Fernando Agraz's research while affiliated with University of Barcelona and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (89)
We demonstrate that joint orchestration of TSN and optical network domains in support of IIoT applications reduces the TSN blocking by four orders of magnitude and the usage of high priority queues by a 28-100%.
Due to the limitations of traditional data center (DC) architectures, the concept of infrastructure disaggregation has been proposed. DC resources are separated into multiple blades to be exploited independently. As a result, composable DC (CDC) infrastructures are achieved, enhancing the modularity of resource provisioning. However, disaggregation...
The rise of traffic intensive services and applications is pushing the limits of conventional single band Wavelength Division Multiplexing (WDM) optical networks. As an answer to this challenge, new data plane technologies are being investigated. Multi-band optical networks have raised as a very interesting candidate due to the potential increased...
We propose a novel SDN control and orchestration architecture to provide composed IaaS over optical disaggregated data centers. We experimentally validate intent-based mechanisms that make the architecture independent from the underlying physical infrastructure technology.
Service quality assurance is of capital importance in modern cloud and network infrastructures, especially in multi-domain scenarios, where multiple operators collaborate to provide end-to-end (E2E) services. However, due to the dynamics of the multiple infrastructures and deployed services, it may be difficult to identify which domains need to per...
In order to compete for a prominent market share, network operators and service providers should retain and increase the verticals’ subscription, catering to their needs in order to differentiate themselves from competitors. In this scenario, verticals’ satisfaction arises of paramount importance. As such, user experience is becoming a reliable ind...
With the globalisation of the multimedia entertainment industry and the popularity of streaming and content services, multicast routing is (re-)gaining interest as a bandwidth saving technique. In the 1990’s, multicast routing received a great deal of attention from the research community; nevertheless, its main problems still remain mostly unaddre...
We present an architectural solution based on data analytics for self-organizing optical data centers. Thanks to a reinforcement learning-based cognitive layer, an adaptive and autonomous resource assignment to deployed services is achieved.
Network Slicing appears as one of the enabling technologies for 5G networks to accommodate services with different requirements and availability. The present work seizes the use of network slicing and focuses on the deployment and maintenance of services which are sensitive to latency constraints. For this purpose, the design and use of a VNF laten...
![CPU (top) average usage [%] and RAM (bottom) consumption [MB] on...](publication/338373224/figure/fig4/AS:961833745788932@1606330443401/CPU-top-average-usage-and-RAM-bottom-consumption-MB-on-VM1-VM2-as-seen-in_Q320.jpg)
![Throughput [Mb/s] vs packet loss ratio [%] with policy-based actuations](publication/338373224/figure/fig5/AS:961833745788933@1606330443504/Throughput-Mb-s-vs-packet-loss-ratio-with-policy-based-actuations_Q320.jpg)
The current deployment of 5G networks in a way to support the highly demanding service types defined for 5G, has brought the need for using new techniques to accommodate legacy networks to such requirements. Network Slicing in turn, enables sharing the same underlying physical infrastructure among services with different requirements, thus providin...
Network slicing has been taking a major role in upcoming 5G network implementations. However, in order to provision and maintain end-to-end slices, the management and orchestration among different network segments is required. As a result, techniques and components have risen to fulfil these tasks. In this work, we present latency-aware slicing, wh...
Optical switching techniques have the potential to enable the optical data center network (DCN) interconnections providing high capacity and fast switching capabilities, overcoming thus the bandwidth and latency bottleneck of present electrical switch-based multi-tiered DCNs. The rapid growth of multi-tenant applications with heterogeneous traffic...
Disaggregated DCs offer multiple benefits. However, transmission capacity limitations at blade level can severely degrade their performance. We analyze several strategies to enhance their service acceptance.
The emergence of new paradigms and services is pushing the limits of nowadays cloud infrastructures. It is a fact that current solutions lack in the flexibility and configurability to adapt to heterogeneous requirements coming from the applications/services to be supported over them. This results most of the time in severe underutilization of the u...
An SDN-controlled DCN enabling QoS-driven network-slice reconfiguration and packet priority updating is experimentally assessed. Network-slice can be reconfigured within 150 ms to decrease packet loss. The measured ToR-to-ToR latency of high-priority packets is 260.55 ns.
The use of optical technologies in modern network scenarios has increased in the last decade, mostly due to their support in crucial networking topics (ie, bandwidth and scalability). In parallel, these scenarios have also experienced the emergence of a new paradigm recognized as software‐defined networking (SDN), which bases on the decoupling of f...
Virtual data center (VDC) solutions provide an environment that is able to quickly scale up, and where virtual machines and network resources can be quickly added on-demand through self-service procedures. VDC providers must support multiple simultaneous tenants with isolated networks on the same physical substrate. The provider must make efficient...
