In band Network Telemetry (INT) is a technique aiming at collecting telemetry information by inserting it inside the data packets, instead of relying on classical centralized monitoring elements that periodically query the network devices. The main drawback of INT is represented by the introduced per-packet overhead, that could negatively affect some traffic flows, especially those having stringent QoS requirements. To deal with the increase in the packet length caused by INT, in this paper we introduce the Sampling and Recovering paradigm to overcome the classical Collect Everything approach where all the INT data must be gathered. The proposed approach hinges on signal processing strategies to sample and recover sparse flow signals. The key idea is to reduce the number of INT data to collect and exploit signal reconstruction algorithms to obtain the unseen samples. The preliminary performance evaluation shows that the 18% of INT data are enough to get an accurate reconstruction of the overall network situation, while allowing for 90% of overhead reduction with respect to the Collect Everything case.

Nowadays, inter domain routing optimization is performed based on the so called “Tweak and Pray” approach, which consists in performing changes in the configuration of the BGP protocol without knowing in advance the consequences of such a modification. This is due to the lack of cooperation among Network Operators in the configuration of the BGP to optimize the inter domain routing. Inefficiency in the resource usage, network anomalies and outages are common consequences of wrong configuration changes performed by Network Operators in an attempt to improve the performance of their infrastructures. In this paper we propose a novel framework based on the Digital Twin technology to enable the execution of “what-if” analysis in the context of Traffic Engineering performed by tuning BGP parameters. Such a paradigm shift will allow Network Operator to be aware of the effects of BGP configuration changes before their actual execution. A proof of concept related to the balancing of inbound traffic in an Autonomous System network, based on the use of the AS Path Prepending technique, is realized to validate the feasibility of the proposed approach.

Network Black Holes (BHs) are logical failures that create a service disruption for a subset of traffic flows, generally due to device misconfiguration. Detection of a BH is a hard task due to its specific nature: the infrastructure is up and the disconnection affects a limited number of flows. An example of BH is the one caused by the failure of the Path MTU Discovery procedure in IPv6. The Segment Routing (SR) Architecture is an overlay infrastructure that provides source routing support by exploiting the connectivity service offered by the underlay IPv6 (SRv6). Thus, SR inherits the problems related to BHs affecting IPv6. In SR this problem is even more stressed due to the encapsulation mechanism that is required to enforce the segment lists on packets. Even worse, existing active probing based tools to detect network BHs for IPv6 are not suitable in SR. In this paper we investigate the problem of detecting SR Black Holes in SR domains. As first, we provide an experimental demonstration of the creation of an SR Black Holes. Then we show that existing tools based on active probing are not suitable to detect SR BHs. Then, a passive framework named Segment Routing Black Holes Detection (SR-BHD) is introduced. SR-BHD makes use of specific traffic counters available in SR capable nodes to verify the validity of the flow conservation principle on each network element. Experimental evaluation carried out through simulation and emulation shows the effectiveness of SR-BHD in detecting the presence of SR BHs.

In this paper we introduce QLR, a per-router control agent that aims at reducing the occupancy of the local buffers by performing re-routing operations. The Segment Routing architecture is exploited to manage the uncoordinated selection of re-routing performed by different nodes, thus avoiding the creation of routing loops, while the Extensible In-band Processing is used to allow the network nodes to have a detailed and updated view of the wide network status. Data and control plane programmability are considered to define a prototype implementation of QLR that allows for the execution of a preliminary performance evaluation and proof-of-concept. From the conducted experiments has emerged that QLR can effectively reduce the maximum queue occupancy and end-to-end delay up to 43% and 63%, respectively.

The increasing number of mobile devices and the enhanced user experience they require have a strong impact on mobile network development, since they result in an increased channel capacity demand to be obtained with a limited site densification. An interesting approach to face this challenge can be found in the combination of two technology enabling solutions: Cloud or Centralized RAN (C-RAN) and Advanced Antenna Systems (AAS). In this paper, we discuss the advantages given by these solutions, with a special focus on how Artificial Intelligence (AI)-based algorithms can improve their combination in terms of functional split and antenna mapping, stated as an optimization problem. In particular, AI can be beneficial in three main areas, such as the actual solution of the optimization problem, the tuning of parameters used in classical heuristic algorithms aiming at solving the optimization problem, and, finally, the traffic and resource allocation prediction at the base of proactive reconfiguration frameworks.

The Network Programming model of SRv6 allows the creation of network programs that can be enforced over traffic flows entering a Segment Routing (SR) domain. A network program is a list of instructions that must be applied on a packet traversing the SR domain. Instructions, also known as behaviors, currently available in SRv6 are divided into two main categories: i) topological (e.g., send the packet over the shortest path), and ii) service based (e.g., duplicate the packet). In this paper we introduce a new behavior for the SRv6 Network Programming model, named maximize Throughput (max_T). This function allows to steer an incoming traffic flow toward the egress node over the path that currently guarantees the highest throughput for the flow. The proposed max_T behavior has been implemented over programmable switches, and its effectiveness in improving the performance experienced by flows asking for its application is evaluated through experiments performed over an emulated environment. The preliminary result shows that a 23% reduction of the transfer time for a file over the SR domain is achieved when the max_T behavior is used.

