Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 50 of 271 results
  • A neuro-fuzzy approach to self-management of virtual network resources

     Mijumbi, Rashid; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Shen, Meng; Xu, Ke; Yang, Kun
    Expert systems with applications
    Vol. 42, num. 3, p. 1376-1390
    DOI: 10.1016/j.eswa.2014.08.058
    Date of publication: 2015-02-15
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Network virtualisation promises to lead to better manageability of the future Internet by allowing for adaptable sharing of physical network resources among different virtual networks. However, the sharing of resources is not trivial as virtual nodes and links should first be mapped onto substrate nodes and links, and thereafter the allocated resources managed throughout the lifetime of the virtual network. In this paper, we design and evaluate reinforcement learning-based neuro-fuzzy algorithms that perform dynamic, decentralised and coordinated self-management of substrate network resources. The objective is to achieve better efficiency in the utilisation of substrate network resources while ensuring that the quality of service requirements of the virtual networks are not violated. The proposed algorithms are evaluated through comparisons with a Q-learning-based approach as well as two static resource allocation schemes.

  • Business-driven policy optimization for service management

     Rubio-Loyola, Javier; Toscano-Pulido, Gregorio; Charalambides, Marinos; Magaña-Aguilar, Marisol; Serrat Fernandez, Juan; Pavlou, George; Galeana Zapien, Hiram
    International journal of network management
    Vol. 25, num. 2, p. 113-140
    DOI: 10.1002/nem.1886
    Date of publication: 2015
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    The performance of services offered by network operators has a direct impact on its reputation, on its revenue due to new customer subscriptions, and also on penalties that can apply when services are not provided to an acceptable quality level. Previous research on business-oriented network and service optimization has mainly focused on optimizing individual business indicators, such as profit and revenue, in isolation without analyzing the effect on network configurations and the subsequent impact on other indicators. Given that different business objectives are usually incompatible, a single network configuration cannot optimize them simultaneously. Determining the configuration and the associated trade-offs that satisfy multiple objectives is a complex task. This paper addresses this gap and presents a framework that derives policy configurations that optimize the business value of the network infrastructure. We describe a methodology to quantify business functions considering the dynamics of network events, the dynamics of end-user service usage, the nature of the business indicators, and their relationships with the underlying control methods. The proposed approach addresses the complexity of the target problem through a surrogate-based optimization approach properly tailored to match our application domain needs. We evaluate the effectiveness of the proposed approach through experimentation in a simulation environment we developed over OPNET

  • Self-managed Resources in Network Virtualisation Environments  Open access

     Mijumbi, Rashid
    Department of Signal Theory and Communications, Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    La virtualització de xarxes es una tècnica prometedora per afrontar la resistència d¿'Internet als canvis arquitectònics, que permet un nou model de negoci en el que la gestió de la infraestructura de xarxa es desacobla de la provisió del servei. Això permet als proveïdors de infraestructura (InPs), propietaris de la xarxa física substrat (SN), llogar segments d¿'aquesta als proveïdors dels serveis, que crearan xarxes virtuals (VNs) que a l¿'hora poden re-llogar-se o utilitzar-se per donar servei a usuaris finals.No obstant això, les diferents VNs s¿han d¿'inicialitzar assignant els seus nodes i enllaços als del substrat. Un dels reptes d¿'aquest procés es el requisit de fer un ús eficient dels recursos de la SN. Donat que el benefici d¿'un InP depèn del nombre de xarxes virtuals que puguin allotjar-se simultàniament en la SN, l¿'èxit de la virtualització de xarxes depèn en part de quan eficient es l¿'ús dels recursos de la xarxa física per part de les VNs. Aquesta Tesi contribueix a la millora de l¿'eficiència en la compartició de recursos en la virtualització de xarxes dividint el problema en tres sots problemes: (1) assignació de nodes i enllaços virtuals a nodes i enllaços del substrat (VNE), (2) gestió dinàmica dels recursos assignats a les VNs al llarg de la seva vida útil (DRA) i (3) aprovisionament de recursos de backup per assegurar la supervivència de les VNs.La naturalesa del problema VNE el fa ¿"NP-Hard¿. En conseqüència, per simplificar la solució, moltes de les propostes son heurístiques que es basen en hipòtesis (per exemple, SN amb recursos il¿limitats) de difícil compliment en escenaris reals. Aquesta Tesi proposa una millora al problema VNE mitjançant un algorisme ¿"one-shot VNE¿ basat en generació de columnes (CG). La solució CG comença resolent una versió restringida del problema, per tot seguit refinar-la i obtenir la solució final. L'¿objectiu del ¿"one-shot VNE¿ es aconseguir millorar l¿'ús dels recursos, mentre que CG redueix significativament la complexitat temporal del procés.D¿'altre banda, les solucions actuals son estàtiques, ja que els recursos assignats en la fase VNE no es modifiquen durant tot el temps de vida útil de la VN. Les poques propostes que permeten reajustar l¿'assignació inicial, es basen en una assignació fixe de recursos a les VNs. No obstant això, degut a que la càrrega de la xarxa varia a conseqüència de la demanda canviant dels usuaris, assignar una quantitat fixe de recursos basada en situacions de càrrega màxima esdevé en ineficiència per infrautilització en períodes de baixa demanda, mentre que en tals períodes de demanda baixa, el tenir recursos reservats, pot originar rebutjos de noves VNs. La segona contribució d¿'aquesta Tesi es un conjunt de propostes que asseguren l¿'ús eficient dels recursos de la SN, garantint a la vegada els requeriments de qualitat de servei de totes les VNs. Amb aquesta finalitat es proposen algorismes d¿'autogestió en els que la SN utilitza tècniques d¿'aprenentatge de màquines per a materialitzar decisions autònomes en l¿'assignació dels recursos. Finalment, malgrat que diversos estudis han tractat ja el problema VNE en entorn multi-domini, les propostes actuals de supervivència de xarxes virtuals s¿'han limitat a contexts d¿'aprovisionament per part d¿'un sol InP. En canvi, a la pràctica, la virtualització de xarxes comportarà un entorn d¿'aprovisionament multi-domini, i com que l¿'extensió de solucions de supervivència d¿'un sol domini al multi-domini no es trivial, aquesta Tesi proposa una solució distribuïda i dinàmica per a la supervivència de VNs. Això s¿'aconsegueix amb un sistema multi-agent que utilitza un protocol de negociació multi-atribut i un model dinàmic de preus per formar coalicions d¿'InPs que proporcionaran backups als recursos de les SNs. L¿'objectiu últim es assegurar que els operadors de xarxes virtuals maximitzin beneficis minimitzant les penalitzacions per violació de la QoS.