An integrated software stack made up of extended OpenStack, OpenDaylight and custom OpenFlow agents enabling Virtual Data Centre deployment on an all-optical architecture employing hollow-core fibre, TDM fast switches and a circuit switched backplane.
The Internet data traffic constant growth caused by the popularization of cloud services, mobile and social networks, is being stressed by the advent of 5G technologies. Hence, architectural changes are required at the underlying networks to support the expected traffic volume growth, whereas providing a highly dynamic connectivity. Cost-effective...
Virtual data center (VDC) is a key service in modern data center (DC) infrastructures. However, the rigid architecture of traditional servers inside DCs may lead to blocking situations when deploying VDC instances. To overcome this problem, the disaggregated DC paradigm is introduced. In this letter, we present an integer linear programming (ILP) f...
Modern high-performance data centers are responsible for delivering a huge variety of cloud applications to the end-users, which are increasingly pushing the limits of the currently deployed computing and network infrastructure. All-optical dynamic data center network (DCN) architectures are strong candidates to overcome those adversities, especial...
We demonstrate an all-optical dynamic DCN utilizing a fully SDN-enabled data-plane including programmable FPGA-based NICs, offering Network Function Virtualization OCS/OPS driven multicasting for Virtual DC applications enabling link recovery and VM migration.
We introduce a holistic solution for softwaredefined optical data centres (DC). Hybrid optical circuit/packet switching technologies are employed in the data plane, while a software-defined networking (SDN) controller based on OpenDaylight with significant extensions is adopted for the data centre network (DCN) control and management. Novel functio...
Optical packet switching (OPS) can enhance the performance of data center networks (DCNs)by providing fast and large-capacity switching capability. Benefiting from the software-defined networking (SDN) control plane, which could update the look-up-table (LUT) of the OPS, virtual DCNs can be flexibly created and reconfigured. In this work, we have i...
We demonstrated an SDN-enabled optical DCN leveraging AoD, OPS, FPGA-based ToR with extended OpenDayLight controller and extended OF protocol. Experimental results show application-aware OCS/OPS connection provisioning (753/214ms), OPS end-to-end connections latency (252μs), and OCS/OPS switchover.
We demonstrate a 1.3 μm port-count scalable SDN-enabled optical packet switch architecture for programmable data-center networks. Experimental assessments of a 40Gb/s 4×4 switch system with SDN-control show <10-5 packet-loss and <430ns latency for 0.5 load.
A Software Defined Networking (SDN)-based architecture, employing optical technologies for multi-tenant data centers (DCs), is firstly discussed. Then, an efficient orchestration algorithm for Virtual Data Centers (VDCs) allocation is presented, highlighting the benefits that come from the usage of hybrid optical technologies.
An SDN-based control framework for OPS switches is experimentally assessed. The OpenFlow messages enabling control communication between SDN controller and OPS switch are validated. Dynamic OPS virtual network slices for intra-data center interconnect are successfully setup and monitored.
We demonstrate a reconfigurable virtual datacenter network by utilizing statistical multiplexing offered by scalable and flow-controlled optical switching system. Results show QoS guarantees by the priority assignment and load balancing for applications in virtual networks.
Current over-provisioned and multi-tier data centre networks (DCN) deploy rigid control and management platforms, which are not able to accommodate the ever-growing workload driven by the increasing demand of high-performance data centre (DC) and cloud applications. In response to this, the EC FP7 project LIGHTNESS (Low Latency and High Throughput...
Originally defined in the 90s, multicast is nowadays (re)gaining interest given the increasing popularity of multimedia streaming/content traffic and the explosion of cloud services. In fact, multicast yields bandwidth savings complementing cached content distribution techniques and its potential benefits have been verified by studies several times...
In this paper, we report our development experience and experimentation studies of two multicast routing schemes for the Internet, namely, PIM-SSM and GCMR. We detail their implementation over the Quagga open source routing suite, as well as their experimentation tests over a large-scale topology that reproduces the Internet characteristics.
Fast lightpath restoration becomes particularly challenging in all-optical networks. First, the optical transparency complicates failure localization and isolation procedures, as loss of light alarms stemming from a failure propagate downstream from the failure point. Besides, such a transparency implies that optical signals must traverse relativel...
We propose GMPLS protocol enhancements enabling dynamic power state management of optoelectronic network devices for setup-time-aware differentiated connection provisioning. Daily energy savings of 56% are demonstrated in a Pan-European-like network compared to always on scenarios.
In the Hierarchical Path Computation Element (H-PCE) architecture, an optimum end-to-end path is computed using a hierarchical relationship among PCEs. An H-PCE-based path computation procedure provides low network blocking probability meanwhile it results on a great amount of control overhead messages. In this paper we propose a hybrid path comput...
The ability of computing optimal routes poses new challenges when extending it to larger multi-domain network scenarios, as
the quality of these computed end-to-end inter-domain routes depends on the selection of the domain sequence to be traversed.