In this work, we provide a Machine Learning framework for augmenting the Differentiated Services (DiffServ) protocol with fine-grained dynamic traffic classification. The framework is called L-DiffServ. It is composed of two classification algorithms able to detect the QoS classes of incoming packets only looking at three packet header fields; the first algorithm, referred to as Inter-L-DiffServ, is a semi-supervised classification procedure able to replicate DiffServ classification; the second one, referred to as Intra-L-DiffServ, is an unsupervised algorithm for intra-class classification, useful for classes taking large portions of the overall traffic. We apply the latter to the low priority best-effort class. The performance evaluation shows that our solution is able to dynamically classify packets and to detect new QoS sub-classes hence adapting to traffic aggregate characteristics. We also show that network resource management can be improved exploiting the new generated QoS sub-classes: two active queue management algorithms based on WRED and CHOKe show a reduction of the number of sessions affected by packet losses up to 40% with respect to the legacy DiffServ procedure.

Self-driving networks represent the next step of network management techniques in the close future. A fundamental point for such an evolution is the use of Machine Learning based solutions to extract information from data coming from network devices during their activity. In this work we focus on a new type of data, available thanks to the definition of the novel SRv6 paradigm, referred to as SRv6 Traffic Counters (SRTCs). SRTCs provide aggregated measurements related to forwarding operations performed by SRv6 routers. In this work a detailed description of different SRTCs types (SR.INT, PISD, PSID.TM and POL) is provided and their relationships is formalized. The theoretical framework deployed is used to identify, on the basis of network configuration parameters of both SRv6 and IGP protocols, the minimum set of independent SRTCs to characterize the Network Status: we show that about the 80% of counters can be neglected with no information loss. We also apply our framework to two use cases: i) Traffic Matrix (TM) Assessment and ii) Traffic Anomaly Detection. For the TM assessment, we show that in a partially deployed SRv6 scenario a specific type of SRTCs, i.e., PSID, is more reliable than other ones; on the contrary, in a fully deployed scenario POL and PSID.TM counters provide the full TM knowledge. For the Traffic Anomaly Detection case, we show that known solutions based on link load measurements can be improved when integrating SRTCs information.

In this work we define a framework for the assessment of the Traffic Matrix (TM) of an Internet Service Provider (ISP) network. The solution, referred to as mrT, i) is completely distributed among network nodes, ii) is based on different Map-Reduce building blocks, iii) and is able to extract the Ingress-Egress nodes traffic relationships starting from raw traces captured on node interfaces. Each network node is able to compute a row of the TM having as input the local trace and low size files sent by other network nodes. mrT can be used for the TM computation of any packet switched network where the source and destination identifiers are unique and global, and computational resources are available in proximity of network nodes. The performance evaluation, carried out with synthetic and real traffic traces, highlight that mrT is a suitable solution for the assessment of the TM in real ISP networks with high traffic volumes. Moreover, the use of the Map-Reduce paradigm allows a reduction of more than the 50% of the execution times, with respect to an SQL-based approach.

Traffic matrix (TM) assessment is a key issue for optimizing network management costs and quality of service. This paper presents a method to measure the intensity of ingress-egress traffic flows on an Internet service providers network that overcomes the limits of the classical measurement-based approaches. The proposed algorithm, called segment routing perturbation traffic (SERPENT), uses a routing perturbation approach enabled by the segment routing paradigm: The paths of a subset of flows are changed so that their intensities can be determined measuring the variation of the load of the network links. The TM is measured in successive steps, called snapshots, in which sets of flows are progressively re-routed and measured, under a maximum link utilization constraint. We state an integer linear programming (ILP) optimization problem to determine the flows to be rerouted in one snapshot. SERPENT is an heuristic offering an efficient solution to the stated ILP. Results show that SERPENT assesses the intensity of more than 80% of flows even when the network is highly stressed, while reducing the configuration cost with respect to classical approaches. Moreover, when used in conjunction with an estimation algorithm, SERPENT allows a reduction of the estimation error by more than 50% with fewer than 5 snapshots.

We consider the problem of controlling the rate of failures triggered by fatigue processes of Base Stations (BSs) in cellular networks subject to Sleep Modes (SMs). Specifically, the increase of time spent in SM tends to decrease the BS failure rate by following, e.g., the Arrhenius law. However, the transitions between the power states tend to increase the BS failure rate, which can be predicted by the Coffin-Manson model. In this context, the energy savings triggered by SMs would not be economically useful if the BS failure rate were increased too much. Our goal is therefore to tackle the problem of minimizing the BS failure rate in a cellular network subject to SMs. After showing that the optimal formulation of the problem is NP-Hard, we propose a new algorithm, named LIFE, to practically solve it. We run LIFE on different scenarios (driven by LTE and legacy UMTS technologies). Our results show that LIFE outperforms two previous energy-aware algorithms, which instead do not take into account the BS failure rate. Specifically, our solution is able to achieve up to 40 percent of power saving at night, without a strong penalty in the BS failure rate.

We propose a framework to manage the link lifetime in an IP backbone network by exploiting the sleep mode (SM). In particular, when an SM feature is available, two different effects coexist: during the SM state, the lifetime tends to be increased and however, when the link changes its power state (from SM to full power or vice-versa), the lifetime tends to be decreased. We, therefore, define an optimal formulation of the lifetime-aware network problem. Moreover, we propose a heuristic, called Acceleration Factor Algorithm, to practically manage the device lifetime. We solve the problem both optimally and with our heuristic, considering two representative case studies. Results show that our approach outperforms the previous energy-aware algorithms, which instead do not consider the lifetime decrease triggered by the power state change. Thus, we argue that a lifetime-aware network management should be pursued when deciding to set an SM state for each device in an Internet Service Provider network.