    Network virtualisation is a promising technique for dealing with the resistance of the Internet to architectural changes, enabling a novel business model in which infrastructure management is decoupled from service provision. It allows infrastructure providers (InPs) who own substrate networks (SNs) to lease chunks of them out to service providers who then create virtual networks (VNs), which can then be re-leased out or used to provide services to end-users. However, the different VNs should be initialised, in which case virtual links and nodes must be mapped to substrate nodes and paths respectively. One of the challenges in the initialisation of VNs is the requirement of an efficient sharing of SN resources. Since the profitability of InPs depends on how many VNs are able to be allocated simultaneously onto the SN, the success of network virtualisation will depend, in part, on how efficiently VNs utilise physical network resources. This thesis contributes to efficient resource sharing in network virtualisation by dividing the problem into three sub-problems: (1) mapping virtual nodes and links to substrate nodes and paths i.e. virtual network embedding (VNE), (2) dynamic managing of the resources allocated to VNs throughout their lifetime (DRA), and (3) provisioning of backup resources to ensure survivability of the VNs. The constrained VNE problem is NP-Hard. As a result, to simplify the solution, many existing approaches propose heuristics that make assumptions (e.g. a SN with infinite resources), some of which would not apply in practical environments. This thesis proposes an improvement in VNE by proposing a one-shot VNE algorithm which is based on column generation (CG). The CG approach starts by solving a restricted version of the problem, and thereafter refines it to obtain a final solution. The objective of a one-shot mapping is to achieve better resource utilisation, while using CG significantly enhances the solution time complexity. In addition current approaches are static in the sense that after the VNE stage, the resources allocated are not altered for the entire lifetime of the VN. The few proposals that do allow for adjustments in original mappings allocate a fixed amount of node and link resources to VNs throughout their life time. Since network load varies with time due to changing user demands, allocating a fixed amount of resources based on peak load could lead to an inefficient utilisation of overall SN resources, whereby, during periods when some virtual nodes and/or links are lightly loaded, SN resources are still reserved for them, while possibly rejecting new VN requests. The second contribution of this thesis are a set of proposals that ensure that SN resources are efficiently utilised, while at the same making sure that the QoS requirements of VNs are met. For this purpose, we propose self-management algorithms in which the SN uses time-difference machine learning techniques to make autonomous decisions with respect to resource allocation. Finally, while some scientific research has already studied multi-domain VNE, the available approaches to survivable VNs have focused on the single InP environment. Since in the more practical situation a network virtualisation environment will involve multiple InPs, and because an extension of network survivability approaches from the single to multi domain environments is not trivial, this thesis proposes a distributed and dynamic approach to survivability in VNs. This is achieved by using a multi-agent-system that uses a multi-attribute negotiation protocol and a dynamic pricing model forming InPs coalitions supporting SNs resource backups. The ultimate objective is to ensure that virtual network operators maximise profitability by minimising penalties resulting from QoS violations.

    La virtualització de xarxes es una tècnica prometedora per afrontar la resistència d'Internet als canvis arquitectònics, que permet un nou model de negoci en el que la gestió de la infraestructura de xarxa es desacobla de la provisió del servei. Això permet als proveïdors de infraestructura (InPs), propietaris de la xarxa física substrat (SN), llogar segments d'aquesta als proveïdors dels serveis, que crearan xarxes virtuals (VNs) que a l'hora poden re-llogar-se o utilitzar-se per donar servei a usuaris finals. No obstant això, les diferents VNs s'han d'inicialitzar assignant els seus nodes i enllaços als del substrat. Un dels reptes d'aquest procés es el requisit de fer un ús eficient dels recursos de la SN. Donat que el benefici d'un InP depèn del nombre de xarxes virtuals que puguin allotjar-se simultàniament en la SN, l'èxit de la virtualització de xarxes depèn en part de quan eficient es l’ús dels recursos de la xarxa física per part de les VNs. Aquesta Tesi contribueix a la millora de l’eficiència en la compartició de recursos en la virtualització de xarxes dividint el problema en tres sots problemes: (1) assignació de nodes i enllaços virtuals a nodes i enllaços del substrat (VNE), (2) gestió dinàmica dels recursos assignats a les VNs al llarg de la seva vida útil (DRA) i (3) aprovisionament de recursos de backup per assegurar la supervivència de les VNs. La naturalesa del problema VNE el fa “NP-Hard". En conseqüència, per simplificar la solució, moltes de les propostes son heurístiques que es basen en hipòtesis (per exemple, SN amb recursos il•limitats) de difícil compliment en escenaris reals. Aquesta Tesi proposa una millora al problema VNE mitjan_cant un algorisme “one-shot VNE" basat en generació de columnes (CG). La solució CG comena resolent una versió restringida del problema, per tot seguit refinar-la i obtenir la solució final. L'objectiu del “one-shot VNE" es aconseguir millorar l’ús dels recursos, mentre que CG redueix significativament la complexitat temporal del procés. D'altre banda, les solucions actuals son estàtiques, ja que els recursos assignats en la fase VNE no es modifiquen durant tot el temps de vida útil de la VN. Les poques propostes que permeten reajustar l’assignació inicial, es basen en una assignació fixe de recursos a les VNs. No obstant això, degut a que la càrrega de la xarxa varia a conseqüència de la demanda canviant dels usuaris, assignar una quantitat fixe de recursos basada en situacions de càrrega màxima esdevé en ineficiència per infrautilització en períodes de baixa demanda, mentre que en tals períodes de demanda baixa, el tenir recursos reservats, pot originar rebutjos de noves VNs. La segona contribució d'aquesta Tesi es un conjunt de propostes que asseguren l’ús eficient dels recursos de la SN, garantint a la vegada els requeriments de qualitat de servei de totes les VNs. Amb aquesta finalitat es proposen algorismes d’autogestió en els que la SN utilitza tècniques d'aprenentatge de màquines per a materialitzar decisions autònomes en l’assignació dels recursos. Finalment, malgrat que diversos estudis han tractat ja el problema VNE en entorn multi-domini, les propostes actuals de supervivència de xarxes virtuals s'han limitat a contexts d'aprovisionament per part d'un sol InP. En canvi, a la pràctica, la virtualització de xarxes comportarà un entorn d'aprovisionament multi-domini, i com que l’extensió de solucions de supervivència d'un sol domini al multi-domini no es trivial, aquesta Tesi proposa una solució distribuïda i dinàmica per a la supervivència de VNs. Això s'aconsegueix amb un sistema multi-agent que utilitza un protocol de negociació multi-atribut i un model dinàmic de preus per formar coalicions d'InPs que proporcionaran backups als recursos de les SNs. L'objectiu últim es assegurar que els operadors de xarxes virtuals maximitzin beneficis minimitzant les penalitzacions per violació de la QoS.

