Distributed training of artificial intelligence models, such as Large Language Models (LLMs), generates highly structured and intense traffic patterns between GPUs, with synchronous and repetitive flows that can easily cause congestion and bottlenecks in data center networks. In this context, currently adopted protocols, such as RoCEv2, show significant limitations in the presence of bursty traffic and low entropy, compromising overall system efficiency. Segment Routing over IPv6 (SRv6) offers a programmable mechanism to steer AI workload traffic along explicitly chosen paths, enabling precise and congestion-aware routing under dynamic conditions. Lightweight monitoring modules can detect congestion conditions in real time and report them to the orchestrator or NICs, enabling dynamic rerouting decisions without requiring control-plane signaling or state in the fabric. SRv6 micro-segment (uSID) encoding allows the NIC to steer traffic along alternate, congestion-free paths simply by updating the IPv6 destination address, preserving RoCEv2 semantics while ensuring rapid adaptability. This work provides a practical implementation and experimental validation of the recent IETF Internet-Draft “SRv6 for Deterministic Path Placement in AI Backends”, demonstrating its feasibility and performance benefits in RoCEv2-based infrastructures. The results highlight the potential of SRv6 as a practical and vendor-agnostic solution to enhance networking efficiency in modern AI datacenters.

Federated testbeds enable collaborative research by providing access to diverse resources, including computing power, storage, and specialized hardware like GPUs, programmable switches and smart Network Interface Cards (NICs). Efficiently sharing these resources across federated institutions is challenging, particularly when resources are scarce and costly. GPUs are crucial for AI and machine learning research, but their high demand and expense make efficient management essential. Similarly, advanced experimentation on programmable data plane requires very expensive programmable switches (e.g., based on P4) and smart NICs. This paper introduces SHARY (SHaring Any Resource made easY), a dynamic reservation system that simplifies resource booking and management in federated environments. We show that SHARY can be adopted for heterogenous resources, thanks to an adaptation layer tailored for the specific resource considered. Indeed, it can be integrated with FIGO (Federated Infrastructure for GPU Orchestration), which enhances GPU availability through a demand-driven sharing model. By enabling real-time resource sharing and a flexible booking system, FIGO improves access to GPUs, reduces costs, and accelerates research progress. SHARY can be also integrated with SUP4RNET platform to reserve the access of P4 switches.

Recent advances in network switch designs have enabled machine learning inference directly within the switch at line speed. However, hardware constraints limit switches capabilities of tracking stateful features essential for accurate inference, as the demand for these features grows rapidly with line rates. To address this, we propose DIDA, a distributed in-network machine learning approach. In DIDA, feature extraction occurs at the host, features are transmitted via in-band telemetry, and inference is performed on the switches. In this paper, we evaluate the effectiveness and efficiency of this architecture. We examine its impact on network bandwidth, CPU and memory usage at the host, and its robustness across different feature sets and deep neural network classifications.

With the rise of the Network Softwarization era, eBPF has become a hot technology for efficient packet processing on commodity hardware. However the development of custom eBPF solutions is a challenging process that requires highly qualified human resources. Indeed, in eBPF, it is difficult to devise truly modular applications since the development model does not favour the use of pre-compiled functions and libraries. In addition, for safety purposes, each eBFF program must pass a binary code verifier of the Linux kernel, which may increase the difficulty of the development process. To overcome such difficulties and enable a new development model, in this paper we propose the eCLAT framework with the goal to lower the learning curve of engineers by re-using eBPF code in a programmable way. eCLAT offers a high level programming abstraction to eBPF based network programmability, allowing a developer to create custom application logic with no need of understanding the complex details of regular eBPF programming. A developer can write eCLAT scripts in a python-like language to compose eBPF programs. To support such abstraction at the eBPF level, we created an eBPF framework called HIKe which brings code reuse and modularity in eBPF. The eCLAT/HIKe solution does not require any kernel modification. The new development model is tested through two concrete examples and compared with other proposed frameworks in the eBPF world.

Software-Defined Wide Area Networks (SD-WANs) are used to provide services to enterprises with geographically dispersed locations in a flexible and efficient way. We focus on SD-WAN services based on the Segment Routing over IPv6 (SRv6) technology. Performance Monitoring solutions are needed in SD-WANs to detect performance degradation and outages, and optimize network operations. In this paper, we describe a high performance solution for end-to-end delay monitoring for SRv6 based SD-WAN services. The proposed solution leverages the Simple Two-way Active Measurement Protocol (STAMP) to monitor the delay of an SRv6 path between two nodes called STAMP Session-Sender and Session-Reflector. We describe three implementations of the STAMP Session-Sender and Session-Reflector for a Linux software router and compare their performance. In particular, two implementations are based on user space processing and one is based on eBPF. The results show that the eBPF-based implementation outperforms the user space implementations and has a negligible impact on the forwarding capacity of the Linux software router.