Segment routing (SR) is a new routing paradigm to provide traffic engineering (TE) capabilities in an IP network. The main feature of SR is that no signaling protocols are needed, since extensions of the interior gateway protocol routing protocols are used. Despite the benefit that SR brings, introducing a new technology into an operational network presents many difficulties. In particular, the network operators consider both capital expenditure and performance degradation as drawbacks for the deployment of the new technology; for this reason, an incremental approach is preferred. In this paper, we face the challenge of managing the transition between a pure IP network to a full SR one while optimizing the network performances. We focus our attention on a network scenario where: 1) only a subset of nodes are SR-capable and 2) the TE objective is the minimization of the maximum link utilization. For such a scenario, we propose an architectural solution, named SR domain (SRD), to guarantee the proper interworking between the IP routers and the SR nodes. We propose a mixed integer linear programming formulation to solve the SRD design problem, consisting in identifying the subset of SR nodes; moreover, a strategy to manage the routing inside the SRD is defined. The performance evaluation shows that the hybrid IP/SR network based on SRD offers TE opportunities comparable to the one of a full SR network. Finally, a heuristic method to identify nodes to be inserted in the set of nodes composing the SRD is discussed.

In this work, we show that there are two effects impacting cellular networks owned by an operator as a consequence of the application of the green networking via Sleep Modes (SMs) state to Base Stations (BSs). On one side, it is possible to save money from the electricity bill by exploiting SMs. On the other hand, however, the SM state triggers a variation in the failure rate of the BS, and therefore in the replacement/reparation costs to fix it. We therefore derive a simple model to compute the total savings vs. costs for an operator network. Our results, obtained over 3G and 4G scenarios, show that there is a trade-off between the saving and the related costs. Moreover, we show that the costs incurred by the operator depend on different factors, including: i) the energy-aware strategy, ii) the specific technology adopted, and iii) the components used to build the BS.

Traffic matrix estimation in communication network is a long standing problem for its intrinsic difficulty and potential benefit to a vast number of network optimization and management functions. We address the improvement of the traffic matrix estimation by means of selected traffic flow measurements, besides the easily obtained link load measurements. The key contribution of this paper is the definition and assessment of an effective criterion, based on the flow spread parameter, to identify the flows to be measured that reduce the estimation error most. It turns out that a small percentage of flows are enough to drive the estimation error an order of magnitude lower than the one obtained with the classical solution solely based on link load measurements. Our algorithm, referred to as flow spread-based algorithm (FSBA), is also able to distribute measurement tasks fairly among network nodes, taking into account the available forwarding tables space. We also show that FSBA outperforms the state-of-the-art similar approaches. A detailed discussion on how the observation of the desired flows can be performed is done as well, by addressing the SDN paradigm. This is in fact a rapidly growing concept that enables individual flow measurements, though for only a limited number of flows to be practical with current technology.

We target the problem of managing the Base Stations (BSs) lifetime and their energy efficiency when a sleep mode (SM) is adopted. We first show that the BS lifetime is affected by two opposite effects: the duration of SM, which tends to increase the lifetime, and the SM frequency, which on the contrary decreases the lifetime. After optimally formulating the problem for a cellular network, we propose a new heuristic, called LIFE, to practically solve it. Our solution integrates the BS lifetime when SM decisions are considered. Results, obtained over an UMTS scenario and a LTE one, prove that LIFE outperforms two previous energy-efficient algorithms in terms of lifetime performance, since all the previous solutions tend to drastically reduce the BS lifetime. Moreover, we show that LIFE is able to save up to 40% of power during night in the long-term.

In this work we study the impact of energy-aware routing algorithms on IP backbone networks, focusing on the routing protocol transients due to network reconfiguration. We first propose the Green Partial Exportation (GPE) algorithm, which is fully compatible with the OSPF protocol and targets the reduction of the number of changed paths in the network; we also realize a green software router by integrating GPE in the Quagga routing suite. Then we define an experimental methodology to evaluate the effects of a green routing strategy on the network behavior, in terms of delay increase and packet loss. Finally, we evaluate our solution on an emulated testbed from a national telecom operator. Our results show a maximum increment of 320 ms for the RTT and a packet loss of 1.45% during the network transients. Moreover, GPE can be safely applied in the network with a time granularity of less than one minute.

We consider the effect of power state transitions on the lifetime of Base Stations (BSs) in a cellular network. In particular, we take into account the impact of putting in sleep mode the BS, and also the change of the radiated power. When the BS reduces its power consumption, its lifetime tends to increase, as a consequence of the temperature reduction. However, the change in the power state triggers a negative effect which instead tends to reduce the BS lifetime. We therefore propose a model to evaluate the BS lifetime considering the two aforementioned effects, triggered either by the application of a sleep mode state or a change in the radiated power. Our results, obtained over a representative case study, indicate that the BS lifetime may be negatively affected when power state transitions take place. Therefore, we argue that the lifetime should be considered in the process of deciding how and when to change from a power state to another one.

