Achille Pattavina

Politecnico di Milano, Milano, Lombardy, Italy

Are you Achille Pattavina?

Claim your profile

Publications (278)168.79 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Cost minimization is a major concern in data center networks (DCNs). Existing DCNs generally adopt Clos network with crossbar middle switches to achieve non-blocking data switching among the servers, and the number of middle switches is proportional to the number of ports of the aggregation switches in a fixed manner. Besides, reconfiguration overhead of the switches is generally ignored, which may contradict the engineering practice. In this paper, we consider batch scheduling based packet switching in DCNs with reconfiguration overhead at each middle switch, which inevitably leads to packet delay. With existing state-of-the-art traffic matrix decomposition algorithms, we can generate a set of permutations, each of which stands for the configuration of a middle switch. By reconfiguring each middle switch to fulfill multiple configurations in parallel with others, we reveal that a tradeoff exists between packet delay and switch cost (denoted by the number of middle switches), while performance guaranteed switching with bounded packet delay can be achieved without any packet loss. Based on the tradeoff, we can minimize the number of middle switches (under a given packet delay bound) and an overall cost metric (by translating delay into a comparable cost factor), as well as formulating criteria for choosing a proper matrix decomposition algorithm. This provides a flexible way to reduce the number of middle switches by slightly enlarging the packet delay bound.
    Computer Networks 05/2015; DOI:10.1016/j.comnet.2015.05.010 · 1.28 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Long-Reach Passive Optical Network (LR-PON) using hybrid TDM/WDM techniques is one of the candidates for the future optical access that can solve the expected increase in terms of traffic demand and area coverage. One of its advantages is the possibility to share the capacity of any wavelength among more than one user, through TDM/WDM hybrid multiplexing. However, it is still an open issue which transmission technology (DWDM transmitters, colorless transmitters, coherent detection, direct detection) can more effectively satisfy the requirements and characteristics of the future long-reach access network. In this article we propose a new optimization model based on Mixed Integer Linear Programming (MILP) that formalizes the problem of selecting the most cost-effective transmission technology in LR TDM/WDM PONs while also assigning the wavelength-channels line rate and the splitting ratio of the remote nodes at different levels, under bandwidth and power budget constraints. Using this proposed MILP formulation we can identify the optimal transmission technology for a wide set of possible LR-PON scenarios of interest. In this work we provide an evaluation of the optimal transmission technologies under several PON scenarios with varying traffic loads and area coverage. We also analyze the cost sensitivity of the optimization process for coherent-detection technology since it is still under research and development.
    Optical Switching and Networking 04/2015; 16:36-45. DOI:10.1016/j.osn.2014.11.001 · 0.91 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: While telecommunication networks have historically been dominated by a circuit-switched paradigm, the last decades have seen a clear trend towards packet-switched networks. In this paper we evaluate how both paradigms (which have also been referred to as optical bypass and non-bypass, respectively) perform in optical backbone networks from a power consumption point of view, and whether the general agreement of circuit switching being more power-efficient holds. We consider artificially generated topologies of various sizes, mesh degrees and - not yet previously explored in this context - transport linerates. We cross-validate our findings with a number of realistic topologies.
    Computer Networks 02/2015; 78:42-56. DOI:10.1016/j.comnet.2014.09.015 · 1.28 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Energy efficiency and resilience are two well established research topics in optical transport networks. However, their overall objectives (i.e., power minimization and resource utilization/ availability maximization) conflict. In fact, provisioning schemes optimized for best resilience performance are in most cases not energy-efficient in their operations, and vice versa. However, very few works in the literature consider the interesting issues that may arise when energy efficiency and resilience are combined in the same networking solution. The objective of this article is to identify a number of research challenges and trade-offs for the design of energy-efficient and resilient optical transport networks from the perspective of long-term traffic forecasts, short-term traffic dynamics, and service level agreement requirements. We support the challenges with justifying numbers based on lessons learned from our previous work. The article also discusses suitable metrics for energy efficiency and resilience evaluation, in addition to a number of steps that need to be taken at the standardization level to incorporate energy efficiency into already existing and well established protocols.
