The AC method is based on edge-to-edge per-flow throughput measurements using the first packets of the flow, and it requires flows to send with a minimum rate. We evaluate the scheme through simulations in a simple bottleneck topology with different traffic loads consisting of TCP flows that carry files of varying sizes. We use a modified TCP source with a new algorithm that forces the source to send with a minimum rate. We compare our scheme with the best-effort service and we study the influence of the measurement duration on the scheme's performance. The results prove that the scheme guarantees the requested throughput to accepted flows and achieves a high utilization of network resources. Copyright © 2006 John Wiley & Sons, Ltd.

In this paper, a network laboratory for distance learning of basic concepts in IP networking is presented. Through a web interface, students can choose various configurations of a real private network (number of routers and subnetworks, use of IPv4/IPv6, etc.), and learn about them using Linux network commands. The utilization of the virtual laboratory and how it is implemented are described.

Nowadays data centers are becoming huge facilities with hundreds of thousands of nodes, connected through a network. The design of such interconnection networks involves finding graph models that have good topological properties and that allow the use of efficient routing algorithms. Cayley Graphs, a kind of graphs that represents an algebraic group, meet these properties and therefore have been proposed as a model for these networks. In this paper we present a routing algorithm based on Shortlex Automatic Structure, which can be used on any interconnection network with an underlying Cayley Graph (of some finite group). We show that our proposal computes the shortest path between any two vertices with low time and space complexity in comparison with traditional routing algorithms.

Aiming at creating a dynamic between elaboration, realization, and validation by means of iterative cycles of experimentation, Future Internet Research and Experimentation (FIRE) projects have been rapidly confronted to the lack of systematic experimental research methodology. Moreover, the “validation by experimentation” objective involves a broad spectrum of experimentation tools ranging from simulation to field trial prototypes together with their associated measurement tools. As experimental measurement results and corresponding tools play a fundamental role in experimental research, devising a systematic experimentation and measurement methodology becomes thus crucial for experimental research projects to achieve this objective for their various realizations, including protocols, systems and components. In turn, and in order to meet scientific validity criteria, the measurement results obtained when performing experimental research implies the availability of reliable and verifiable measurement tools, including on-line measurement data analysis and mining.

Admission Control (AC) is an efficient way of dealing with congestion situations in a network. Using AC, when network resources in a path are not enough for all flows (i.e., during congestion), some of the flows receive the requested service and the rest do not. Congestion situations can be reduced by increasing network resources or by optimizing their use through better routing techniques, but if congestion still occurs, AC achieves efficient use of network resources by maximizing the number of satisfied flows. However, using AC complicates the network scheme, and therefore a major concern is making the AC as simple as possible. In this paper we review the main AC schemes that have been proposed for the Internet, focusing on the simplicity of their architectures in terms of the number of nodes that participate in the AC, the required state, the use of signaling, and others.

Following the iterative research cycle process, this chapter elaborates a methodology and documents the steps followed for the design of a dynamic multicast routing algorithm, referred to as Greedy Compact Multicast Routing. Starting from the design of the dynamic multicast routing algorithm, we then evaluate by simulation on large-scale topologies its performance and compare them with the Abraham compact multicast routing scheme and two other reference schemes, namely the Shortest Path Tree (SPT) and the Steiner Tree (ST) algorithm. Performance evaluation and comparison include i) the stretch of the multicast routing paths also referred to as multicast distribution tree (MDT), ii) the memory space required to store the resulting routing table entries, and iii) the total communication or messaging cost, i.e., the number of messages exchanged to build the MDT. However, such performance evaluation is a necessary but not a sufficient condition to meet in order to expect deployment of multicast routing. Indeed, if one can determine that traffic exchanges are spatially and temporally concentrated, this would provide elements indicating the relevance for the introduction of such scheme in the Internet. Otherwise (if traffic exchanges are spatially and temporally diverse, i.e., highly distributed), then very few of them would benefit from a (shared) point-to-multipoint routing paths and multicast routing scheme would be less useful. For this purpose, we have conducted a multicast tree inference study. In turn, data and results obtained from these studies provides more realistic scenarios for emulation experiments against the currently deployed approach combining MBGP and PIMdeployed in IPTV or mVPN context.

In this paper, we report the results of the workshop organized by the FP7 EULER project on measurement-based research and associated methodology, experiments and tools. This workshop aimed at gathering all Future Internet Research and Experimentation (FIRE) experimental research projects under this thematic. Participants were invited to present the usage of measurement techniques in their experiments, their developments on measurement tools, and their foreseeable needs with respect to new domains of research not currently addressed by existing measurement techniques and tools.