This paper proposes a novel energy-aware adaptive routing solution to face the energy consumption problem in IP networks, exploiting the IP over IP tunneling technique. The problem of minimizing the number of used links by configuring a set of tunnels, referred to as energy minimized tunneling (EMT), is modeled as an integer linear programming problem. The general EMT problem is then slightly modified by adding a set of constraints to make it more applicable to real networks scenario. With respect to previously proposed solutions, the EMT formulation exploits IP tunneling to change traffic routing assuring three main features: 1) no modifications to both data and control planes of current IP routers, so representing a feasible short-term solution for actual IP networks; 2) no need of IP routing protocols convergence to modify the routing paths, so avoiding routing instabilities; and 3) performance comparable with flow-based solutions requiring the deployment of a connection-oriented protocol. We propose a practical solution, called Virtual Interface oN Off (VINO), that exploits the tunnel aggregation mechanism in order to reduce EMT operational complexity. VINO works in two steps and it is based on the preconfiguration of a limited set of (virtual) tunnel interfaces along with a set of static routes on IP routers; thus, these virtual interfaces are dynamically activated and deactivated according to traffic variations. The performance analysis carried out demonstrates that VINO is able to outperform IP green routing solutions proposed in the literature, in terms of energy efficiency.

Energy efficiency in telecommunication networks has been recognized as a very important topic during the last few years. This is motivated by the fact that reduction of power consumption translates into reduction of carbon footprint and operating costs. The IEEE standardization body also included energy consumption aspects into its activities and developed a standard on Energy Efficient Ethernet (IEEE P802.3az). Its objective was to define a mechanism to reduce power consumption of the Physical layer when links are underutilized. It therefore defined a protocol to coordinate transitions to and from a lower power consumption mode without changing the link status and dropping frames. Time required by such transitions is however comparable with packet transmission time; that makes power consumption reduction of the method strongly dependent on packet inter-arrival time and limits its application to cases of low link utilization, such as home/office environments and access networks. A new solution for extending the application of the EEE mechanism in Ethernet networks with different traffic load conditions and QoS requirements, where data flows are statically provisioned and opportunely conditioned at the edge, is proposed. It allows shaping traffic across the network so as to reduce O0/OFF transitions at EEE aware switch interfaces while ensuring end to end delay constraints to packets traversing multiple links. It off-line determines on the basis of the Parekh Gallager theorem if the activation of a dummy flow, associated to the OFF periods, can provide power consumption reduction without impacting data flows delay requirements. On ports where the dummy flow is activated, the scheduler mechanism triggers the OFF period each time a dummy packet is served. A performance analysis of the EEE mechanism enhanced with the proposed QoS aware sleep mode controller has been carried out in order to quantify the improvements in terms of energy efficiency with respect to the standard EEE operation and to assess its effectiveness in terms of Quality of Service (QoS).

This paper deals with an energy saving routing solution, called Energy Saving IP Routing (ESIR), to be applied in an IP network. ESIR operation is integrated with Open Shorthest Path First (OSPF) protocol and allows the selection of the links to be switched off so that the negative effects of the IP topology reconfiguration procedures are avoided. The basic mechanisms which ESIR is based on are the concepts of SPT exportation and move. These mechanisms allow to share a Shortest Path Tree (SPT) between neighbor routers, so that the overall set of active network links can be reduced. Properties of moves are defined and the energy saving problem in an IP network is formulated as the problem of finding the Maximum Set of Compatible Moves (MSCM). The MSCM problem is investigated in two steps: firstly, a relaxed version of the problem, named basic MSCM problem, is considered in which QoS requirements are neglected; in the second step, the solution of the full problem, named QoS-aware MSCM problem, is faced. We prove that the basic MSCM problem can be formulated as the well-known Maximum Clique Problem in a graph; instead the QoS-aware MSCM introduces a condition equivalent to the Knapsack problem. ILP formulations to solve both the problems are given and heuristics to solve them in practical cases are proposed. The performance evaluation shows that in a real ISP network scenario ESIR is able to switch off up to 30% of network links by exploiting over-provisioning adopted by operators in the network resource planning phase and typical daily traffic trend.

This paper proposes a novel power-aware routing and wavelength assignment (PA-RWA) algorithm to be applied to a transparent wavelength division multiplexing (WDM) optical network. The proposed algorithm aims at improving the energy efficiency of the optical network by leaving unused optical fibres as much as possible in order to minimize the number of optical amplifiers kept active in the network. A dynamic lightpath establishment scenario is considered and results are compared with other routing algorithms showing that the proposed algorithm can drastically reduce the power consumption for any value of traffic load.

This work proposes a distributed and adaptive mechanism for saving energy in IP/MPLS over WDM networks by switching off router line cards according to the traffic variability in the network. The proposed mechanism optimizes the traffic routing and adapts the IP topology to the traffic that is actually carried in the network. This is done by re- computing the path of each traffic flow several times during a day when their requested capacity changes. The routing is performed by using a specific cost function, named V-Like, to compute link weights into the shortest path routing algorithm. The proposed solution is compared with a static energy-aware heuristic algorithm proposed in the literature; results show that it is possible to save from 35% up to 50% of energy with respect to the static case, depending on the traffic load.