    IEEE Communications Magazine 02/2015; 53(2-2):144-150. DOI:10.1109/MCOM.2015.7045403 · 4.46 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Today's growth in the demand for access band-width is driven by the success of the Video-on-Demand (VoD) bandwidth-consuming service. At the current pace at which network operators increase the end users' access bandwidth, and with the current network infrastructure, a large amount of video traffic is expected to flood the core/metro segments of the network in the near future, with the consequent risk of congestion and network disruption. There is a growing body of research studying the migration of content towards the users. Further, the current trend towards the integration of metro and access segments of the network makes it possible to deploy Metro Servers (MSes) that may serve video content directly from the novel integrated metro/access segment to keep the VoD traffic as local as possible. This paper investigates a potential risk of this solution, which is the increase in the overall network energy consumption. First, we identify a detailed power model for network equipment and MSes, accounting for fixed and load-proportional contributions. Then, we define a novel strategy for controlling whether to switch MSes and network interfaces on and off so as to strike a balance between the energy consumption for content transport through the network and the energy consumption for processing and storage in the MSes. By means of simulations and taking into account real values for the equipment power consumption, we show that our strategy is effective in providing the least energy consumption for any given traffic load.
    IEEE LatinCom 2014; 11/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Energy efficiency is expected to be a key design parameter for next-generation access/aggregation networks. Using a single network infrastructure to aggregate/backhaul both mobile and fixed network traffic, typically referred to as fixed/mobile convergence (FMC), seems a promising strategy to pursue energy efficiency. WDM networks are a prominent candidate to support next-generation FMC network architectures, as they provide huge capacity at relatively low costs and energy consumption. We consider a FMC WDM aggregation network in which the novel concept of “hotelling” of mobile baseband units (BBUs) is employed. The so-called BBU hotelling consists in separating BBUs from their cell sites and consolidating them in single locations, called hotels. As a result, the aggregation network will transport both IP (fixed and mobile) traffic and CPRI (fronthaul) traffic, the latter exchanged between each BBU and its cell site. In this paper, we propose an energy-efficient WDM aggregation network, and we formally define the BBU placement optimization problem, whose objective is to minimize the defined aggregation infrastructure power (AIP). We consider three different network architectures: Bypass, Opaque, and No-Hotel, which feature different placement of BBUs and routing of traffic. By modeling the power contributions of each active device, we study how and how much BBU consolidation, optical bypass, and active traffic aggregation influence the AIP, for all the three architectures. Our results show that, in our case study, the proposed architectures enable savings up to about 60%–65% in dense-urban/urban and about 40% in rural scenarios.
    IEEE Journal on Selected Areas in Communications 08/2014; 32(8):1542-1551. DOI:10.1109/JSAC.2014.2335071 · 4.14 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We are currently facing two major challenges for the development of future photonic networks: scalability and cost/energy efficiency. The process of evaluating the impact on the network of the expected increase of traffic demand is called scalability analysis. It is one of the most important tasks for a network designer, along with minimizing energy consumption and cost. In this paper, we propose a novel approach to assess Wavelength Switched Optical Network (WSON) scalability and efficiency. Our method takes into account the routing constraints of Reconfigurable Optical Add/Drop Multiplexers (ROADMs), a variety of coherent transmission systems, different amplification schemes and types of fibre. We have assessed the network scalability and the roadmap for technological upgrades by running simulations of the recently deployed Telecom Italia’s WSON Kaleidon. We have used realistic traffic profiles and traffic growth-rate projections under a variety of case studies of practical interest. This study provides an innovative tool and insights to drive network designers’ decisions based on the impact of present and future photonic technologies.
    Journal of Lightwave Technology 06/2014; 32(12):1-1. DOI:10.1109/JLT.2014.2315759 · 2.86 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cloud services are fundamentally supported by data center networks (DCNs). With the fast growth of cloud services, the scale of DCNs is increasing rapidly, leading to great concern about system scalability due to multiple constraints. This paper proposes a scalable DCN architecture based on optical switching and transmission, with the distributed placement of optical switches and server racks at different nodes in a given optical network. This solves the scalability issue by relaxing power and cooling constraints and by reducing the number of (electronic) switches using high-capacity optical switches, as well as by simplifying DCN internal connections using wavelengths in the optical network. Moreover, the distributed optical switches provide service access interfaces to meet demand within areas, and thus reduce the transmission cost of the external traffic. The major concern is the additional delay and cost for remote transmissions of the DCN internal traffic. To this end, we study the component placement problem in DCNs under a given set of external demands and internal traffic patterns. By leveraging among multiple conflicting factors such as scalability and internal overhead of the DCN as well as the transmission cost of external traffic, we propose both an integer linear program and a heuristic to minimize the system cost of a DCN while satisfying all service demands in the network. This addresses both scalability and cost minimization issues from a network point of view.