In the scope of the Internet Engineering Task Force (IETF), the Path Computation Element (PCE) Worki...
Export Date: 10 February 2012, Source: Scopus, Art. No.: 5875362
Export Date: 10 February 2012, Source: Scopus, Art. No.: 5875359
Core optical networks using reconfigurable optical switches and tunable lasers appear to be on the road towards widespread deployment and could evolve to all-optical mesh networks in the coming future. Considering the impact of physical layer impairments in the planning and operation of all-optical (and translucent) networks is the main focus of th...
Core optical networks using reconfigurable optical switches and tunable lasers appear to be on the road towards widespread deployment and could evolve to all-optical mesh networks in the coming future. Considering the impact of physical layer impairments in the planning and operation of all-optical (and translucent) networks is the main focus of th...
The European research project DICONET proposed and implemented a multi-plane impairment-aware solution for flexible, robust and cost-effective core optical networks. The vision of DICONET was realized via a set of cross-layer optimization algorithms designed to serve the network during planning and operation. The cross-layer modules were incorporat...
The efficient accommodation of subwavelength client flows on optical channels is a current challenge for the optimization of resources in GMPLS-controlled optical networks. While the capacity of the optical channels usually exceeds 10 Gbps, connection requests show finer granularity. This paper concentrates on the design and implementation of the A...
This paper evaluates a centralised impairment-aware path restoration approach for GMPLS-controlled transparent optical networks. Experimental results on a 14-node network test-bed show successful QoT compliant path restoration of around 3.6 seconds.
In this letter: we assess the scalability of a path computation flooding (PCF) approach to compute optimal end-to-end inter-domain paths in a path computation element-based multidomain network PCF yields a drastically reduced network blocking probability compared to a blind per-domain path computation hut introduces significant network control over...
This paper presents and compares different TE information dissemination strategies between Path Computation Elements (PCEs) in multi-domain optical networks. In such network context, recent studies have found that path computation only with local domain visibility yields poor network performance. Accordingly, certain visibility between domains seem...
A connection spanning, for example, several countries crosses multiple optical backbone networks, each one controlled by different administrators or operators. In this context, the interworking of these networks is thus necessary to set up end-to-end optical connections. A key issue when delivering such optical services is the use of efficient and...
Two GMPLS restoration strategies operating at wavelength and link granularities are experimentally validated in a multi-domain WSON. The strategies are qualitatively compared in terms of resource usage, restorability and restoration time.
We demonstrate and compare distributed and centralized impairment-aware control plane schemes for transparent optical networks with dynamic traffic. Experimental results show that distributed scheme yields one fifth of setup time required by previously reported alternatives.
In this paper, we introduce and evaluate a preventive contention avoidance protocol to reduce the burst loss probability in emerging OBS networks. The proposed solution reacts to highly loaded downstream node situations by preventively deflecting the bursts towards less loaded neighbors. To keep pace with OBS traffic dynamics while minimizing the r...
This paper demonstrates the benefits of GMPLS-based integrated routing and grooming in a 16-Node ASON/GMPLS network test-bed. Experimental results highlight significant blocking probability and E/O port usage reduction against all-optical and opaque transport network alternatives.
Large optical backbone networks may be composed of several domains, each one controlled by different administrators/operators. Besides, the bandwidth granularity of these domains may be different. Label Switched Paths (LSPs) provisioning in multi-domain/multi-operators/multi-layer network scenarios is a challenging problem actually, which has to be...
The efficient accommodation of sub-wavelength client flows on optical channels is a current challenge for resources use optimization in GMPLS controlled optical networks. While optical channels capacity usually exceeds 10 Gbit/s, client connections requests show finer granularity. This paper concentrates on the design and implementation of a GMPLS-...
Aiming at better resource utilization, an important requirement of future optical transport networks is the capability to accommodate subwavelength client flows efficiently. This can be put into action thanks to the enhanced traffic engineering (TE) protocols provided within the generalized multiprotocol label switching (GMPLS) standardization. The...
Current GMPLS standardization allows control plane deployment to be either physically or only logically separated from the data plane, describing out-of-fiber or in-fiber control plane configurations. It is widely accepted, that the out-of-fiber strategy provides enhanced flexibility, which derives from the natural separation of both planes. Noneth...
In this paper we propose a mechanism for connecting two or more MPLS islands belonging to the same MPLS domain through one ASON/GMPLS domain. It is based on the overlay model, where client and server networks do not exchange routing information. The interconnection is firstly done at the control plane level allowing the OSPF-TE flooding mechanism t...
In this paper we propose a mechanism for connecting two or more MPLS islands belonging to the same MPLS domain through one ASON/GMPLS domain. It is based on the Overlay Model, where client and server networks do not exchange routing information. The interconnection is firstly done at the control plane level allowing the OSPF-TE flooding mechanism t...