The Segment Routing (SR) architecture is based on source routing. Within an SR enabled network, a list of instructions called segments can be added to the packet headers to influence the forwarding and the processing of the packets. In SRv6 (Segment Routing over IPv6 data plane) the segments are represented with IPv6 addresses, which are 16 bytes long. There are some SRv6 service scenarios that may require to carry a large number of segments in the IPv6 packet headers. Reducing the size of these overheads is useful to minimize the impact on MTU (Maximum Transfer Unit) and to enable SRv6 on legacy hardware devices with limited processing capabilities that could suffer from the long headers. In this paper we present the Micro SID solution for the efficient representation of segment identifiers. The proposed Micro SID solution has been implemented on three different architectures (VPP, Linux, P4) and interoperability tests have been performed. We also analyze the reduction of the header size that can be achieved with Micro SIDs and compare it with other proposals for segment list compression. Our results show that the header size can be reduced up to 75%. Finally, we mention that a fundamental asset of the proposed Micro SID solution is the full compatibility and seamless interoperability with existing SRv6 architecture.

With the rise of the Network Softwarization era, eBPF has become a hot technology for efficient packet processing on commodity hardware. However the development of custom eBPF solutions is a challenging process that requires highly qualified human resources. In this paper we propose the eCLAT framework with the goal to lower the learning curve of engineers by re-using eBPF code in a programmable way. eCLAT offers a high level programming abstraction to eBPF based network programmability, allowing a developer to create custom application logic in eBPF with no need of understanding the complex details of regular eBPF programming. To support such modularity at the eBPF level, we created an eBPF library that implements a virtual machine, called HIKe VM. The HIKe VM library extends the conventional eBPF programs so that they can be integrated in eCLAT. The eCLAT/HIKe solution does not require any kernel modification.

Network operators are facing significant challenges meeting the demand for more bandwidth, agile infrastructures, innovative services, while keeping costs low. Network Functions Virtualization (NFV) and Cloud Computing are emerging as key trends of 5G network architectures, providing flexibility, fast instantiation times, support of Commercial Off The Shelf hardware and significant cost savings. NFV leverages Cloud Computing principles to move the data-plane network functions from expensive, closed and proprietary hardware to the so-called Virtual Network Functions (VNFs). In this paper we deal with the management of virtual computing resources (Unikernels) for the execution of VNFs. This functionality is performed by the Virtual Infrastructure Manager (VIM) in the NFV MANagement and Orchestration (MANO) reference architecture. We discuss the instantiation process of virtual resources and propose a generic reference model, starting from the analysis of three open source VIMs, namely OpenStack, Nomad and OpenVIM. We improve the aforementioned VIMs introducing the support for special-purpose Unikernels and aiming at reducing the duration of the instantiation process. We evaluate some performance aspects of the VIMs, considering both stock and tuned versions. The VIM extensions and performance evaluation tools are available under a liberal open source licence.

Segment Routing (SR) is a form of loose source routing. It provides the ability to include a list of instructions, called segments, in the packet header. The SR architecture has been first implemented with the MPLS (SR-MPLS) data plane and then, quite recently, with the IPv6 data plane (SRv6). SRv6 is a promising solution to support advanced services such as Traffic Engineering, Service Function Chaining and Virtual Private Networks. The SRv6 data plane is supported in many different software forwarding engines including the Linux kernel and the Vector Packet Processor (VPP), as well as in hardware devices. In this paper, we present SRPerf, a performance evaluation framework for software and hardware implementations of SRv6. SRPerf is able to perform different benchmarking tests such as throughput and latency. The architecture of SRPerf can be easily extended to support new benchmarking methodologies as well as different SRv6 implementations. We have used SRPerf to evaluate the performance of two SRv6 implementations: Linux kernel and VPP. SRPerf is a valuable tool in the context of modern forwarding engines where new features can be added at fast pace, as it helps experimenters to validate their work. In this work, we have leveraged SRPerf to validate the implementation of some SRv6 behaviors in the Linux kernel and we have discovered and fixed some implementation flaws, making available the fixed code.

Segment Routing over IPv6 (SRv6 in short) is a networking architecture suitable for both IP backbones and datacenters. The research, standardization and implementation of this architecture are actively progressing and SRv6 is already adopted in a number of large scale deployments. Effective solutions for Performance Monitoring (PM) of SRv6 networks are strongly needed and there is a lot of activity in this area. A full blown Performance Monitoring solution needs to include: i) Data Plane (as needed to measure metrics such as packet loss and delay); ii) Control Plane (to send commands to the monitoring entities in the nodes); iii) Management Plane (e.g., to collect the measured metrics). Moreover, Big-Data tools and solutions can be applied inside or above the traditional Management Plane boundaries to store and analyze the collected data. In this article we describe SRv6-PM, a solution for Performance Monitoring of SRv6 networks that deals with all the aspects discussed above. SRv6-PM features a cloud-native architecture that supports: i) the ingestion, processing, storage and visualization of PM data using Big-Data tools; ii) the SDN-based control of network routers to drive the performance monitoring operations. In particular, we focus on Loss Monitoring and consider a solution capable of tracking single packet loss events operating in near-real time (e.g., with a time granularity in the order of 10-20 seconds). SRv6-PM is released as open source. We offer a re-usable and extensible platform that can be automatically deployed in different environments, from a single host to multiple servers on private/public clouds and includes a set of Big-Data tools and the SDN control plane. We also provide a reproducible Data Plane environment for PM experiments in SRv6 networks based on the Mininet emulator.