An optical packet switch that shares both limited range and full range wavelength converters for contention resolution is proposed with the aim to guarantee an high conversion cost saving. To optimally dimension the number and the conversion range of the wavelength converters, an analytical model, validated by simulation, is introduced to evaluate the packet loss probability of the switch. Numerical results show that the proposed switch architecture allows for a conversion cost saving in the order of 90% with respect to a classical architecture in which only shared full range wavelength converters are used.

In this paper we evaluate the performance of Bufferless Optical Packet Switches equipped with shared Tunable Optical Wavelength Converters (TOWC) and supporting Quality of Service. The TOWCs sharing is partial, that is each Output Fiber shares one pool of TOWCs shared by all of the packets directed to that Output Fiber. The QoS, expressed in terms of Packet Loss Probability, is differentiated by giving the packets different priorities in accessing both the output wavelengths and the TOWCs. A scheduling algorithm is proposed and its complexity is evaluated. The QoS technique effectiveness is studied by means of a sophisticated analytical model validated by simulation results. The results show that the proposed technique to support QoS allows a good differentiation of the QoS offered to the packets.

In this paper we analyze intra-domain routing protocols improvements to support new features required by realtime services. In particular we introduce OSPF fast convergence and highlight the advantage of using a dynamic algorithm instead of the Dijkstra one to compute the shortest paths. Then we propose a new multi-path dynamic algorithm which uses multipath information to make a fast determination about the new shortest paths when a link failure occurs, reducing this way the network re-convergence time. To evaluate the proposed algorithm performance we have implemented it in the OSPF code of the Quagga open-source routing software. We compare our own algorithm with three different dynamic algorithms, like the one implemented in Cisco routers and the two others, well known in literature, proposed by Narvaez and Ramalingam-Reps. We show how, by exploiting multi-path information, our algorithm performs, in many case studies, better than the above algorithms, especially in a link failure scenario.

An architecture is proposed for a wavelength division multiplexed (WDM) optical packet switch equipped with both limited range wavelength converters (LRWCs) and shared full range wavelength converters (FRWCs). The FRWCs are used to overcome the performance degradation in terms of packet loss probability due to the use of LRWCs only. A probabilistic model is proposed to dimension the number of shared FRWCs so that the same packet loss probability of a switch equipped with only shared FRWCs is guaranteed. After introducing a cost model of the converters depending on the range conversion, we show that the architecture may allow conversion cost saving in the order of 85%.

The main idea of the third generation (3G) networks is to merge two of the most important communications systems: Cellular networks and Internet. The IP Multimedia Subsystem was defined by 3GPP as the key element in the 3G architecture that makes it possible to provide ubiquitous cellular access to all the services provided by the Internet. In this scenario a secure mobile service becomes an important issue. Considering that Mobile IPv6 and SIP are key technologies for mobility management and provision of services in IMS respectively, this article shows the impact of different security levels and types of mobility using as security performance parameters the average authentication cost and the average authentication delay and suggests a method where the user can choose the security level as a function of the distance to the IMS Home domain and IMS CN (Correspondent Node) Terminal.

It is cost-effective to install multiple fibers in each link of an all-optical network, because the cost of fibers is relatively low compared with the installation cost. In this paper we propose an architecture of an bufferless multi- fiber optical packet switch (OPS) using the wavelength dimension for contention resolution. In order to save the number of tunable optical wavelength converters (TOWC), the proposed architecture shares the TOWCs among the arriving packets. An analytical model, validated by means of simulations, is proposed to evaluate the Packet Loss Probability of the switch. A sensitivity analysis of the TOWCs saving of a multi-fiber switch with respect to a single-fiber switch is carried out as a function of the main switch and the traffic parameters (number of input lines, number of wavelengths per fiber, offered traffic,......). In some cases the saving can reach 50%.

This paper analyses the performance of an Optical Packet Switch equipped with multicast wavelength converters shared among the arriving packets. The architecture performance is evaluated by means of an analytical model and it is compared to the one of an Optical Packet Switch equipped with unicast wavelength converters. The obtained results show that in a multicast traffic scenario the proposed architecture allows the Wavelength Converters to be saved. In some cases the gain can be in the order of 95%.

OSPF (open shortest path first) is a widely used intra-domain routing protocol in IP networks. Processing delays in OSPF implementations impact the time needed for both intra-domain and inter-domain routing to reconverge after a topology change. In this paper we introduce a performance index, referred to as the switching time, allowing the router reconverge to be characterized when network topology changes occur. We propose a test methodology in order to measure the introduced performance index in router realized with the personal computer hardware and equipped with Quagga, the most used open routing software. An optimization of the Quagga routing software has been performed and better performance has been obtained in terms of switching time

This paper evaluates the performance of an optical packet switching architecture that uses the wavelength conversion technique to solve the packet contention problem. The architecture, referred to as shared per node (SPN), is equipped with limited-range wavelength converters shared per node. We evaluate for this architecture the performance of the optimum scheduling algorithm by resolving an integer linear programming problem. Unfortunately the optimum scheduling algorithm has a high time complexity and it cannot be adopted for optical packet switches requiring packet scheduling time in the order of 10/100 ns. For this reason we propose some scheduling algorithms allowing the best optimum scheduling performance to be reached in low computation time. In particular an algorithm, based on heuristic rules, is proposed able to reach good performance with a complexity O(M),M being the number of wavelengths used

This paper compares selected optical packet switching architectures that use a wavelength conversion technique to solve the packet contention problem. The architectures are equipped with shared and limited-range wavelength converters. This paper focuses on two architectures: the shared per node (SPN) and the shared per output fiber (SPOF) architectures. The analytical results show how the use of a reduced number of limited-range wavelength converters with small range allows these switches to obtain the same performance as an architecture equipped with all of the wavelength converters and using a full wavelength conversion.