In this paper a novel methodology aimed at minimizing the probability of network failure and the failure impact (in terms of QoS degradation) while optimizing the resource consumption is introduced. A detailed study of MPLS recovery techniques and their GMPLS extensions are also presented. In this scenario, some features for reducing the failure impact and offering minimum failure probabilities at the same time are also analyzed. Novel two-step routing algorithms using this methodology are proposed. Results show that these methods offer high protection levels with optimal resource consumption.

TCP flows from applications such as the web or ftp are well supported by a Guaranteed Minimum Throughput Service (GMTS), which provides a minimum network throughput to the flow and, if possible, an extra throughput. We propose a scheme for a GMTS using Admission Control (AC) that is able to provide different minimum throughput to different users and that is suitable for "standard" TCP flows. Moreover, we consider a multidomain scenario where the scheme is used in one of the domains, and we propose some mechanisms for the interconnection with neighbor domains. The whole scheme uses a small set of packet classes in a core-stateless network where each class has a different discarding priority in queues assigned to it. The AC method involves only edge nodes and uses a special probing packet flow (marked as the highest discarding priority class) that is sent continuously from ingress to egress through a path. The available throughput in the path is obtained at the egress using measurements of flow aggregates, and then it is sent back to the ingress. At the ingress each flow is detected using an implicit way and then it is admission controlled. If it is accepted, it receives the GMTS and its packets are marked as the lowest discarding priority classes; otherwise, it receives a best-effort service. The scheme is evaluated through simulation in a simple "bottleneck" topology using different traffic loads consisting of "standard" TCP flows that carry files of varying sizes.

We present a system for dynamic network resource configuration in environments with bandwidth reservation. The proposed system is completely distributed and automates the mechanisms for adapting the logical network to the offered load. The system is able to manage dynamically a logical network such as a virtual path network in ATM or a label switched path network in MPLS or GMPLS. The system design and implementation is based on a multi-agent system (MAS) which make the decisions of when and how to change a logical path. Despite the lack of a centralised global network view, results show that MAS manages the network resources effectively, reducing the connection blocking probability and, therefore, achieving better utilisation of network resources. We also include details of its architecture and implementation.

TCP elastic traffic is generated by the traditional “data” applications in the Internet, such as web browsing, peer-to-peer file sharing, ftp, e-mail and other. These applications are built on top of TCP, which provides reliable transfers and adjusts the sending rate to the network conditions to achieve the maximum possible throughput, a feature that makes TCP flows to be called “elastic”. From the point of view of the network, TCP elastic traffic requires the maximum possible throughput above a minimum value, a network service that we call the Minimum Throughput Service (MTS). In this paper we survey the main network schemes that have been proposed in the Internet to provide this service for TCP elastic traffic, classified in two broad groups, the ones that do not use Admission Control (AC) and the ones that do use it. For each network scheme we describe the main characteristics of the service (whether the minimum throughput can be different or is the same for all flows, whether isolation among flows is provided, etc.) and their architecture (the specific traffic conditioning, queue disciplines and AC mechanisms used, the required state, the use of signaling, etc.).

Due to the high cost of a large ATM network working up to full strength to apply our ideas about network management, i.e., dynamic virtual path (VP) management and fault restoration, we developed a distributed simulation platform for performing our experiments. This platform also had to be capable of other sorts of tests, such as connection admission control (CAC) algorithms, routing algorithms, and accounting and charging methods. The platform was posed as a very simple, event-oriented and scalable simulation. The main goal was the simulation of a working ATM backbone network with a potentially large number of nodes (hundreds). As research into control algorithms and low-level, or rather cell-level methods, was beyond the scope of this study, the simulation took place at a connection level, i.e., there was no real traffic of cells. The simulated network behaved like a real network accepting and rejecting SNMP ones, or experimental tools using the API node.

This paper proposes a traffic engineering scheme using different distribution trees to several multicast flows. We formulate this problem as one with Non Linear programming with discontinuous derivatives (DNLP). The aim is to combine into a single aggregated metric the following weighting objectives: the maximum link utilization, the hop count, the total bandwidth consumption and the total end-to-end delay. Our proposal solves the traffic split ratio for multiple trees. The proposed approach is applied in MPLS networks by allowing the establishment of explicit routes in multicast events. Furthermore, the results obtained with GAMS tools show that several objectives are decreased; the maximum link utilization is minimized. The main contribution of this paper is the optimization model and the formulation of the multi-objective function.

Internet applications such as web or ftp will be satisfactorily supported by a guaranteed minimum throughput service. We propose to build this service in a core-stateless network such as Differentiated Services with an Admission Control (AC) method based on end-to-end measurements, using the first packets of the flow. The whole scheme uses a small set of packet classes (with different discarding priorities), and is therefore simple and scalable. We evaluate the scheme through simulations in several scenarios using TCP flows. Finally, we propose an extension of the method aimed at improving its performance.