Current IP-based networks support a wide range of delay-sensitive applications such as live video streaming of network gaming. Providing an adequate quality of experience to these applications is of paramount importance for a network provider. The offered services are often regulated by tight Service Level Agreements (SLAs) that needs to be continuously monitored. Since the first step to guarantee a metric is to measure it, delay measurement becomes a fundamental operation for a network provider. In many cases, the operator needs to measure the delay on all network links. We refer to the collection of all link delays as the Link Delay Vector (LDV). Typical solutions to collect the LDV impose a substantial overhead on the network. In this paper, we propose a solution to measure the LDV in real-time with a low-overhead approach. In particular, we inject some flows into the network and infer the LDV based on the delay of those flows. To this end, the monitoring flows and their paths should be selected minimizing the network monitoring overhead. In this respect, the challenging issue is to select a proper combination of flows such that by knowing their delay it is possible to solve a set of linear equations and obtain a unique LDV. This combination of monitoring flows should be optimal according to some criteria and should meet some feasibility constraints. We first propose a mathematical formulation to select the optimal combination of flows, in form of an Integer Linear Programming (ILP) problem. Then we develop a heuristic algorithm to overcome the high computational complexity of existing ILP solvers. As a further step, we propose a meta-heuristic algorithm to solve the above-mentioned equations and infer the LDV. The challenging part of this step is the volatility of link delays. The proposed solution is evaluated over real-world emulated network topologies using the Mininet network emulator. Emulation results show the accuracy of the proposed solution with a negligible networking overhead in a real-time manner.

The Segment Routing (SR) architecture is based on loose source routing. A list of instructions, called segments can be added to the packet headers, to influence the forwarding and the processing of the packets in an SR enabled network. In SRv6 (Segment Routing over IPv6 data plane) the segments are represented with IPv6 addresses, which are 16 bytes long. There are some SRv6 service scenarios that may require to carry a large number of segments in the IPv6 packet headers. Reducing the size of these overheads is useful to minimize the impact on MTU (Maximum Transfer Unit) and to enable SRv6 on legacy hardware devices with limited processing capabilities that could suffer the long headers. In this paper we present the Micro SID solution for the efficient representation of segment identifiers. With this solution, the length of the segment list can be drastically reduced.

Segment Routing over IPv6 (SRv6 in short) is a networking solution for IP backbones and datacenters, which has been recently adopted in several of large scale network deployments. The SRv6 research, standardization and implementation activities are going on at a remarkable pace. In particular, a number of Internet Drafts have been submitted related to the Performance Monitoring (PM) of flows in an SRv6 network. In this paper we discuss the proposed PM approaches, considering both data plane and control plane aspects and focusing on loss monitoring. Then we describe the implementation of a per-flow packet loss measurement (PF-PLM) solution based on the “alternate marking” method. Our implementation is based on Linux kernel networking and it is open source. We describe a platform that can be used to validate the standardization proposals from a functional perspective and the implemented solution from the performance point of view. We analyze two different design choices for the implementation of PF-PLM and evaluate their impact on the maximum forwarding throughput of a software based (Linux) router.

Segment Routing is a source routing based architecture that provides an opportunity to include a list of instructions called segments in the packet headers. The segments may allow the inclusion of detours for responding to Traffic Engineering needs or Service Function Chaining implementations. Even though there is an increasing interest towards enhancing and adopting Segment Routing, the administrators are still burdened with the task of manually write and maintain the segment lists. Such type of management presents several challenges ranging from error-prone configurations to increased response time for network updates. In this paper, we present a Segment Routing management framework named Busoni, which automates and simplifies the process of segments lists management. Additionally, we also provide programming tools to compose and manage Segment Routing policies that operate efficiently, even under multi-tenancy environments. Using different use cases, we show the programming capabilities offered by our framework.

We consider the IPv6 Segment Routing (SRv6) technology for Service Function Chaining of Virtual Network Functions (VNFs). Most of the VNFs are legacy VNFs (not aware of the SRv6 technology) and expect to process traditional IP packets. An SR proxy is needed to support them. We have extended the implementation of SRv6 in the Linux kernel, realizing an open source SR-proxy, referred to as SRNK (SR-Proxy Native Kernel). The performance of the proposed solution (SRNKvl) has been evaluated, identifying a poor scalability with respect to the number of VNFs to be supported in a node. Therefore we provided a second design (SRNKv2), enhancing the Linux Policy Routing framework. The performance of SRNKv2 is independent from the number of supported VNFs in a node. We compared the performance of SRNKv2 with a reference scenario not performing the encapsulation and decapsulation operation and demonstrated that the overhead of SRNKv2 is very small, on the order of 3.5%.

Summary Middleboxes have become a vital part of modern networks by providing services such as load balancing, optimization of network traffic, and content filtering. A sequence of middleboxes comprising a logical service is called a Service Function Chain (SFC). In this context, the main issues are to maintain an acceptable level of network path survivability and a fair allocation of the resource between different demands in the event of faults or failures. In this paper, we focus on the problems of traffic engineering, failure recovery, fault prevention, and SFC with reliability and energy consumption constraints in Software Defined Networks (SDN). These types of deployments use Fog computing as an emerging paradigm to manage the distributed small‐size traffic flows passing through the SDN‐enabled switches (possibly Fog Nodes). The main aim of this integration is to support service delivery in real‐time failure recovery in an SFC context. First, we present an architecture for Failure Recovery called FRFP; this is a multi‐tier structure in which the real‐time traffic flows pass through SDN‐enabled switches to jointly decrease the network side‐effects of flow rerouting and energy consumption of the Fog Nodes. We then mathematically formulate an optimization problem called the Optimal Fast Failure Recovery algorithm (OFFR) and propose a near‐optimal heuristic called Heuristic HFFR to solve the corresponding problem in polynomial time. In this way, the reliability of the selected paths are optimized, while the network congestion is minimized.