The objective of this study is to propose a new optical packet switching architecture in which the wavelength converters, needed to solve output packet contentions, are shared per input line; according to this sharing strategy the packets arriving at a given input fiber shares a converter pool that can be accessed when wavelength conversions are required. In the paper we evaluate the performances of the proposed architecture when control algorithms with different complexity, are adopted. Under a unicast traffic scenario the obtained performances are compared to the ones of the architectures in which the wavelength converters are shared per node and per output line respectively. The carried out comparison shows that, with respect to the architecture with wavelength converters shared per output line, the proposed architecture allows to obtain a 30% saving of wavelength converters when a simple control algorithm is adopted; the saving can reach 80% if an optimized control algorithm is used. On the contrary the architecture with sharing per node needs fewer wavelength converters than the proposed architecture, but has the drawback to have a switching matrix much complex evaluated in terms of needed number of semiconductor optical amplifier; this complexity is due to the flexibility provided to the arriving packets in accessing the converters bank shared per node.

The objective of this study is investigate the performance difference of packet switching architectures working in a synchronous and asynchronous way respectively; in such architectures the packet contention is resolved in the wavelength domain and the used wavelength converters are shared; we investigate on the saving of the number of converters that the sharing technique allows to obtain in the synchronous and asynchronous architectures and compare the obtained results. These ones show that when a packet loss probability is fixed, in the synchronous case a greater number of converters is saved, in some cases the gain is 40% more than the asynchronous case; furthermore in the asynchronous case a more expensive switching matrix is needed.

In this paper, the optical burst switching with burst dropping (OBS/BD) technique is proposed to be implemented in an all-optical backbone network to support IP traffic. The OBS/BD is based on two main features: i) several IP packets are assembled in a single macro-packet, called burst; ii) the burst contention in an optical switch is handled by the means of two techniques: the wavelength dimension and the "burst dropping". In the optical burst switching (OBS), the entire burst is discarded when all of the output wavelengths are engaged at its arrival instant. Whereas, the OBS/BD technique discards only the initial part of the burst and forwards the final part of the burst beginning at the instant in which one wavelength becomes free. Obviously, the OBS/BD, respect to the OBS, allows to increase the switch throughput, i.e. the number of forwarded IP packets. We develop the analytical models that quantify this increase tacking into account of several system parameters.

We study the optical burst switching (OBS) paradigm for the support of the TCP flows in an all optical network (AON). We analyze the TCP send rate, i.e. the amount of data sent per time unit, taking into account of: (i) the burst assembly mechanism, called burstification process; (ii) the burst loss events inside the OBS network. The goals of the paper are to investigate the effect of the variation of the burstification period and to derive some general guidelines about the dimensioning of the burstification period. With respect to the case in which any assembly mechanism is missing, the results show that an accurate dimensioning of the burstification period yields negligible penalties with regard to the low speed sources and significant benefits with regard to the high speed sources.

Coupling MPLS traffic engineering on top of a wavelength-routed WDM layer offers great flexibility to operators to allocate traffic demands in their networks. We consider the problem of off-line joint configuration at both packet and optical layers. We consider time-variant offered traffic, and assume that the operator has knowledge of the traffic dynamics as a set of traffic matrices at different instants. A novel mixed integer linear programming (MILP) formulation is proposed, which takes as input this set of traffic matrices, and provides an optimal static configuration capable of accommodating the time-varying traffic. We provide a resolution strategy based on heuristics, and give numerical results for some sample cases. The proposed method is compared with a simple alternative approach for obtaining a single static solution, to show that our method utilizes much fewer resources. The solution under the proposed formulation is also compared with the set of solutions obtained by running distinct optimization problems at different instants, showing that the increase of resource is minimal. Hence our approach can provide a static configuration with about the same resources as a fully adaptable dynamical configuration.

In this paper multicast three-stage multiple-link interconnection networks are considered. Each network stage is composed by full multicast switching elements connected to the switching elements of adjacent stages through h links, with h>1. For such networks, called generalized three-stage interconnection networks, the necessary and sufficient condition for strict sense non-blocking is presented. These results extend those currently available in literature for multicast networks only in case of single-link inter-stage connections. Moreover, it is also demonstrated that, in the worst case of unrestricted fanout, the complexity of a N/spl times/N multicast multi-link network can be limited to O(N5/3). Such a complexity is lower than that relevant to a crossbar network of the same size for N/h>182.

The differentiated service architecture is proposed as a scalable approach to QoS for IP networks. Therefore it is based on the aggregate (per class) scheduling of packets, but it aims at providing QoS to single flows. In particular the expedited forwarding (EF) per hop behavior (PHB) and the related premium service have been defined in order to provide determinist QoS guarantees to IP flows: zero loss and very low delay and jitter. Hence a possible approach to characterize and to dimension a network using the EF PHB is the worst-case analysis. We propose a worst case analysis which provides bounds to the queuing delay for a class of network topologies. Our results are compared with similar available results, which provide "looser" bounds. The comparison with simulation results shows that the bound is not enough tight to be of practical use. We justify the reason for this behavior and indicate directions for further improvements.