    La virtualización de redes es una técnica prometedora para afrontar la resistencia de Internet a cambios arquitectónicos, que permite un nuevo modelo de negocio en el que la gestión de la infraestructura está desacoplada del aprovisionamiento del servicio. Esto permite a los proveedores de infraestructuras (InPs), propietarios de la red física subyacente (SN), alquilar segmentos de la misma a los proveedores de servicio, los cuales crearán redes virtuales (VNs), que a su vez pueden ser realquiladas o usadaspara proveer el servicio a usuarios finales. Sin embargo, las diferentes VNs deben inicializarse, mapeando sus nodos y enlaces en los del substrato. Uno de los retos de este proceso de inicialización es el requisito de hacer un uso eficiente de los recursos de la SN. Dado que el benecio de los InPs depende de cuantas VNs puedan alojarse simultáneamente en la SN, el éxito de la virtualización de redes depende, en parte, de cuan eficiente es el uso de los recursos de red físicos por parte de las VNs. Esta Tesis contribuye a la compartición eficiente de recursos para la virtualización de redes dividiendo el problema en tres sub-problemas: (1) mapeo de nodos y enlaces virtuales sobre nodos y enlaces del substrato (VNE), (2) gestión dinámica de los recursos asignados a las VNs a lo largo de su vida útil (DRA), y (3) aprovisionamiento de recursos de backup para asegurar la supervivencia de las VNs. La naturaleza del problema VNE lo hace “NP-Hard". En consecuencia, para simplificar la solución, muchas de las actuales propuestas son heurísticas que parten de unas suposiciones (por ejemplo, SN con recursos ilimitados) de difícil asumir en la práctica. Esta Tesis propone una mejora al problema VNE mediante un algoritmo “one-shot VNE" basado en generación de columnas (CG). La solución CG comienza resolviendo una versión restringida del problema, para después refinarla y obtener la solución final. El objetivo del “one-shot VNE" es mejorar el uso de los recursos, a la vez que con CG se reduce significativamente la complejidad temporal del proceso. Por otro lado,las propuestas actuales son estáticas, ya que los recursos asignados en la fase VNE no se alteran a lo largo de la vida útil de la VN. Las pocas propuestas que permiten reajustes del mapeado original ubican una cantidad fija de recursos a las VNs. Sin embargo, dado que la carga de red varía con el tiempo, debido a la demanda cambiante de los usuarios, ubicar una cantidad fija de recursos basada en situaciones de pico conduce a un uso ineficiente de los recursos por infrautilización de los mismos en periodos de baja demanda, mientras que en esta situación, al tener los recursos reservados, pueden rechazarse nuevas solicitudes de VNs. La segunda contribución de esta Tesis es un conjunto de propuestas para el uso eficiente de los recursos de la SN, asegurando al mismo tiempo la calidad de servicio de las VNs. Para ello se proponen algoritmos de auto-gestión en los que la SN usa técnicas de aprendizaje de máquinas para materializar decisiones autónomas en la asignación de recursos. Finalmente, aunque determinadas investigaciones ya han estudiado el problema multi-dominio VNE, las propuestas actuales de supervivencia de redes virtuales se han limitado a un entorno de provisión de infraestructura de un solo InP. Sin embargo, en la práctica, la virtualización de redes comportará un entorno de aprovisionamiento con múltiples InPs, y dado a que la extensión de las soluciones de supervivencia de un entorno único a uno multi-dominio no es trivial, esta Tesis propone una solución distribuida y dinámica a la supervivencia de VNs. Esto se consigue mediante un sistema multi-agente que usa un protocolo de negociación multi-atributo y un modelo dinámico de precios para conformar coaliciones de InPs para proporcionar backups a los recursos de las SNs. El objetivo último es asegurar que los operadores de VNs maximicen su beneficio minimizando la penalización por violación de la QoS.

  • Contributions to efficient resource management in virtual networks

     Mijumbi, Rashid; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan
    Lecture notes in computer science
    Vol. 8508, p. 47-51
    DOI: 10.1007/978-3-662-43862-6_5
    Date of publication: 2014-06-30
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Network virtualisation is a promising technique for a better future Internet by allowing for network resource sharing. However, resource sharing requires that virtual nodes and links be embedded onto substrate nodes and links (virtual network embedding), and thereafter the allocated resources dynamically managed throughout the lifetime of the virtual network (dynamic resource allocation). Since the constrained virtual network embedding problem is NP–Hard, many existing approaches are not only static, but also make simplifying assumptions, most of which would not apply in practical environments. This PhD research proposes improvements to both virtual network embedding and dynamic resource allocation. The objective is to achieve an efficient utilisation of physical network resources. To this end, we propose a path generation-based approach for a one-shot, unsplittable flow virtual network embedding, and a reinforcement learning-based dynamic allocation of substrate network resources.

  • Neural network-based autonomous allocation of resources in virtual networks

     Mijumbi, Rashid; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Claeys, Maxim; Famaey, Jeroen; De Turck, Filip
    EUROPEAN CONFERENCE ON NETWORKS AND COMMUNICATIONS
    p. 1-6
    DOI: 10.1109/EuCNC.2014.6882668
    Presentation's date: 2014-06-24
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Network virtualisation has received attention as a way to allow for sharing of physical network resources. Sharing resources involves mapping of virtual nodes and links onto physical nodes and links respectively, and thereafter managing the allocated resources to ensure efficient resource utilisation. In this paper, we apply artificial neural networks for a dynamic, decentralised and autonomous allocation of physical network resources to the virtual networks. The objective is to achieve better efficiency in the utilisation of substrate network resources while ensuring that the quality of service requirements of the virtual networks are not violated. The proposed approach is evaluated by comparison with two static resource allocation schemes and a reinforcement learning-based approach.