Service function chaining (SFC) allows the forwarding of traffic flows along a chain of virtual network functions (VNFs). Software defined networking (SDN) solutions can be used to support SFC to reduce both the management complexity and the operational costs. One of the most critical issues for the service and network providers is the reduction of energy consumption, which should be achieved without impacting the Quality of Service. In this paper, we propose a novel resource allocation architecture which enables energy-aware SFC for SDN-based networks, considering also constraints on delay, link utilization, server utilization. To this end, we formulate the problems of VNF placement, allocation of VNFs to flows, and flow routing as integer linear programming (ILP) optimization problems. Since the formulated problems cannot be solved (using ILP solvers) in acceptable timescales for realistic problem dimensions, we design a set of heuristic to find near-optimal solutions in timescales suitable for practical applications. We numerically evaluate the performance of the proposed algorithms over a real-world topology under various network traffic patterns. Our results confirm that the proposed heuristic algorithms provide near-optimal solutions (at most 14% optimality-gap) while their execution time makes them usable for real-life networks.

This paper focuses on analyzing some key business aspects that arise during the deployment of key novel enabling technologies for 5G systems. Results are taken out of two EU-funded ongoing research projects, namely 5G-MiEdge and Superfluidity, which largely exploit mmWave communications and softwarization concepts for 5G networks. We initially provide a stakeholder analysis of the 5G ecosystem, as well as a Strengths Weaknesses Opportunities Threats (SWOT) analysis of a couple of key and most promising 5G use cases. For one use case also a preliminary business model is provided. Then we detail an economic 5G cost model, which is able to provide indications on the profitability of 5G networks. Finally, we highlight the planned future works.

Optimal interface selection is a key mobility management issue in heterogeneous wireless networks. Measuring the physical or link level performance on a given wireless access networks does not provide a reliable indication of the IP connectivity, delay, and loss on the (bidirectional) paths from the Mobile Host to the node that is handling the mobility, over different heterogeneous networks. In this paper, we propose, implement, and analyze mechanisms for connectivity check and performance (network delay and packet loss) monitoring over IP access networks. We evaluate the accuracy and timeliness of the performance estimates and provide guidelines for tuning up the parameters. From the implementation perspective, we show that using application level measurements is highly CPU intensive, while a kernel based implementation has comparably a very low CPU usage. The Linux kernel implementation results in an efficient use of batteries in Mobile Hosts and intermediate Mobility Management Nodes can scale up to monitoring thousands of flows. The proposed solutions have been implemented in the context of a specific mobility management solution, but the results are of general applicability. The Linux implementation is available as Open Source.

The SRv6 architecture (segment routing based on IPv6 data plane) is a promising solution to support services like Traffic Engineering, service function chaining and virtual private networks in IPv6 backbones and datacenters. The SRv6 architecture has interesting scalability properties as it reduces the amount of state information that needs to be configured in the nodes to support the network services. In this paper, we describe the advantages of complementing the SRv6 technology with an software defined networking (SDN) based approach in backbone networks. We discuss the architecture of a SRv6 enabled network based on Linux nodes. In addition, we present the design and implementation of the Southbound API between the SDN controller and the SRv6 device. We have defined a data-model and four different implementations of the API, respectively based on gRPC, REST, NETCONF, and remote command line interface. Since it is important to support both the development and testing aspects we have realized an Intent-based emulation system to build realistic and reproducible experiments. This collection of tools automate most of the configuration aspects relieving the experimenter from a significant effort. Finally, we have realized an evaluation of some performance aspects of our architecture and of the different variants of the Southbound APIs and we have analyzed the effects of the configuration updates in the SRv6 enabled nodes.

5G is expected to become the dominant technology in the forthcoming years. In this work, we consider a 5G Superfluid network, as an outcome of the H2020 project SUPERFLUIDITY. The project exploits the concept of Reusable Functional Block (RFB), a virtual resource that can be deployed on top of 5G physical nodes. Specifically, we focus on the management of the RFBs in a Superfluid network to deliver a high definition video to the users. We design an efficient algorithm, called P5G, which is based on Particle Swarm Optimization (PSO). Our solution targets different Key Performance Indicators (KPIs), including the maximization of user throughput, or the minimization of the number of used 5G nodes. Results, obtained over a representative scenario, show that P5G is able to wisely manage the RFBs, while always guaranteeing a large throughput to the users.

We target the evaluation of a Superfluid 5G network from an economic point of view. The considered 5G architecture has notably features, such as flexibility, agility, portability and high performance, as shown by the H2020 SUPERFLUIDITY project. The proposed economic model, tailored to the Superfluid network architecture, allows to compute the CAPEX, the OPEX, the Net Present Value (NPV) and the Internal Rate of Return (IRR). Specifically, we apply our model to estimate the impact for the operator of migrating from a legacy 4G to a 5G network. Our preliminary results, obtained over two realistic case studies located in Bologna (Italy) and San Francisco (CA), show that the monthly subscription fee for the subscribers can be kept sufficiently low, i.e., typically around 5 [USD] per user, while allowing a profit for the operator.