This paper analyzes a framework to offer reservation of resources and QoS guarantees according to the resource reservation protocol (RSVP) paradigm in a network cloud that supports a differentiated services architecture. The key elements are: intelligent edge devices; a flow admission and resource allocation method involving an admission control server; "simple" core routers based on the differentiated services model. The main functionality of a client/server protocol between the edge devices and the admission control server, called simple admission control protocol, is described. The proposed framework is referred to as admission control server based resource allocation. Scalability is analyzed and compared with RSVP approach.

We describe an ATM system architecture for satellite communications. The proposed architecture includes on-board switching, and supports the ATM traffic categories defined in previous specifications. In this framework, a critical issue is the control of congestion phenomena. In particular, the application of feedback-based control strategies to a satellite network is critical due to the peculiarities of such an environment: very large propagation delay, expensive transfer capacity, and limited on-board processing capability. The available bit rate (ABR) is the ATM service category handled according to a reactive congestion control (RCC). The focus of this paper is the definition of an RCC that is fully compatible with the standard ABR protocols, and that takes into account the constraints of the satellite environment. We also derive an analytical model that allows us to evaluate the performance of the proposed scheme and to dimension the system. The analytical model is validated with simulations.

In this paper, an analytical model for the evaluation of the blocking probability of a three stage STM switch in presence of multicast is presented. The basic characteristics of this model are: (i) the elementary switches can assume any size; (ii) multicast connections can be characterised by any fan-out distribution; (iii) both single request and additive request scenarios are analysed. Moreover, three network operation alternatives are analysed, i.e. multicasting is carried-out in: (a) the first and the third stages; (b) the second and the third stages; (c) all the three stages. The model uses a mixed approach derived from approaches proposed by Lee (1955)and Jacobeus (1950). The analytical results are compared with those arising from simulation. The good accordance of the two series of results demonstrates the soundness of the model assumptions.

The main purpose of this paper is to assess the feasibility of the distributed control approach in the definition of a wireless ATM MAC protocol. A novel protocol, named D/sup 2/MA, is presented. D/sup 2/MA is based on a double distribution of the access procedure and queueing capabilities. All the reservation and scheduling functions are performed by the mobile stations independently, whereas only passive operations are required to the base station. An accurate analytical model of D/sup 2/MA has been developed. This model examines a single radio cell with a population m of mobile stations acting as traffic sources. Each station is equipped with a finite buffer of B cell size. A comparison with simulation results shows the accuracy of the analytical approach.

This paper deals with a novel strategy for connection admission control in ATM networks. This strategy, called worst deterministic pattern allocation (WDPA), aims at reaping statistical gain of ATM, through a simple and controllable bandwidth allocation. WDPA is based on the concept of preventively constraining information sources to emit their cells according to a superimposed deterministic mask. Resource allocation is performed taking into account only the parameters of the declared deterministic mask. The same allocation rule is utilized in every network section. Application of WDPA to input and output queueing switches is also discussed and its compatibility with both these architectures is demonstrated. A performance study is presented. A comparison of the efficiency resulting from WDPA application with that relevant to peak allocation and pure statistical allocation is presented. Results show that, by fixing a maximum transit delay, WDPA outperforms statistical allocation if path length exceed few hops.>

The multiplexing of shaped on-off sources on an asynchronous transfer mode (ATM) link is addressed. In particular, an N-level shaper is analyzed. It modulates the source output bit rate on the basis of the buffer occupancy level. A very accurate analytical model describing its behavior is provided. Such a model allows an accurate description of the shaper output flow characteristics. A simple analytical model is also proposed for an ATM multiplexer in order to evaluate the advantages arising from the source shaping. The accuracy of the analytical results comes out from the comparison with the simulation ones. Numerical results show the effectiveness of the proposed shaping mechanism. They demonstrate that a substantial increase of the number of multiplexable sources is possible, for a given value of cell loss probability.>

The capabilities of the cyclic reservation multiple access (CRMA) protocol for supporting mixed video and data traffic was evaluated by computer simulation. The results show that in order to obtain good performance and fairness between all the mixed stations, they should have similar requirements in terms of the number of slots that are requested at each reservation cycle. It is therefore important to reduce the variability by aggregating more slots for stations with short packets, and by transmitting long frames in successive cycles for long packets. The optimal selection of the low and high bound on the number of slots can significantly improve the performance of the CRMA network under mixed traffic conditions.>

The loss performance is studied of an ATM (asynchronous transfer mode) multiplexer, whose input consists of the superposition of a multiplicity of homogeneous ON-OFF sources. The approach is based on the approximation of the actual input process by means of a suitably chosen two-state Markov modulated Poisson process (MMPP), as a simple and effective choice for the representation of the superimposed arrival streams. To accurately evaluate the cell loss performance, a matching procedure was developed which allows the derivation of a tight upper bound on the cell loss probability and the characterization of its asymptotic behavior as the buffer size increases. Moreover, this procedure yields insight into the multiplexer performance behavior, as the buffer size and the source parameters are varied, and clarifies the modeling limits implied by the choice of an approximating MMPP with only two states.>