  • Access to the full text
    Design and evaluation of learning algorithms for dynamic resource management in virtual networks  Open access

     Mijumbi, Rashid; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Claeys, Maxim; De Turck, Filip; Latré, Steven
    IEEE/IFIP Network Operations and management Symposium
    p. 1-9
    DOI: 10.1109/NOMS.2014.6838258
    Presentation's date: 2014-05-08
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Network virtualisation is considerably gaining attention as a solution to ossification of the Internet. However, the success of network virtualisation will depend in part on how efficiently the virtual networks utilise substrate network resources. In this paper, we propose a machine learning-based approach to virtual network resource management. We propose to model the substrate network as a decentralised system and introduce a learning algorithm in each substrate node and substrate link, providing self-organization capabilities. We propose a multiagent learning algorithm that carries out the substrate network resource management in a coordinated and decentralised way. The task of these agents is to use evaluative feedback to learn an optimal policy so as to dynamically allocate network resources to virtual nodes and links. The agents ensure that while the virtual networks have the resources they need at any given time, only the required resources are reserved for this purpose. Simulations show that our dynamic approach significantly improves the virtual network acceptance ratio and the maximum number of accepted virtual network requests at any time while ensuring that virtual network quality of service requirements such as packet drop rate and virtual link delay are not affected.

    Postprint (author’s final draft)

  • Multi-layered reinforcement learning approach for radio resource management

     Collados Zamora, Kevin; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Hu, Zheng
    Lecture Notes in Electrical Engineering
    Vol. 277, p. 1191-1199
    DOI: 10.1007/978-3-319-01766-2_135
    Date of publication: 2014-02-07
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    In this paper we face the challenge of designing self-tuning systems governing the working parameters of base stations on a mobile network system to optimize the quality of service and the economic benefit of the operator. In order to accomplish this double objective, we propose the combined use of fuzzy logic and reinforcement learning to implement a self-tuning system using a novel approach based on a two-agent system. Different combinations of reinforcement learning techniques, on both agents, have been tested to deduce the optimal approach. The best results have been obtained applying the Q-learning technique on both agents, clearly outperforming the alternative of using non-learning algorithms.

  • Challenges to support edge-as-a-service

     Davy, Steven; Famaey, Jeroen; Serrat Fernandez, Juan; Gorricho Moreno, Juan Luis; Miron, Avi; Dramitinos, Manos; Neves, Pedro Miguel; Latré, Steven; Goshen, Ezer
    IEEE communications magazine
    Vol. 52, num. 1, p. 132-139
    DOI: 10.1109/MCOM.2014.6710075
    Date of publication: 2014-01-16
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    A new era in telecommunications is emerging. Virtualized networking functions and resources will offer network operators a way to shift the balance of expenditure from capital to operational, opening up networks to new and innovative services. This article introduces the concept of edge as a service (EaaS), a means of harnessing the flexibility of virtualized network functions and resources to enable network operators to break the tightly coupled relationship they have with their infrastructure and enable more effective ways of generating revenue. To achieve this vision, we envisage a virtualized service access interface that can be used to programmatically alter access network functions and resources available to service providers in an elastic fashion. EaaS has many technically and economically difficult challenges that must be addressed before it can become a reality; the main challenges are summarized in this article.

  • Report on the 7th International Conference on Autonomous Infrastructure, Management, and Security (AIMS 2013): Emerging Management Mechanisms for the Future Internet

     Doyen, Guillaume; Waldburger, Martin; Sperotto, Anna; Celeda, Pavel; Gorricho Moreno, Juan Luis; Schaaf, Thomas; Serrat Fernandez, Juan
    Journal of network and systems management
    Vol. 21, num. 4, p. 1-8
    DOI: 10.1007/s10922-013-9298-9
    Date of publication: 2013-12-31
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This article contains the report on AIMS 2013, which was held on June 25–28, 2013 at the Universitat Politècnica de Catalunya (UPC), Spain and was driven by the theme “Emerging Management Mechanisms for the Future Internet”. It covers the three main parts that formed the event program: the keynote and technical sessions of the main track, the PhD workshop and the hands-on tutorials. Finally, the report highlights the evolutions that would shape the future version of AIMS.

  • Software Enabled Future Internet – challenges in orchestrating the future Internet

     Galis, Alex; Rubio-Loyola, Javier; Clayman, Stuart; Mamatas, Lefteris; Kuklinski, Slawomir; Serrat Fernandez, Juan; Zahariadis, Theodore
    International Conference on Mobile Networks and Management
    p. 228-244
    DOI: 10.1007/978-3-319-04277-0_18
    Presentation's date: 2013-09-24
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This position paper presents SoftINTERNET an initiative for a service-aware and management-aware network control infrastructure for heterogeneous networks (i.e., wired and wireless) that uses software driven features for the elaboration, development, and validation of networking concepts. The proposed infrastructure aims to optimally integrate the connectivity and management layers. It operates across multiple network environments and on top of private and public network clouds utilising fixed and mobile virtual resources, OpenFlow enabled network devices like switches and routers, and networks of Smart Objects. In this position paper, we discuss the motivation, architecture and research challenges for such a promising concept.

  • Multilayered reinforcement learning approach for radio resource management

     Collados Zamora, Kevin; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Hu, Zheng
    International Conference on Computer Engineering and Network
    p. 1191-1199
    DOI: 10.1007/978-3-319-01766-2-135
    Presentation's date: 2013-07
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    In this paper we face the challenge of designing self-tuning systems governing the working parameters of base stations on a mobile network system to optimize the quality of service and the economic benefit of the operator. In order to accomplish this double objective, we propose the combined use of fuzzy logic and reinforcement learning to implement a self-tuning system using a novel approach based on a two-agent system. Different combinations of reinforcement learning techniques, on both agents, have been tested to deduce the optimal approach. The best results have been obtained applying the Q-learning technique on both agents, clearly outperforming the alternative of using non-learning algorithms.

