Diego Reforgiato

Measuring and modeling energy consumption to design a green NetFPGA giga-router

One of the most weighty matter in the Internet today is the waste of energy due to the fact that consumption of network nodes is not tuned with the input traffic. For this reason, the implementation of rate adaptation facilities in the routers constitutes a challenging problem to make the network energy efficient. Rate adaptation in the green routers is usually achieved by scaling the processing power according to the data rate the router has to manage; at this purpose the clock frequency driving the router processes can be modified according to the input data rate. In this context this paper, starting from a measurement study of the Reference Router implemented on the NetFPGA platform, defines a model of the consumed power as a function of both the managed input traffic and the available clock frequencies. As demonstrated in the paper, the model can be applied by router designers to choose the main router platform parameters, i.e. the number of clock frequencies and the clock frequency switching time, while respecting a given tradeoff between the percentage of energy saved and the maximum tolerated loss probability due to frequency switch.

A northbound interface for power management in next generation network devices

Recently, a number of approaches based on dynamic power management techniques have been proposed to reduce the energy consumption of telecommunication networks and devices. They are able to optimize the trade-off between network performance and energy requirements. It is possible to execute and extend these techniques to the whole network, by using local control policies together with energy-aware routing and traffic engineering. However, the lack of a standardized representation of the energy-aware capabilities of heterogeneous networking equipment makes their deployment confusing and impractical. To this aim, we have proposed a novel framework, the green abstraction layer (GAL), whose purpose is to define a multi-layered abstraction interface for the hardware and physical resources, where energy management actions are directly performed. Therefore, the GAL syntax can be exposed to the platform-independent logical representation commonly used in network control protocols. Given the internal architectural complexity and heterogeneity of many network devices, the GAL approach is based on a hierarchical decomposition, where each level provides an abstract and aggregated representation of internal components.

Exporting data-plane energy-aware capabilities from network devices toward the control plane: The Green Abstraction Layer

Energy efficiency is well-known to have recently become one of the most important aspects for both todays and tomorrows telecommunications infrastructures. To curb their energy requirements, next-generation hardware platforms of network devices are expected to include advanced power management capabilities, which may allow a dynamic trade-off between power consumption and network performance. At the same time, network protocols are going to evolve in order to carry energy-aware information, and to add them to classical performance indexes in network optimisation strategies. However, the question of how to map energy-aware indexes, often arising from low-level local hardware details, and the ones related to network performance is still an open issue. Starting from these considerations, we propose the Green Abstraction Layer (GAL), a device internal interface that provides a standard way of accessing and organising energy-aware information from the low-level hardware components to control processes. The GAL is specifically designed to hide the heterogeneous hardware implementation details, and to provide a simple, hierarchical, and common view of underlying power management capabilities to network control processes.

GraphClust: A Method for Clustering Database of Graphs

Any application that represents data as sets of graphs may benefit from the discovery of relationships among those graphs. To do this in an unsupervised fashion requires the ability to find graphs that are similar to one another. That is the purpose of GraphClust. The GraphClust algorithm proceeds in three phases, often building on other tools:(1) it finds highly connected substructures in each graph;(2) it uses those substructures to represent each graph as a feature vector; and(3) it clusters these feature vectors using a standard distance measure. We validate the cluster quality by using the Silhouette method. In addition to clustering graphs, GraphClust uses SVD decomposition to find frequently co-occurring connected substructures. The main novelty of GraphClust compared to previous methods is that it is application-independent and scalable to many large graphs.

P2P and MPEG FGS Encoding: A Good Recipe for Multipoint Video Transmission on the Internet