This work deals with a general method for buffer design in an ATM system in which the target loss probability should be very low (e.g. less than 10/sup -9/). This method is based on the application of the generalized extreme value theory (GEVT) to results arising from simulation runs. This theory allows the estimation of very small probabilities which would not be evaluable with the traditional Monte Carlo approach. An advantage of 4/5 decades with respect to Monte Carlo limits can be obtained utilizing the same sample set. The extension of the theory to the case of distribution functions of discrete random variables is discussed. The applicability of the method is demonstrated with reference to known probability distribution functions. Moreover, the GEVT is applied in the cases of classical queuing systems. The general criteria for the evaluation of the basic GEVT parameters are discussed.>

An algorithmic model for the performance evaluation of the medium access control (MAC) protocol for a satellite system in an asynchronous transfer mode (ATM) environment is presented. This model allows analysis of general load configurations and yields the mean value of the performance parameters (e.g. queue lengths and access delays). The model is based on a computer-oriented approach, and the characterization of the key model variables is obtained by means of an iterative procedure. A comparison of the model analysis results to those obtained by a simulative approach shows a satisfactory matching.>

The performance of an asynchronous transfer mode (ATM) multiplexer whose input consists of the superposition of a multiplicity of homogeneous on-off sources modeled by a two-state Markovian process is studied. The approach is based on the approximation of the actual input process by means of a suitably chosen two-state Markov modulated Poisson process (MMPP), as a simple and effective choice for the representation of superposition arrival streams. To evaluate the cell loss performance, a new matching procedure that leads to accurate results compared to simulation is developed. The application limits of the proposed method are also discussed. The outstanding physical meaning of this procedure permits a deep insight into the multiplexer performance behavior as the source parameters and the multiplexer buffer size are varied.>

An access protocol suitable for asynchronous transfer mode (ATM) operation in an integrated service broadband metropolitan area network (MAN) is presented. This protocol is designed for a twin-bus optical network and is characterized by a fully distributed control mechanism. A detailed description of the MAC procedure and the results of its performance evaluation are given. In particular, the high fairness degree and the very high throughput values that are the distinctive features of this protocol are highlighted and compared with those relevant to the current version of the IEEE standard 802.6.>

A fully distributed routing control scheme, called the flooding technique, is described. It is to be applied to an ATM (asynchronous transfer mode) switch architecture for the establishment of CBO (continuous bit stream oriented) calls. The main advantage of this technique with respect to a centralized solution consists of a sensitive improvement of the system performance, particularly in fault-tolerance and flexibility. Two service scenarios are considered: CBO services characterized by a burstiness equal to one, and by a burstiness greater than one. The implementation alternatives of the flooding technique relevant to both the scenarios are presented, and their main characteristics are compared. The ATM switch architecture and its mode of operation are also described. In particular, the different strategies for handling CBO and nonisochronous classes of traffic are presented, and some properties on the topology of the switching fabric are given.>

The nonblocking properties of the generalized parallel delta networks (GPDNs) and their application to the photonic switching environment are discussed. It is demonstrated that the crosstalk due to the switch crossover can be completely avoided by means of a proper dimensioning of the network parameters. A classification of the nonblocking properties is proposed. In particular, a nonblocking condition, called as strong, is defined. It establishes that two paths are not in conflict if they do not share any switching element. The strong nonblocking condition has been considered together with the traditional one. This second condition, called as weak because it is based on the unshareability of the interstage links, is normally applied in the electronic environment. The conditions which have to be satisfied so that a GPDN can be weakly and/or strongly nonblocking are found and demonstrated.>

The definition is presented of a class of N*N multistage interconnection networks called generalized parallel delta networks (GPDNs). This class includes the already known replicated delta networks (RDNs) and parallel delta networks (PDNs). For GPDNs, the rearrangeability condition is given and a routing algorithm for the establishment of any set of connection requests is presented. The proposed algorithm operates for GPDNs composed of 2/sup q/*2/sup q/ switching elements and it is able to set up any permutation with a time complexity equal to O(N log/sub 2/ N). The applicability of RDNs, PDNs, and other GPDNs for the implementation of rearrangeable topologies is investigated. In particular, it is proved that if large networks (N>256) have to be implemented, GPDNs require a smaller number of switching elements than RDNs or PDNs.>

A study has been carried out to ascertain the potential benefits of asynchronous transfer mode (ATM) in the context of satellite communications and to determine the most suitable system architectures. System design guidelines are examined, and the network architecture, transmission arrangements, multiplexing and switching schemes, medium access control, and protocol layering are discussed. Particular consideration is given to the definition of the onboard switch structure.>

This paper deals with the definition of a class of NxN interconnection networks called Parallel Delta Network (PDN). For this class of networks the non-blocking conditions are given. In particular, by means of the graph colouring technique, it has been proved that the minimum number of Delta subnetworks (L) necessary to provide the non-blocking property is L=nfS/21-1 where n is the size of the basic switching element and S the number of stages required by an NxN Delta network. A routing algorithm for the establishment of any permutation has been defined. \nIt operates for any value of n and shows a polynomial time \ncomplexity equal to O(N3/2). Moreover, in case of the setup \nof a single connection request, this algorithm assures a \ntime complexity equal to O(VN). This property makes it \nwell suitable to an asynchronous telecommunication \nenvironment.