Many reasons make NFV an attractive paradigm for IT security: lowers costs, agile operations and better isolation as well as fast security updates, improved incident responses and better level of automation. On the other side, the network threats tend to be increasingly complex and distributed, implying huge traffic scale to be monitored and increasingly strict mitigation delay requirements. Considering the current trend of the networking and the requirements to counteract to the evolution of cyber-threats, it is expected that also network monitoring will move towards NFV based solutions. In this paper, we present D-StreaMon an NFV-capable distributed framework for network monitoring realized to face the above described challenges. It relies on the StreaMon platform, a solution for network monitoring originally designed for traditional middleboxes. An evolution path which migrates StreaMon from middleboxes to Virtual Network Functions (VNFs) has been realized.

This paper presents an architecture to support Vir- tual Network Functions (VNFs) chaining using the IPv6 Segment Routing (SR) network programming model. Two classes of VNFs are considered: SR-aware and SR-unaware. The operations to support both SR-aware and SR-unaware VNFs are described at an architectural level and we propose a solution for SR-unaware VNFs hosted in a NFV node. An Open Source implementation of the proposed solution for a Linux based NFV host is available and a set of performance measurements have been carried out in a testbed.

We consider the problem of evaluating the performance of a 5G network based on reusable components, called Reusable Functional Blocks (RFBs), proposed by the Horizon 2020 SUPERFLUIDITY project. RFBs allow a high level of flexibility, agility, portability and high performance. After formally modelling the RFB entities and the network physical nodes, we optimally formulate the problem of maximizing different Key Performance Indicators (KPIs) on an RFB-based network architecture, in which the RFBs are shared among the nodes, and deployed only where and when they are really needed. Our results, obtained by solving the proposed optimization problem over a simple yet representative scenario, show that the network can be managed in a very efficient way. More in depth, the RFBs are placed into the nodes in accordance with the amount of requested traffic from users and the specific pursued KPI, e.g., maximization of user throughput or minimization of the number of used nodes. Moreover, we evaluate the relationship between the capacity of each node and the number of RFBs deployed on it.

We explore the opportunities and design options enabled by novel SDN and NFV technologies, by re-designing a dynamic content delivery network (CDN) service. Our system, named MOSTO, provides performance levels comparable to that of a regular CDN, but does not require the deployment of a large distributed infrastructure. In the process of designing the system, we identify relevant functions that could be integrated in the future Internet infrastructure. Such functions greatly simplify the design and effectiveness of services, such as MOSTO. We demonstrate our system using a mixture of simulation, emulation, testbed experiments, and by realizing a proof-of-concept deployment in a planet-wide commercial cloud system.

The introduction of SDN in Service Providers' networks like GÉANT is a challenging task. Prototypes of new generation services have to exhibit “carrier grade” characteristics, meet the high level expectations and specialized needs of GÉANT customers. In this demonstration, we present the SDN based prototype of GÉANT Open service, used by GÉANT customers and approved commercial partners to interconnect using Layer 2 circuits. Currently, this service is delivered through a set of Open eXchange Points leveraging on legacy solutions. The SDN based prototype has been realized on top of ONOS and leverages on hardware switches for the data plane. During the demo, which runs inside the GÉANT Testbed Service, we show how operators can deploy services and manage the SDN based infrastructure.

The current specification of the Segment Routing (SR) architecture requires enhancements to the intradomain routing protocols (e.g. OSPF and IS-IS) so that the nodes can advertise the Segment Identifiers (SIDs). We propose a simpler solution called PMSR (Poor Man's Segment Routing), that does not require any enhancement to routing protocol. We compare the procedures of PMSR with traditional SR, showing that PMSR can reduce the operation and management complexity. We analyze the set of use cases in the current SR drafts and we claim that PMSR can support the large majority of them. Thanks to the drastic simplification of the control plane, we have been able to develop an open source prototype of PMSR. In the second part of the paper, we consider a Traffic Engineering use case, starting from a traditional flow assignment optimization problem, which allocates hop-by-hop paths to flows. We propose a SR path assignment algorithm and prove that it is optimal with respect to the number of segments allocated to a flow.

The introduction of SDN in large-scale IP provider networks is still an open issue and different solutions have been suggested so far. In this paper, we propose a hybrid approach that allows the coexistence of traditional IP routing with SDN based forwarding within the same provider domain. The solution is called OSHI-Open Source Hybrid IP/SDN networking, as we have fully implemented it combining and extending open source software. We discuss the OSHI system architecture and the design and implementation of advanced services like pseudo wires and virtual switches. In addition, we describe a set of open source management tools for the emulation of the proposed solution using either the Mininet emulator or distributed physical testbeds. We refer to this suite of tools as Mantoo (management tools). Mantoo includes an extensible Web-based graphical topology designer, which provides different layered network “views” (e.g., from physical links to service relationships among nodes). The suite can validate an input topology, automatically deploy it over a Mininet emulator or a distributed SDN testbed and allows access to emulated nodes by opening consoles in the web GUI. Mantoo provides also tools to evaluate the performance of the deployed nodes.

Several Network Operating Systems have been proposed in the last few years for Software Defined Networks; however, only few of them are offering resiliency, scalability and high availability required for production environments. In our demonstration we present a geographically distributed SDN Control Plane, called ICONA, build on top of the Open Networking Operating System (ONOS) and designed to meet the aforementioned Service Providers requirements. During the demo, that runs inside the GEANT OpenFlow pan-european testbed, we show how a Service Provider engineer can easily manage and monitor the network, deploy some services and how ICONA can automatically recover from Control and Data planes failures.