    Journal of Optical Communications and Networking 03/2014; 6(3):270-281. DOI:10.1364/JOCN.6.000270 · 1.55 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Cloud Computing (CC) services are rapidly catching on as an alternative to conventional office-based computing. As cloud computing adoption increases, the energy consumption of the network and of the computing resources that underpin the cloud is growing and causing the emission of enormous quantities of CO2. Research is now focusing on novel "low-carbon" cloud-computing solutions. Renewable energy sources are emerging as a promising solution both to achieve drastic reduction in CO2 emissions and to cope with the growing power requirements of data centers. These infrastructures can be located near renewable energy plants and data can be effectively transferred to these locations via reconfigurable optical networks, based on the principle that data can be moved more efficiently than electricity. This paper focuses on how to dynamically route on-demand optical circuits that are established to transfer energy-intensive data processing towards data centers powered with renewable energy. Our main contribution consists in devising two routing algorithms for connections supporting CC services, aimed at minimizing the CO2 emissions of data centers by following the current availability of renewable energies (e.g., coming from sun and wind). The trade-off with energy consumption for the transport equipments is considered. We also compare three different IP-over-WDM network architectures. The results show that relevant reductions, up to about 30% in CO2 emissions can be achieved using our approaches compared to baseline shortest-path-based routing strategies, paying off only a marginal increase in terms of network blocking probability.
    IEEE Journal on Selected Areas in Communications 01/2014; 32(1):28-38. DOI:10.1109/JSAC.2014.140104 · 4.14 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: While telecommunication networks have historically been dominated by a circuit-switched paradigm, the last decades have seen a clear trend towards packet-switched networks. In this paper we evaluate how both paradigms perform in optical backbone networks from a power consumption point of view, and whether the general agreement of circuit switching being more power-efficient holds. We consider artificially generated topologies of various sizes, mesh degrees and-not yet previously explored in this context-transport linerates. We cross-validate our findings with a number of realistic topologies. Our results show that, as a generalization, packet switching can become preferable when the traffic demands are lower than half the transport linerate. We find that an increase in the network node count does not consistently increase the energy savings of circuit switching over packet switching, but is heavily influenced by the mesh degree and (to a minor extent) by the average link length.
    Proc. of the OnlineGreenComm, online conference; 10/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Future passive optical networks (PONs) are expected to support much larger capacity and much wider coverage. How to jointly address these two design requirements represents one of the most challenging aspects in today's research on PONs. So far, most research efforts have been devoted to devising new architectural or technological solutionsto support such stringent requirements. In particular, the technology to be used for transmission may have diverse multiplexing techniques, types of transceivers, modulation formats, and detection techniques. However, the question of which transmission technology is the most effective considering the trade-offs in terms of complexity, offered capacity, and reach is still open. In this paper, we aim at answering this question comparing the use of time division multiplexing (TDM), wavelength division multiplexing (WDM), and hybrid TDM/WDM techniques in PONs. To achieve this goal, we first categorize the main options for transmission technologies in PONs in three families: colored dense WDM (DWDM), tunable DWDM, and colorless DWDM. Then, we propose a new optimization scheme that selects the optimal transmission technology for different operational scenarios that are defined by varying the number of users, the distance to the users, and the traffic load. The choice of the passive optical components to be used at the remote node is also part of the optimization scheme given its significant impact on the choiceof the transmission technology. As a result, we report and discuss which transmission technologies are the most suitable under different operational scenarios.
    Journal of Optical Communications and Networking 09/2013; 5(9):1010-1020. DOI:10.1364/JOCN.5.001010 · 1.55 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The quest of extended optical reach has been one of the major drivers for the transmission systems research field. Since extending the optical reach does not come for free and that reducing the power consumption has become a mandatory task for network designers, we investigate IP-over-WDM network power consumption as a function of 100 Gb/s Transponders' (TXP) transmission reach. In order to achieve this target, we propose a novel analytical model that captures the increase of TXP power consumption versus its optical reach. Network design is performed via a Mixed Integer Linear Programming (MILP) optimization engine. We have used two Multi-Layer design strategies, the Bypass (Bp) and the Direct-Bypass (DBp), that we have both applied to the “All-On” and the “On-Off” planning approaches: the former considers that transmission devices are always on and provides an upper bound to the network power consumption whereas the latter maximizes power savings by switching network devices On-Off according to daily traffic variations. Finally, simulations on a European-like backbone network show that there exists an optical reach that leads to a minimum network power consumption, the so-called optimal reach. By performing network design at the optimal reach we can achieve up to 36% and 37% of energy savings with respect to an extended reach-based design in the All-On and in the On-Off planning respectively.