  • Conectividad como servicio: acceso para la internet de futuro-1

     Postigo Boix, Marcos; Gorricho Moreno, Juan Luis; Valle Alarcon, Rafael; Melus Moreno, Jose Luis; Serrat Fernandez, Juan
    Competitive project

     Share

  • Making sense of monitoring data to support managed next-generation services: a report on DANMS 2012

     Keeney, John; Serrat Fernandez, Juan
    Journal of network and systems management
    Vol. 20, num. 4, p. 608-615
    DOI: 10.1007/s10922-012-9252-2
    Date of publication: 2012-12
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Management of the Future Internet

     Melus Moreno, Jose Luis; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan; Postigo Boix, Marcos; Valle Alarcon, Rafael
    Competitive project

     Share

  • Access to the full text
    Multi-agent based resource allocation in next generation virtual networks  Open access

     Mijumbi, Rashid; Serrat Fernandez, Juan; Gorricho Moreno, Juan Luis
    Barcelona Forum on Ph.D. Research in Information and Communications Technologies
    Presentation's date: 2012-10-16
    Presentation of work at congresses

    Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    On the equilibrium of pricing assignment for heterogeneous wireless access networks  Open access

     López de la Torre, Carmen; Choque, Johnny; Agüero Calvo, Ramón; Serrat Fernandez, Juan; Muñoz Gutierrez, Luis
    International Conference on Mobile Networks and Management
    p. 1-15
    Presentation's date: 2012-09-24
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Next generation networks and service providers are rapidly evolving in order to satisfy the demands of an increasing number of users. Nowadays, one of the most relevant research lines in the Heterogeneous Wireless Access Networks realm is the use of procedures and mechanisms so as to provide intelligence to the network, with the main goal of optimizing its performance. Furthermore, mobile communication users are becoming more demanding, and thus it becomes essential for the providers to be able to offer a competitive value for money. This paper pursues the objective of obtaining, from an analytical perspective, the optimum price assignment strategy according to the characteristics of a particular scenario, analyzing the improvement attained with such optimum pricing policy as compared to a more traditional one. Game theory techniques, which are gathering the interest within the communications scientific community, are used for the analysis.

  • Access to the full text
    A price based load balancing scheme for multi-operator wireless access networks  Open access

     Choque, Johnny; Agüero Calvo, Ramón; Serrat Fernandez, Juan; Muñoz Gutierrez, Luis
    International Conference on Mobile Networks and Management
    p. 1-13
    Presentation's date: 2012-09-24
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    We study a load balancing strategy, based on the price offered by the base stations to the end-users who are willing to establish a connection. The proposed scheme is compared with a pure load balancing procedure, in a scenario comprising two different operators.We study the impact of modifying the price offered by the base stations, in terms of the achieved load balancing, as well as considering the revenue obtained by the operators. Furthermore, we also enhance the two former access selection schemes, by incorporating the willingness of reducing the number of handovers, so as to analyze the impact over this particular parameter, and over all the previous results. The whole work is conducted over a proprietary event-based simulation tool, which offers the required degree of flexibility and low computational overhead.

  • A two-dimensional architecture for end-to-end resource management in virtual network environments

     Wang, Ning; Zhang, Yi; Serrat Fernandez, Juan; Gorricho Moreno, Juan Luis; Guo, Tao; Hu, Zheng; Zhang, Ping
    IEEE network
    Vol. 26, num. 5, p. 8-14
    DOI: 10.1109/MNET.2012.6308069
    Date of publication: 2012-09
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    In recent years, various network virtualization techniques have been proposed for flexibly supporting heterogeneous services over virtual network platforms. However, systematic views on how virtual network resources (VNRs) can be practically managed in such open environments has been missing till now. To fill the gap, we present in this article a two-dimensional architecture for end-to-end VNR management from distinct viewpoints of service providers and network providers. The horizontal dimension of VNR management allows SPs to bind VNRs rented from heterogeneous NPs to form unified end-to-end service delivery platforms. The vertical dimension of VNR management enables NPs to perform cost-efficient allocation of VNRs to requesting SPs, but without necessarily forcing themselves to collaborate with each other. Such a VNR management architecture will complement existing network virtualization platforms in accelerating the realization of virtual resource sharing in the future Internet business marketplaces.

  • Service Management in Federated e-Infrastructures

     Melus Moreno, Jose Luis; Postigo Boix, Marcos; Gorricho Moreno, Juan Luis; Valle Alarcon, Rafael; Serrat Fernandez, Juan
    Competitive project

     Share

  • A Business-Oriented Management Framework for Mobile Communication Systems

     Galeana Zapien, Hiram; Rubio Loyola, Javier; Salazar Linares, Pablo; Agüero Calvo, Ramón; Serrat Fernandez, Juan; Davy, Steven
    Mobile networks and applications
    Vol. 17, num. 4, p. 479-491
    DOI: 10.1007/s11036-012-0378-y
    Date of publication: 2012-08
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Autonomic resource management in virtual network

     Mijumbi, Rashid; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan
    Scalable and Adaptive Internet Solutions Summer School
    Presentation's date: 2012-06-28
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Virtualization enables the building of multiple virtual networks over a shared substrate. One of the challenges to virtualisation is efficient resource allocation. This problem has been found to be NP hard. Therefore, most approaches to it have not only proposed static solutions, but have also made many assumptions to simplify it. In this paper, we propose a distributed, autonomic and artificial intelligence based solution to resource allocation. Our aim is to obtain self-configuring, self-optimizing, self-healing and context aware virtual networks

  • Scalable service deployment on software-defined networks

     Rubio Loyola, Javier; Astorga Rivera, Jose Antonio; Galis, Alex; Serrat Fernandez, Juan; Lefevre, L.; Fischer, Andreas; Paler, A.; de Meer, Hermann
    IEEE communications magazine
    Vol. 49, num. 12, p. 84-93
    DOI: 10.1109/MCOM.2011.6094010
    Date of publication: 2011-12-01
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    It is widely accepted that the network of the future will require a greater degree of service awareness and optimal use of network resources. This article presents an architectural design for an open software-defined network infrastructure that enables the composition of fast and guaranteed services in an efficient manner and the execution of these services in an adaptive way, taking into account better shared network resources provided by network virtualization. Validation results are provided with special emphasis on service deployment scalability over virtualized network infrastructures.