In this paper we propose to integrate Software Defined Networking (SDN) principles in Wireless Mesh Networks (WMN) formed by OpenFlow switches. The use of a centralized network controller and the ability to setup arbitrary paths for data flows make SDN a handy tool to deploy fine-grained traffic engineering algorithms in WMNs. However, centralized control may be harmful in multi-hop radio networks formed by commodity devices (e.g. Wireless Community Networks), in which node isolation and network fragmentation are not rare events. To exploit the pros and mitigate the cons, our framework uses the traditional OpenFlow centralized controller to engineer the routing of data traffic, while it uses a distributed controller based on OLSR to route: i) OpenFlow control traffic, ii) data traffic, in case of central controller failure. We implemented and tested our Wireless Mesh Software Defined Network (wmSDN) showing its applicability to a traffic engineering use-case, in which the controller logic balances outgoing traffic among the Internet gateways of the mesh. Albeit simple, this use case allows showing a possible usage of SDN that improves user performance with respect to the case of a traditional mesh with IP forwarding and OLSR routing. The wmSDN software toolkit is formed by Open vSwitch, POX controller, OLSR daemon and our own Bash and Python scripts. The tests have been carried out in an emulation environment based on Linux Containers, NS3 and CORE tools.

Information Centric Networking (ICN) is a new paradigm in which the network layer provides users with content, instead of providing communication channels between hosts, and is aware of the name (or identifiers) of the contents. In this paper, we first describe what, we believe, are the main advantages and components of an ICN infrastructure; then we present an overall architecture for ICN, and then we focus on the main contribution of the paper, which is a route caching technique, designed to improve the scalability of the routing by name functionality.

The Information-Centric Networking (ICN) paradigm is expected to be one of the major innovation of the Future Internet An ICN can be characterized by some key components like: (i) the content-centric request/reply paradigm for data distribution, (ii) route-by-name operations, and (iii) in-network caching. In this paper we focus on a framework for ICN called CONET (COntent NETwork) and in particular on a solution devised under this framework called coCONET. coCONET characteristics make it suitable for deployment in accordance to the Software Defined Networks (SDN) philosophy. In this paper, we will describe how coCONET can be implemented over an OpenFlow (the most popular SDN instantiation, to date) network and how OpenFlow should be modified to better suit the operations of coCONET and, more in general, of ICN solutions.

In this paper we present a cooperative video streaming application running on top of an “Information Centric Network” (ICN). The application could be used on mobile devices to offload the cellular radio interface. We demonstrate our application in a test-bed exploiting the CCNx software implementation of an ICN, the VideoLan tool and the Apple HTTP Live Streaming format.

In this paper, we provide the performance evaluation of the UPMT (Universal Per-application Mobility management using Tunnels) solution. UPMT offers per-application mobility management, i.e. the capability of separately taking handover decisions for each application. UPMT supports legacy applications, private IP addressing/NATs and it is an overlay solution that does not require the access network to offer any specific support. We have implemented UPMT under Linux OS and made it available under the GPL Open Source license.

In this paper, we propose and evaluate an overlay distribution algorithm for P2P, chunk-based, streaming systems over forest-based topologies. In such systems, the stream is divided in chunks; chunks are delivered by each node in a store-and-forward way. A relaying node starts distributing a chunk only when it has completed its reception from another node. Peers are logically organized in a forest of trees, where each tree includes all peers. The source periodically distributes different chunks to each tree for their delivery. Our key idea consists in employing serial transmission: for each tree, and thus, for each chunk, the source node sends the chunk to its children in series; the same holds for each peer node of the tree, excluding the leaves. Besides this basic idea, the contributions of this paper are: 1) we demonstrate the feasibility of serial transmission over a forest of trees, which is not a trivial problem, unlike the case of parallel transmission; 2) we derive an analytical model to evaluate the system performance; 3) we derive a theoretical bound for the number of nodes reachable in a given time interval or equivalently for the time required to reach a given number of nodes; 4) we prove the optimality of our approach in terms of its capability to reach such bound; and 5) we develop a general simulation package for P2P streaming systems and use it to compare our solution to literature results. Finally, we stress that this paper is focused on the theoretical properties and performance understanding of the proposed distribution algorithm, rather than on its practical implementation in a real system. However, we also briefly describe a practical workable implementation of our algorithm.

Many distribution algorithms have been proposed up to now for P2P real time streaming. However, due to the lack of basic theoretical results and bounds, common sense and intuitions and heuristics have driven their design so far. The consequence is that we can find in the literature a large variety of different choices about the main aspects of a P2P system, such as overlay topology, scheduling process and upload strategy. In this situation, it is difficult to establish unambiguously the absolute goodness of a particular algorithm or even the rationale behind a particular choice or solution. In this paper we propose and evaluate a theory-driven distribution algorithm for P2P real time streaming. We take advantage from a previous theoretical study, where: i) we derived a theoretical performance bound for forest-based overlay topologies regarding the number of nodes reachable in a given time interval or equivalently the time required to reach a given number of nodes; ii) we proved the optimality of streamline, a distribution algorithm based on the serial transmission over forest-based topologies, in terms of its capability to reach such a bound. The streamline algorithm is based on some ideal assumptions that prevent its practical implementation. In this paper we remove these assumptions and present a practical and working algorithm, named operational streamline or simply O-Streamline. We also evaluate the performance of O-Streamline, comparing them with the optimal bounds of streamline.