In the last years Peer-to-Peer (P2P) systems have gained ground for content sharing between communities, determining a real revolution on the Internet. The characteristics of P2P systems make them a very good choice for multimedia content distribution over IP networks. However, although P2P technology gives new opportunities to define an efficient multimedia streaming application, at the same time it involves a set of technical challenges and issues due to the best-effort service offered by the Internet and its dynamic and heterogeneous nature. The most of existent protocols for video communications over P2P mainly focus on tree topology maintenance, without paying any attention to the encoding problem. The idea of this paper is to propose a multipoint video broadcast framework over a heterogeneous content distribution P2P network. In the proposed system the source generates the video flow by using an MPEG-4/FGS encoder, in such a way that no losses occur at the Baselayer stream even in the presence of short-term bandwidth fluctuations. Although in the past the FGS was not employed due to its encoding complexity, today, thanks to advances in hardware technology, we were able to develop an MPEG-4/FGS encoder on low-cost PCs which turned out to be more feasible and appealing for its flexibility. The FGS layer is sent together with the Base layer, but with a lower priority. The source uses a rate controller to regulate the encoding rate of the Base layer. To this aim, a protocol is defined in order to provide the source with information related to the most stringent bottleneck link on the overlay network. A technique to reorganize the content distribution tree is proposed and discussed. To evaluate the performance of the proposed framework a case study is introduced; improvements obtained with respect to several reference cases where FGS is not applied are also shown.

A Module for Packet Hijacking in NetFPGA Platform

The reference router implementation on the Net FPGA platform has been changed in order to hijack the incoming packets according to rules specified by the user through Net FPGA registers. This means that we are able to change any field of any incoming packets, of course, depending on whether we are changing TCP or IP header fields, we need to recompute the TCP or IP checksum and store them back into the packets. It might be useful to change information of the IP or TCP header or the data itself. For example, we could crypto the data, change the URL address in order to point to the desired web site or for URL filtering, change the priority information of a bunch of data, and much more. Our implementation works at user data path level and modifies packet fields if certain conditions defined by the user through Net FPGA registers are satisfied. The project has been implemented as a fully open-source project and serves as an exemplar project on how to build and distribute Net FPGA applications. All the code (Verilog, system software, graphical user interface, verification scripts, make files, and support tools) can be freely downloaded from the Net FPGA.org website.

Modeling temperature and dissipation behavior of an open multi-frequency green router

Development of green routers aimed at saving energy when the input traffic is low has the positive side effect of reducing the working temperature of their internal components. This idea can encourage the realization of smaller scale routers, but this process has to be supported by the confidence that temperature remains in a given range. For this reason, the target of this paper is to propose an analytical discrete-time Markov model that helps green router designers to calculate in advance the temperature statistics of a router, for given input traffic statistics and energy saving law applied by the router Governor, which is an entity which decides the router policy to be adopted. At the same time the model evaluates the obtained energy saving gain. The proposed model is applied to a case study to show how it can be used to support the design of the router Governor parameters to achieve the target of maintaining the mean temperature below a given threshold.

A banner recommendation system based on web navigation history

We address the problem of selecting a banner advertisement, based on the profile of the online user. The profile consists of the set of webpages opened by the online user, optionally clustered.

A comprehensive platform to manage peer churn and bandwidth fluctuations in real-time multimedia P2P networks

In the last few years, new service providers are growing in the Internet scenario to create new multimedia services. The most common approach to this end is based on peer-to-peer (P2P) networks. The new service providers are manifesting great interest not only for classical multimedia applications, like video streaming and video on demand, but also for multi-party games, private video-chat rooms, videoconference and real-time video teaching, usually containing a small number of high-interactive group members. The target of this paper is to define a multipoint multimedia communication platform for such kind of applications, accounting both peer set variation (peer arrivals and departures) and peer bandwidth modifications. In addition, a revenue model for providers of this kind of services is proposed to allow them to design their networks in order to maximize their revenue while satisfying user requirements in terms of both admission rejection probability and perceived quality on the received video stream.

Design of a service platform for delay-sensitive video streaming applications based on multicast p2p and scalable MDC encoding

The great diffusion of Internet accesses in the world and the enormous evolution of the Internet technologies have strongly determined dissemination and consolidation of many applications of video content distribution. However, multicast real-time video communications for interactive service applications with a very high number of users, like for example multipoint videoconferences and interactive video games, remains a challenging research topic for the presence of very strict requirements in terms of end-to-end delay and perceived quality. The target of this paper is to propose a video distribution platform that is able to provide a huge number of users with a delay constrained multicast video streaming. To this purpose, the proposed content delivery platform is based on a peer-to-peer approach that exploits multicast overlay organization of the peers to address the challenges due to bandwidth heterogeneity. To improve reliability and flexibility, video is coded using a scalable multiple description approach. Some design guidelines are provided taking into account some requirements in terms of delay, average PSNR, robustness against underlying network bandwidth fluctuations, and fairness.