  • A service-centric orchestration protocol for self-organizing autonomic management systems

     Rubio Loyola, Javier; Mérida-Campos, Carlos; Serrat Fernandez, Juan; Fernandes Macedo, Daniel; Davy, Steven; Movahedi, Zeinab; Pujolle, Guy
    IEEE network
    Vol. 25, num. 6, p. 16-23
    DOI: 10.1109/MNET.2011.6085638
    Date of publication: 2011-11-01
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This article presents a service-centric orchestration protocol for self-interested autonomic management systems that supports the coalition formation process in largescale collaborative and competitive environments. It supports environments in which coalition formations are carried out targeting multiple service requests at the same time, and in which the autonomic management systems compete to work in the most appropriate coalition. The protocol exploits the benefits of social networking in favor of manageability and scalability. Its performance is analyzed taking into account crucial aspects of self-organizing systems such as stability and convergence to optimal coalition formation results.

  • Policy-assisted planning and deployment of virtual networks

     Davy, Steven; Serrat Fernandez, Juan; Astorga Rivera, Jose Antonio; Jennings, Brendan; Rubio-Loyola, J.
    International Conference on Network and Service Management
    p. 1-8
    Presentation's date: 2011-10-24
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    We present an approach for deploying and subsequently managing a virtual network overlay, which is tailored to an end-user’s request. Our approach combines a binary integer optimisation process to decide on the number and placement of virtual routers, and an autonomic network management system that subsequently manages the configuration of the running virtual network. High-level optimisation policies are used to guide the optimisation process to identify a virtual network that favours lower hosting costs or higher network quality (we use mean delays as a quality metric). Low-level deployment policies are generated and used to govern the deployment and management of the virtual networks. Our results indicate that the binary integer optimisation process produces a virtual network that has lower cost as compared to creating a network based on combined shortest paths.

  • Camps Invisibles. Geografies de les ones ràdio

     Santacana Juncosa, Amadeo; Viotto, Umberto; Serrat Fernandez, Juan
    Collaboration in exhibitions

     Share

  • Gestión de políticas y precios en entornos de acceso heterogéneos

     Baliosian, Javier; Rubio-Loyola, J.; Agüero Calvo, Ramón; Serrat Fernandez, Juan
    Jornadas de Ingeniería Telemática1
    p. 1-7
    Presentation's date: 2011-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    La irrupción de nuevos servicios, y el imparable aumento del número de tecnologías de acceso a disposición de los usuarios, hace que los diferentes actores involucrados en el ámbito de las comunicaciones tengan que replantearse sus estrategias tradicionales. Es necesario afrontar el diseño de una arquitectura capaz de asumir los retos que van apareciendo, siendo clave romper con algunas de las soluciones tradicionales, que no son capaces de responder a las nuevas exigencias que aparecen. Uno de los aspectos más importantes es afrontar el diseño desde un punto de vista global, haciendo que las diferentes entidades cooperen entre sí de manera abierta y flexible, lo que no es posible (en muchas ocasiones) con parches a las alternativas que actualmente existen. Este marco es en el que se sitúa el proyecto Comunicaciones Cognitivas, Cooperativas y Gestión Autónoma de Servicios (C3SEM), que se fundamenta en la cooperación e integración del substrato de comunicación subyacente con la arquitectura de gestión de servicios. En este trabajo se plantea una de las líneas de trabajo actuales, en la que se analiza diferentes políticas de gestión de precios, ya que parece razonable que en el medio plazo los operadores se vean obligados a redefinir sus estrategias actuales, principalmente basadas en tarifas planas.

  • On importance of service level management in grids

     Szepieniec, Tomasz; Kocot, Joanna; Schaaf, Thomas; Appleton, Owen; Heikkurinen, Matti; Belloum, Adam S.Z.; Serrat Fernandez, Juan; Metzker, Martin
    Management and Delivering Grid Services
    p. 64-75
    DOI: 10.1007/978-3-642-29740-3-9
    Presentation's date: 2011-08-31
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    The recent years saw an evolution of Grid technologies from early ideas to production deployments. At the same time, the expectations for Grids shifted from idealistic hopes - buoyed by the successes of the initial testbeds - to disillusionment with available implementations when applied to large-scale general purpose computing. In this paper, we argue that a mature e-Infrastructure aiming to bridge the gaps between visions and realities cannot be delivered without introducing Service Level Management (SLM). To support this thesis, we present an analysis of the Grid foundations and definitions that shows that SLM-related ideas were incorporated in them from the beginning. Next, we describe how implementing SLM in Grids could improve the usability and user-experience of the infrastructure - both for its customers and service providers. We also present a selection of real-life Grid application scenarios that are important for the research communities supported by the Grid, but cannot be efficiently supported without the SLM process in place. In addition, the paper contains introduction to SLM, a discussion on what introducing SLM to Grids might mean in practice, and what were the current efforts already applied in this field. © 2012 Springer-Verlag Berlin Heidelberg.

  • Policy-based pricing for heterogeneous wireless access networks

     Baliosian, Javier; Serrat Fernandez, Juan; Richart, Matias; Saavedra, Juan; Borba, Mariela; Melus Moreno, Jose Luis
    International Conference on Autonomous Infrastructure, Management and Security
    p. 73-85
    DOI: 10.1007/978-3-642-21484-4_11
    Presentation's date: 2011-06
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Our cities are already covered by a myriad of diverse wireless access networks. The most ubiquitous access networks are the well organized homogeneous and centralized operator-based cellular networks that sustain their business model on a captive client basis. However, a new billing paradigm is rising, where a client can choose to connect to the provider that best comply with his/her current requirements and context. Inside this paradigm, this paper presents a distributed, rule-based pricing strategy aimed to improve the quality of service and to increase the global income of a service provider. The performance and reliability of the rule-based decisions is supported by a Finite State Transducersbased inference machine specially designed to manage networking systems. We show, with simulations, that, using our strategy, the operators can make the new billing paradigm profitable while the clients benefit from the economic advantages of competition and of the quality given by a pricing–based network balance mechanism.