In this paper we introduce SMILE (simple middleware independent layer), a framework whose main purpose is to facilitate the development of distributed applications. In the SMILE abstraction an application is composed by a set of processes that exchange information. The interfaces of these processes are described using WSDL or by an equivalent UML definition. Using the open source AndroMDA tool and starting from the UML interface specification we are able to generate the skeleton of SMILE applications and most part of their business logic. An application developed using SMILE can run on different middleware platforms just changing its binding, i.e. the code that adapts SMILE to a given middleware. We have implemented bindings to CORBA, JAVA- RMI, JADE, JXTA and to an our own communication mechanism based on SIP suitable for mobile devices. At the end we hint at the usage of SMILE in service composition and present some prototype applications.

In this paper we discuss a methodology for performance evaluation of the solutions for vertical handovers between different wireless access technologies in IP network. The performance evaluation is based on simple analytical models and covers both the ideal case (no packet loss) and the real case where there is a given packet loss rate. The methodology is applied to a comparison among three solutions, namely MIPv4, classical SIP mobility management using re-INVITE messages and a SIP based solution called MMUSE (Mobility Management Using SIP Extensions) proposed by the authors.

Abstract The 3GPP architecture includes the Multimedia Broadcast Multicast Service (MBMS) to provide efficient broadcast and multicast services. In the 3GPP long‐term evolution, the evolved MBMS (e‐MBMS) architecture is currently being standardized. Unlike MBMS, the new e‐MBMS architecture explicitly raises, as additional security requirement, the protection of the IP multicast user plane. Currently proposed e‐MBMS security architectures “limit” themselves to suggest the deployment of Group Security Associations (GSA). In this paper, we start by discussing that, on one side, GSA might not be a sufficiently secure solution in the long run, and on the other side GSA integration within the e‐MBMS architecture might not be as straightforward as it might appear. The point made in this paper is that there are sound alternatives to GSA if the goal is to deploy a short‐term solution with basically no impact on the current e‐MBMS architecture. In particular, we propose to adopt a Secure Multicast Overlay (SMO) approach. To prove the straightforward implementation of SMO we describe how a proof‐of‐concept test‐bed over public domain linux routers. Moreover, a functional comparison between GSA and SMO leads us to the following conclusions: (i) not only SMO provides the same level of security of GSA, but also it achieves a reduced risk of denial of service attacks; (ii) SMO has significant advantages over GSA in terms of impact on the architecture and on device requirements; (iii) security association management and key management in GSA has a greater impact on the performance achievable than in the case of SMO. We believe that these advantages outweigh the performance penalties due to overlay networking overhead. Copyright © 2008 John Wiley & Sons, Ltd.

The actual standards for service authoring, composition and development are not easy to port and to apply for next generation mobile applications. This paper describes some tools that we're developing in the context of the IST-Simple Mobile Service project, whose aim is to ease the authoring and the use of services for mobile devices. We propose a service composition approach using an UML profile very close to the actual standards for Web services definition and authoring, like WSDL and BPEL. We take a glance at SMILE, the run-time support we provide for service execution. Finally we hint at an efficient serialization mechanism based on JSON, a human readable data exchange format less verbose and, in our opinion, more suitable for mobile terminals than XML.

In this paper, we study the problem of maintaining fairness for TCP connections in wireless local area networks (WLANs), based upon the IEEE 802.11 standard and operating in DCF mode. Although this mode of operation ensures fair access to the medium at the MAC level, it does not provide fairness among TCP connections. TCP unfairness may result in significant degradation of performance, leading to users perceiving unsatisfactory quality of service. We propose and analyze a solution capable of enabling TCP fairness with minimal additional complexity. The proposed solution is based on utilizing an IP rate-limiter with an adaptive rate control mechanism and does not require modifying existing standards at the MAC or network layers. The solution is fully compatible with existing devices and can be integrated either within the access point or within and external device (e.g., the network gateway). The performance analysis is performed in a real test-bed and proves the feasibility and effectiveness of our mechanism. To allow fellow researchers to reproduce our work we published on the WEB all the implementation code.

In this paper, we study the problem of maintaining fairness for TCP connections in wireless local area networks (WLANs) based upon the IEEE 802.11 standard. Current implementations of 802.11 use the so-called distributed coordination function (DCF), which provides similar medium access priority to all stations. Although this mode of operation ensures fair access to the medium at the MAC level, it does not provide any provisions for ensuring fairness among the TCP connections. TCP unfairness may result in significant degradation of performance leading to users perceiving unsatisfactory quality of service. We propose and analyze two solutions that are capable of enabling TCP fairness with minimal additional complexity. The proposed solutions are based on utilizing a rate-control mechanism in two modes: static or adaptive. They do not require modifying existing standards at the MAC or network layers. Hence, they are fully compatible with existing devices. Our performance analysis results prove the efficaciousness of our proposed solutions in achieving TCP fairness compared to existing approaches. We have, also, implemented the proposed solutions in an ad-hoc experimental test-bed, and performed measurements to demonstrate the validity of our approach and results