    Journal of Lightwave Technology 06/2013; 31(11):1828-1834. DOI:10.1109/JLT.2013.2259799 · 2.86 Impact Factor
  • Fotonica 2013; 05/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: For decades, optical networks have provided larger bandwidths than could be utilized, but with the increasing growth of the global Internet traffic demand, new optical transmission technologies are required to provide a much higher data rate per channel and to enable more flexibility in the allocation of traffic flow. Currently, researchers are investigating innovative transceiver architectures capable of dynamically adapting the modulation format to the transmission link properties. These transceivers are referred to as elastic and enable flexible allocation of optical bandwidth resources. To exploit their capabilities, the conventional fixed spectrum grid has to evolve to provide a more scalable and flexible system that can provide the spectral resources requireded to serve the client demand. The benefits of elastic transceivers with distance-adaptive data rates have been evaluated in optical core networks, but their application to metro ring networks has still not been addressed. This paper proposes methods based on integer linear programs and heuristic approaches to solve the routing, modulation level, and spectrum assignment problem in optical rings with elastic transceivers and rate-adaptive modulation formats. Moreover, we discuss how to analytically compute feasible solutions that provide useful upper bounds. Results show a significant reduction in terms of transceiver utilization and spectrum occupation.
    Journal of Optical Communications and Networking 04/2013; 5(4):305-315. DOI:10.1364/JOCN.5.000305 · 1.55 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Novel distance-adaptive optical transmission technologies have been proposed to boost transceiver datarates and to enable more flexibility in the allocation of traffic flows. The application of this new class of transceivers is being widely investigated in core networks, while their suitability in the metro area is still an open issue. On one hand, the short metro distances enable the utilization of higher spectrally efficient modulation formats, on the other hand, the lower bitrate suggests to employ lower baud rate with respect to core networks. In this letter, we perform traffic grooming and spectrum assignment using transceivers with fixed baud rate of 28 and 14 GBd and distance-adaptive modulation formats in optical metro networks. Comparisons with the wavelength-division multiplexing systems running over a fixed grid show that 1) significant savings in terms of spectrum occupation can be achieved, and that 2) such savings can be effectively achieved also using lower baud rate transceivers (e.g., 14 GBd).
    IEEE Photonics Technology Letters 01/2013; 25(2):183-186. DOI:10.1109/LPT.2012.2228479 · 2.18 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Recently, the need for energy-efficient and sustainable capacity growth has become stringent for telecommunication networks and great efforts have been produced to reduce their power consumption. Optical technologies based on Wavelength Division Multiplexing are well-recognized as a promising solution for greening the future Internet. One relevant approach to achieve such power savings consists in aggregating traffic flows in few network links, so that power can be saved by switching-off some unused network devices. However, the need to ensure network resiliency against link and/or node failures imposes that still the resources reserved to protect connections become available immediately after a failure occurs. Therefore, a possible solution is to set some devices into low-power sleep-mode, so that they can be rapidly re-activated and provide fast connection recovery.In this paper we focus on the power-efficiency of protected IP-over-WDM networks and provide a comprehensive comparison of four different protection strategies, namely Shared-Link, Shared-Path, Dedicated-Link and Dedicated-Path Protection SLP, SPP, DLP and DPP respectively in a sleep-mode scenario. In the proposed design strategies we assume that low-power sleep-mode is enabled for devices used for protection. Mathematical models for a power-aware design with sleep-mode is proposed for the four protection strategies. We show that relevant power savings up to about 60% can be obtained for all the protection strategies by setting protection devices into sleep-mode.
    Journal of High Speed Networks 01/2013; 19(1):19-32. · 0.38 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Data center networks (DCNs) generally adopt Clos network with crossbar middle switches to achieve non-blocking data switching among the servers, and the number of middle switches is proportional to the number of ports of the aggregation switches in a fixed manner. Besides, reconfiguration overhead of the switches is generally ignored, which may contradict the engineering practice. In this paper, we consider batch scheduling based packet switching in DCNs with reconfiguration overhead at each middle switch, which inevitably leads to packet delay. With existing state-of-the-art traffic matrix decomposition algorithms, we can generate a set of permutations, each of which stands for the configuration of a middle switch. By reconfiguring each middle switch to fulfill multiple configurations in parallel with others, we reveal that a tradeoff exists between packet delay and switch cost (denoted by the number of middle switches), while performance guaranteed switching with bounded packet delay can be achieved without any packet loss. Based on the tradeoff, we can minimize the number of middle switches (under a given packet delay bound) and an overall cost metric (by translating delay into a comparable cost factor), as well as formulating criterions for choosing a matrix decomposition algorithm. This provides a flexible way to reduce the number of middle switches by slightly enlarging the packet delay bound.