  • Towards In-Network Clouds in Future Internet

     Galais, Alex; Clayman, S.; LEFEVRE, JOSETTE; Fisher, Andreas; de Meer, Hermann; Rubio Loyola, Javier; Serrat Fernandez, Juan; Davy, Steven
    DOI: 10.1007/978-3-642-20898-0_22
    Date of publication: 2011-05-04
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    One of the key aspect fundamentally missing from the current Internet infrastructure is an advanced service networking platform and facilities, which take advantage of flexible sharing of available connectivity, computation, and storage resources. This paper aims to explore the architectural co-existence of new and legacy services and networks, via virtualisation of connectivity and computation resources and self-management capabilities, by fully integrating networking with cloud computing in order to create In-Network Clouds. It also presents the designs and experiments with a number of In-Network Clouds platforms, which have the aim to create a flexible environment for autonomic deployment and management of virtual networks and services as experimented with and validated on large-scale testbeds.

  • End-to-end Virtual Resource Management across Heterogeneous Networks and Services

     Gorricho Moreno, Juan Luis; Postigo Boix, Marcos; Melus Moreno, Jose Luis; Valle Alarcon, Rafael; Serrat Fernandez, Juan
    Competitive project

     Share

  • C/033194/10 Cooperación Institucional entre las universidades AAU y UPC y académica en el ámbito de las TIC

     Torres Urgell, Luis; Vidal Lopez, Eva Maria; Vidal Manzano, Jose; Serrat Fernandez, Juan; Aguilar Igartua, Mónica; Fernandez Muñoz, Marcel
    Competitive project

     Share

  • Access to the full text
    Platforms and software systems for an autonomic internet  Open access

     Rubio-Loyola, J.; Astorga Rivera, Jose Antonio; Serrat Fernandez, Juan; Chai, W.K.; Galis, Alex; Mamatas, L.; Clayman, S.; Cheniour, A.; Lefevre, L.; Mornard, O.; Fischer, A.; Paler, A.; de Meer, H.
    IEEE Global Communications Conference
    p. 1-6
    DOI: 10.1109/GLOCOM.2010.5683380
    Presentation's date: 2010-12-08
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    The current Internet does not enable easy introduction and deployment of new network technologies and services. This paper aims to progress the Future Internet (FI) by introduction of a service composition and execution environment that re-use existing components of access and core networks. This paper presents essential service-centric platforms and software systems that have been developed with the aim to create a flexible environment for an Autonomic Internet.

  • Service management in future networks: the C3SEM vision

     Serrat Fernandez, Juan
    International ICST Conference on Mobile Networks and Management
    Presentation's date: 2010-09-23
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Business-driven management of differentiated services  Open access

     Rubio Loyola, Javier; Serrat Fernandez, Juan; Charalambides, Marinos; Aib, Issam; Pavlou, George; Boutaba, Raouf
    IEEE/IFIP Network Operations and management Symposium
    p. 240-247
    DOI: 10.1109/NOMS.2010.5488468
    Presentation's date: 2010-04-23
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Several intra- and inter-domain quality of service (QoS) provisioning mechanisms for IP networks have been researched and developed using Differentiated Services (DiffServ) technology. However, the incremental efforts needed to manage DiffServ networks from a business-oriented viewpoint have received relatively little attention. This paper addresses this gap and presents a framework for achieving business-driven QoS provisioning in DiffServ over MPLS networks. We provide a rich model of SLA and business indicators as well as reasonable mapping functions that define, with key degrees of importance, the impact of business indicators over service management policies. Business and service indicators are used to control static and dynamic admission of services. The paper advances the state of the art by considering the influence of business-level objectives on the policy refinement process. We evaluate and discuss the effectiveness of our approach through a simulation environment that we developed over OPNET.

  • Manageability of future internet virtual networks from a practical viewpoint

     Rubio Loyola, Javier; Astorga Rivera, Jose Antonio; Serrat Fernandez, Juan; Lefevre, L.; Cheniour, A.; Muldowney, D.; Davy, Steven; Galis, Alex; Mamatas, L.; Clayman, S.; Fernandes Macedo, Daniel; Movahedif, Z.; Fischer, A.; de Meer, H.
    Date of publication: 2010-04-01
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    The Autonomic Internet project [1] approach relies on abstractions and distributed systems of a five plane solution for the provision of Future Internet Services (OSKMV): Orchestration, Service Enablers, Knowledge, Management and Virtualisation Planes. This paper presents a practical viewpoint of the manageability of virtual networks, exercising the components and systems that integrate this approach and that are being validated. This paper positions the distributed systems and networking services that integrate this solution, focusing on the provision of Future Internet services for self-configuration and selfperformance management scenes

  • GESTION DE SERVICIOS DE NUEVA GENERACION EN INTERNET

     Sanvicente1 Gargallo, Emilio; Postigo Boix, Marcos; Bagnasco Aguirre, Ricardo Javier; Astorga Rivera, Jose Antonio; Melus Moreno, Jose Luis; Gorricho Moreno, Juan Luis; Serrat Fernandez, Juan
    Competitive project

     Share

  • GESTIÓ, POLÍTIQUES DE PREUS I SERVEIS EN XARXES DE NOVA GENERACIÓ (MAPS)

     Bagnasco Aguirre, Ricardo Javier; Melus Moreno, Jose Luis; Sanvicente1 Gargallo, Emilio; Astorga Rivera, Jose Antonio; Postigo Boix, Marcos; Gorricho Moreno, Juan Luis; Valle Alarcon, Rafael; Serrat Fernandez, Juan
    Competitive project

     Share

  • Access to the full text
    Monitoring of a virtual infrastructure testbed  Open access

     Magana, Edgar; Astorga Rivera, Jose Antonio; Serrat Fernandez, Juan; Valle Alarcon, Rafael
    IEEE Latin-American Conference on Communications
    Presentation's date: 2009-09-10
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This paper presents a SNMP-based Monitoring Agents for Multi-Constrain Resource Scheduling in Grids (SBLOMARS) as an effective solution for resource usage monitoring in virtual network environments. SBLOMARS is different to current large-scale distributed monitoring systems in three essential aspects: Firstly, it reaches a high level of generality by the integration of the SNMP protocol and thus, facilitates to handle heterogeneous operating platforms. Secondly, it is able to self-configure the polling periods of the resources to be monitored depending of network context and finally, it makes use of dynamic software structures to interface with third parties, allowing to be deployed in a wide range of devices, from simple mobile access devices to robust multiprocessor systems or clusters with even multiple hard disks and storage partitions. SBLOMARS has been deployed in EmanicsLab, a virtual laboratory constituted by fourteen nodes distributed in seven European Universities. Although the research is not yet concluded, available results confirm its suitability to deal with the challenges of monitoring virtual networks.