As technology develops, people are using an ever broader and heterogeneous range of ICT devices and network-based services. The result is an enormous burden of complexity on the shoulders of users, service providers and network operators. The goal of the Simplicity project, supported by the European Union, is to reduce this complexity by: (i) providing automatic customization of user access to services and the network; (ii) automatically adapting services to terminal characteristics and user preferences; (iii) orchestrating network capabilities. The Simplicity approach is based on a personalization device, the so-called Simplicity device, which, together with a brokerage framework, offers transparent service configuration and runtime adaptation, according to user preferences and computing/networking context conditions. This paper presents the Simplicity project, briefly discusses its architecture and introduces the Simplicity demonstrator: a proof of concept implementation used to verify our approach, through diverse usage scenarios. In addition, we introduce the main aspects of a follow-up project of Simplicity, named SMS.

High data rate wireless networks enables the provisioning of real time services to mobile devices over IP. At the same time, the different nature of the adopted radio technologies (802.11/WiFi, Bluetooth, 2.5G/3G networks) has introduced the problems of supporting seamless communication across these heterogeneous wireless accesses, which is a goal for 4G network. This paper describes a Session Initiation Protocol (SIP) based solution for mobility management aiming to provide seamless voice service in this heterogeneous scenario. The novelty of the solution is that it relies on the so called "Session Border Controllers" which are currently used in commercial SIP telephony solutions to deal with NAT traversal. A prototype of the proposed solution has been implemented in a test bed where the 802.11 and 3G (UMTS) technologies have been used respectively as typical WLAN and cellurar access networks. Measurements results are reported which analyze the performance of the solution in a real world environment, using commercial WiFi and 3G services.

In WLANs, secure access can be provided operating at link layer, at network layer (IP) or at application level, and several solutions have been implemented in current public/private access networks; however most of them are proprietary and the interworking between different operators is still an open issue. At the same time, the 3GPP is working in integrating the WLAN access with the rest of 3GPP/UMTS network infrastructure. In this paper we propose a generic layer-two-independent open solution for secure authentication in a heterogeneous wireless access scenario based on 3G SIM credentials and on the SIP protocol. The solution follows the 3G specification for the authentication in the IMS, with the only addition of a new parameter in a specific header of the SIP protocol. Therefore the security infrastructure of the 3G networks can be fully reused also in scenarios in which the visited network does not provide 3G services. The proposed solution has been implemented in a testbed in which UMTS, 802.11, and Bluetooth has been used as access technologies.

Reconfigurable radio systems allow user terminals to access different communication technologies, without duplication of hardware. To this end, terminals need appropriate software (SW) modules, which, in advanced scenarios, can be downloaded on demand from the network. The network element that provides these modules to the terminals may need to know information about the terminal/user, in order to better adapt the SW modules to user needs and terminal capabilities and to grant only requests coming from authorized users. For this reason, such network element needs to access user profile information. In this paper, we propose a distributed approach to retrieve users profile information that does not require the mandatory presence of a public network operator. The goal of this mechanism is to allow a suitably appointed entity to retrieve all the needed information, related to the user/terminal, from a suitable location/server in the network, given some information provided by the terminal itself. Our approach is based on the "Dataweb" paradigm, under standardization in the Oasis consortium

Despite its recent release, the mobile agent JADE platform is attracting the scientific community attention for its effective and seamless portability. Unlike most of the JADE research efforts, which have so far focused mainly on the agent framework architecture and on the technical design issues, this paper aims at showing JADE performance measurements. First, we assess the effect of two different factors, the operating system and the execution environment, on the container start up operations. A statistical approach based on the ANOVA analysis has been followed. Second, we investigate JADE scalability with specific reference to the agent migration and the interaction with FIPA agents

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.

This paper describes a solution for the Intserv operations over Diffserv network, based on the use of a bandwidth broker for the resource allocation. The architectural scenario is described, which is based on the current IETF work in this area. For the communication of the admission control request to the bandwidth broker, the use of COPS protocol is proposed and the detailed protocol specifications have been given. In particular, a new client type for the COPS protocol is proposed to support dynamic Diffserv admission control. The policy decision point (PDP) acts as a "bandwidth broker" for the policy enforcement point (PEP) which is requesting resources. The use of the defined mechanism is suited for (but it is not limited to) the integrated services operation over Diffserv networks. The proposed model has been implemented in a test-bed, where both the control plane and the data plane are realized according to the specification.

The integration of voice, data, and video services modified the target of networking technologies. Now, instead of simply providing best effort delivery, the network has also to address integration of services and quality of service (QoS) support. The applications should be therefore provided with means to describe the service they want to receive from the network. In the Internet, two major mechanisms have been studied and developed: Integrated Services and Differentiated Services. Combining Integrated Services (R. Braden et al., 1994), QoS mechanisms for end-to-end signaling at hosts and Differentiated Services (S. Blake et al., 1998), QoS mechanisms in the network core is one proposal for overcoming the limitation of either mechanisms when applied alone (Y. Bernet et al., 1999). Some of the open issues of Y. Bernet et al. are discussed and a concrete proposal is presented, which maps the IntServ Controlled Load Service into the DiffServ Expedited Forwarding "Per Hop Behavior". The proposed approach has been implemented under the Linux operating system. The implementation allows verifying of the correct functional behavior and provides a platform where more complete performance tests are possible.

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.