    High Performance Switching and Routing (HPSR), 2013 IEEE 14th International Conference on; 01/2013
  • D.G. Garao, Guido Maier, Achille Pattavina
    [Show abstract] [Hide abstract]
    ABSTRACT: Future switching and interconnection fabrics inside switching equipment, high-performance computers and datacenters will require more throughput and more energy efficiency. Optical technology provides many opportunities of improvement of both features compared to electronic counterparts. This work defines a procedure to design the architecture of optical multistage switching networks. Modularity of the implementation is the primary concern, allowing for the construction of a genericsize fabric by the simple cascading of multiple stage-modules. In this paper we show in details the application of the approach to a family of banyan networks. The designed architecture can be exploited for various implementation technologies, as, for instance, integrated optics with micro-ring resonators, free-space optics with 2-D MEMS, networks on chip.
    INFOCOM, 2013 Proceedings IEEE; 01/2013
  • D.G. Garao, G. Maier, A. Pattavina
    [Show abstract] [Hide abstract]
    ABSTRACT: Interconnection systems inside switching equipment, high-performance computers and data-centers are nowadays facing more and more demanding requirements. Optical interconnections based on multistage switching networks provide more bandwidth and less energy consumption compared to electronic counterparts. In this work a procedure to design the architecture of optical multistage switching networks is proposed which exploits the properties of multistage networks, on one side, and of optical switching systems on the other side. Thanks to the modularity of the architecture, a generic-size fabric can be implemented by simply cascading multiple stage-modules. In this paper we show in details the application of the approach to the Extended Generalized Shuffle (EGS) networks, though the method can be extended to other types of networks. The proposed procedure supports various implementation technologies, as, for example, integrated optics with micro-ring resonators, free- space optics with 2-D MEMS, networks on chip.
    Computer Communications and Networks (ICCCN), 2013 22nd International Conference on; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: The ever-increasing Internet traffic demand introduces new challenges for telecommunications carriers. Telecom networks will have to be upgraded to cope with the new capacity requirements. However, deploying enough capacity is not the only requirement for network operators. The impact of new technologies in terms of capital investment and energy consumption becomes a key issue. There is a special interest in investigating new mechanisms and technologies to improve the energy efficiency of future networks, while maintaining the high reliability and service availability of current optical transport networks. This article evaluates the energy- and cost-efficiency of an innovative flexible-grid orthogonal-frequency-division-multiplexing (OFDM) -based network and compares them with those for conventional wavelength-division-multiplexing (WDM) networks. Due to the importance of resilience in optical transport networks, the study considers and evaluates different protection schemes. The results demonstrate the potential energy efficiency improvements that can be achieved by an elastic OFDM-based technology, especially when a shared protection scheme is adopted, and give an insight into the potential cost benefits that such a novel technology can offer to telecommunication carriers.
    Optical Switching and Networking 01/2013; 11. DOI:10.1016/j.osn.2013.08.005 · 0.91 Impact Factor

Publication Stats

2k Citations
168.79 Total Impact Points

Institutions

  • 1–2015
    • Politecnico di Milano
      • • Department of Electronics, Information, and Bioengineering
      • • Department of Electrical Engineering
      Milano, Lombardy, Italy
  • 2011
    • CTTC Catalan Telecommunications Technology Centre
      Barcino, Catalonia, Spain
  • 2010
    • Alcatel Lucent
      Lutetia Parisorum, Île-de-France, France
  • 2007–2009
    • University of California, Davis
      • Department of Computer Science
      Davis, CA, United States
  • 2008
    • ParisTech
      Lutetia Parisorum, Île-de-France, France
  • 2007–2008
    • Tohoku University
      • Graduate School of Information Sciences
      Miyagi, Japan
  • 2006
    • Institute of Electrical & Electronics Engineers
      Italy, Texas, United States
  • 1987–1991
    • Sapienza University of Rome
      Roma, Latium, Italy