  • A Viewpoint of the Network Management Paradigm for Future Internet Networks

     Rubio Loyola, Javier; Serrat Fernandez, Juan; Astorga Rivera, Jose Antonio; Fischer, Andreas; Berl, Andreas; de Meer, Hermann; Koumoutsos, Giannis
    IFIP/IEEE International Symposium on Integrated Network Management Workshops
    p. 93-100
    DOI: 10.1109/INMW.2009.5195943
    Presentation's date: 2009-06
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Management architecture and systems for future

     Galis, Alex; Denazis, S.; Serrat Fernandez, Juan; Rubio Loyola, Javier; Giacomin, P.; Bassi, Alessandro; de Meer, Hermann; Fischer, Andreas; Berl, Andreas; Srassner, J. S.; Fernandes Macedo, Daniel; Pujolle, Guy
    Date of publication: 2009-05-01
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper presents a new autonomic management architectural model consisting of a number of distributed management systems running within the network, which are described with the help of five abstractions and distributed systems: Virtualisation, Management, Knowledge, Service Enablers and Orchestration Planes. The envisaged solution is applicable to the management design of Future Internet as a service and self-aware network, which guarantees built-in orchestrated reliability, robustness, context, access, security, service support and self-management of the communication resources and services

  • The 6 The International Conference on Autonomic Computing and Communications

     Postigo Boix, Marcos; Serrat Fernandez, Juan
    Competitive project

     Share

  • Multi-Agent Reinforcement Learning in Network Management

     Bagnasco, R; Serrat Fernandez, Juan
    3rd International Conference on Autonomous Infrastructure, Management and Security
    p. 199-202
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • A Viewpoint of the Network Management Paradigm for Future Internet Networks

     Rubio-Loyola, J; Serrat Fernandez, Juan; Astorga, A; Fischer, A; Berl, A; Koumoutsos, G
    1st IFIP/IEEE International Workshop on Management of the Future Internet
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Service Coalitions for Future Internet Services

     Rubio-Loyola, J; Mérida-Campos, C; Willmott, S; Astorga, A; Serrat Fernandez, Juan; Galis, Alex
    IEEE International Conference on Communications
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Autonomic Systems in Network and Service Management

     Serrat Fernandez, Juan; Antonio, Astorga; Javier, Rubio
    Upgrade
    Vol. IX, num. 6, p. 41-48
    Date of publication: 2008-12
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • MANAGEMENT AND CONTEXT INTEGRATION BASED ON ONTOLOGIES FOR PERVASIVE SERVICE OPERATIONS IN AUTONOMIC COMMUNICATIONS SYSTEMS

     Serrano Orozco, Jaime Martín
    Department of Signal Theory and Communications, Universitat Politècnica de Catalunya
    Theses

     Share Reference managers Reference managers Open in new window

  • Review of Knowledge Engineering Requirements for Semantic Reasoning in Autonomic Networks

     Serrat Fernandez, Juan
    11th Asia-Pacific Network Operations and Management Symposium
    Presentation's date: 2008-10-22
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • A Distributed and Heuristic Policy-based Management Architecture for Large-Scale Grids  Open access

     Magaña Perdomo, Edgar Fco.
    Department of Signal Theory and Communications, Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    The aim of this thesis is to design and implement a new Grid Resource Management methodology, where non-massive resources owners would be able to share their resources and integrate human collaboration across multiple domains regardless of network technology, operative platform or administrative domain.This thesis proposes a distributed and heuristic policy-based resource management architecture for large-scale Grids. The resource management architecture proposed herein is composed of four main building blocs: services management, resource discovery and monitoring, resource scheduling and jobs allocation and activation. The Grid Services Management (GSM) and Jobs Allocation and Activation (JAA) are supported by means of a Policy-based Grid Resource Management Architecture (PbGRMA). This architecture is able to identify service needs arising from diverse sources during the deployment and management of Grid Services, such as requirements demanded by customers, applications and network conditions. Afterwards, the PbGRMA merges these requirements into deployment policies for the corresponding Grid Services. The Grid Resource Discovery and Monitoring (GRDM) is supported by the introduction of the SNMP-based Balanced Load Monitoring Agents for Resource Scheduling (SBLOMARS), in which network and computational resources are monitored by distributed agents. This allows for a flexible, heterogeneous and scalable monitoring system. The Grid Resource Scheduling (GRS) is based on the Balanced Load Multi-Constrained Resource Scheduler (BLOMERS). This heuristic scheduler represents an alternate way of solving the inherent NP-hard problem for resource scheduling in large-scale distributed networks by means of the implementation of a Genetic Algorithm.Finally, based on the outcome of both the GRDM and GRS, the PbGRMA allocates the corresponding Grid Services by means of its interfaces with Globus ToolKit Middleware and Unix-based CLI commands along of any large-scale Grid Infrastructure. The synergy obtained by these components allows Grid administrators to exploit the available resources with predetermined levels of Quality of Service (QoS), reducing computational costs and makespan in resource scheduling while ensuring that the resource load is balanced throughout the Grid. The makespan of a schedule is the time required for all jobs to be processed when no one job could be interrupted during its execution and each node can perform at most one operation at any time.This new approach has been successfully tested in a real large-scale scenario such as Grid5000. The results presented along this Thesis show that our general solution is a reliable, flexible and scalable architecture to deploy and manage Grid Services in large-scale Grid Infrastructures. Moreover, the substitution of the heuristic algorithm approach used into the Grid Resource Scheduling (GRS) phase by other non-heuristics selection algorithms could make our solution useful in smaller Grid Infrastructures.

  • FACILITATING AUTONOMIC MANAGEMENT FOR SERVICE PROVISIONING USING ONTOLOGY-BASED FUNCTIONS & SEMANTIC CONTROL

     Serrat Fernandez, Juan
    The 3rd International Workshop on Broadband Convergence Networks
    Presentation's date: 2008-04-07
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window