Alberto Garcia-Martinez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Alberto Garcia-Martinez has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Marcelo Bagnulo
Department of Telematic Engineering, University Carlos III of Madrid, Legans, Spain
18 shared publications - Arturo Azcorra
Universidad Carlos III de Madrid Universidad Carlos III de Madrid IMDEA Networks Institute
9 shared publications - Stefano Angieri
Universidad Carlos III de Madrid Madrid, Spain
3 shared publications - Andra Lutu
Telefónica Research, Madrid, Spain
2 shared publications - Bingyang Liu
HUAWEI, Shenzhen, China
2 shared publications - Guillermo Ibanez
Departamento de Automatica, Escuela Politecnica Superior, Universidad de Alcala, 28807 Madrid, Spain
2 shared publications
Latest Publications
- Open Access
- 11 January 2024
- Published by Elsevier in Computer Networks
- Vol. 240
BGP convergence in an MRAI-free Internet
- 11 January 2024
- Published by Elsevier in Computer Networks
- Vol. 240
Open AccessBGP convergence in an MRAI-free Internet
- Open Access
- 21 May 2022
- Published by Elsevier in Computer Networks
- Vol. 212
Measuring DoH with web ads
- 21 May 2022
- Published by Elsevier in Computer Networks
- Vol. 212
Open AccessMeasuring DoH with web ads
- Open Access
- 17 May 2022
- Published by Elsevier in Computer Networks
- Vol. 212
An experimental evaluation of LEDBAT++
- 17 May 2022
- Published by Elsevier in Computer Networks
- Vol. 212
Open AccessAn experimental evaluation of LEDBAT++
- Open Access
- 18 April 2022
- Published by Elsevier in Computer Networks
- Vol. 211
Practicable route leak detection and protection with ASIRIA
- 18 April 2022
- Published by Elsevier in Computer Networks
- Vol. 211
Open AccessPracticable route leak detection and protection with ASIRIA
- Open Access
- 24 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 94122-94131
An Elephant in the Room: Using Sampling for Detecting Heavy-Hitters in Programmable Switches
The ability to detect elephant flows in the forwarding device itself, i.e., a switch, facilitates the deployment of new advanced applications such as load-balancing, per-flow QoS management, etc. Sketches and Space Saving summarization techniques are used for elephant flow detection. However, their memory and computing requirements force the cooperation of an external controller device, due to the scarce resources of current programmable switches. To overcome this limitation, we adapt Sketch and Space Saving elephant flow detection techniques to operate with instant notification and sampled traffic. We evaluate the performance of the resulting techniques with three real traffic traces. The use of sampling allows the identification of a large share of the total traffic corresponding to the elephant flows with a low memory footprint and a reduction of the computing requirements in two orders of magnitude compared to unsampled versions. In turn, we observe a slight increase in the number of false positives and the number of flow notifications.
- 24 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 94122-94131
Open AccessAn Elephant in the Room: Using Sampling for Detecting Heavy-Hitters in Programmable Switches
The ability to detect elephant flows in the forwarding device itself, i.e., a switch, facilitates the deployment of new advanced applications such as load-balancing, per-flow QoS management, etc. Sketches and Space Saving summarization techniques are used for elephant flow detection. However, their memory and computing requirements force the cooperation of an external controller device, due to the scarce resources of current programmable switches. To overcome this limitation, we adapt Sketch and Space Saving elephant flow detection techniques to operate with instant notification and sampled traffic. We evaluate the performance of the resulting techniques with three real traffic traces. The use of sampling allows the identification of a large share of the total traffic corresponding to the elephant flows with a low memory footprint and a reduction of the computing requirements in two orders of magnitude compared to unsampled versions. In turn, we observe a slight increase in the number of false positives and the number of flow notifications.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 15 (3) , 3528-3539
Design and Implementation of InBlock—A Distributed IP Address Registration System
The current mechanism to secure Border Gateway Protocol relies on the resource public key infrastructure (RPKI) for route origin authorization. The RPKI implements a hierarchical model that intrinsically makes lower layers in the hierarchy susceptible to errors and abuses from entities placed in higher layers. In this article, we present InBlock, a distributed autonomous organization that provides decentralized management of IP addresses based on blockchain, embedding an alternative trust model to the hierarchical one currently implemented by the RPKI. By leveraging on blockchain technology, InBlock requires consensus among the involved parties to change existent prefix allocation information. InBlock also fulfills the same objectives as the current IP address allocation system, i.e., uniqueness, fairness, conservation, aggregation, registration, and minimized overhead. InBlock is implemented as a set of blockchain smart contracts in Ethereum, performing all the functions needed for the management of a global pool of addresses without human intervention. Any entity may request an allocation of addresses to the InBlock registry by solely performing a (crypto) currency transfer to the InBlock. We describe our InBlock implementation and we perform several experiments to show that it enables fast address registering and incurs in very low management costs.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 15 (3) , 3528-3539
Design and Implementation of InBlock—A Distributed IP Address Registration System
The current mechanism to secure Border Gateway Protocol relies on the resource public key infrastructure (RPKI) for route origin authorization. The RPKI implements a hierarchical model that intrinsically makes lower layers in the hierarchy susceptible to errors and abuses from entities placed in higher layers. In this article, we present InBlock, a distributed autonomous organization that provides decentralized management of IP addresses based on blockchain, embedding an alternative trust model to the hierarchical one currently implemented by the RPKI. By leveraging on blockchain technology, InBlock requires consensus among the involved parties to change existent prefix allocation information. InBlock also fulfills the same objectives as the current IP address allocation system, i.e., uniqueness, fairness, conservation, aggregation, registration, and minimized overhead. InBlock is implemented as a set of blockchain smart contracts in Ethereum, performing all the functions needed for the management of a global pool of addresses without human intervention. Any entity may request an allocation of addresses to the InBlock registry by solely performing a (crypto) currency transfer to the InBlock. We describe our InBlock implementation and we perform several experiments to show that it enables fast address registering and incurs in very low management costs.
- 3 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 28 (3) , 1074-1087
Power Prefixes Prioritization for Smarter BGP Reconvergence
BGP reconvergence events involving a large number of prefixes may result in the loss of large amounts of traffic. Based on the observation that a very small number of prefixes carries the vast majority of traffic, we propose Power Prefixes Prioritization (PPP) to ensure the routes of these popular BGP prefixes converge first. By doing so, we significantly reduce the amount of traffic lost during reconvergence events. To achieve this, PPP obtains an ordered list of popular prefixes through traffic inspection, and configures the resulting prefix rank in the BGP routers to prioritize the processing and advertisement of BGP routes. We model the benefits of PPP over traditional BGP processing in terms of traffic loss for both generic and a Zipf traffic distribution, and we consider the impact of sampling in the process of obtaining the prefix rank. Applying the mechanism to real traffic traces obtained from WIDE, we show that PPP reduces the amount of traffic lost by an order of magnitude, even when we configure it to use conservative sampling rates. We prototype our proposal in Quagga to show the feasibility of its implementation, and we observe similar traffic loss reduction. PPP can be deployed incrementally, as it is implemented purely as a change in the router-internal BGP processing behavior.
- 3 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 28 (3) , 1074-1087
Power Prefixes Prioritization for Smarter BGP Reconvergence
BGP reconvergence events involving a large number of prefixes may result in the loss of large amounts of traffic. Based on the observation that a very small number of prefixes carries the vast majority of traffic, we propose Power Prefixes Prioritization (PPP) to ensure the routes of these popular BGP prefixes converge first. By doing so, we significantly reduce the amount of traffic lost during reconvergence events. To achieve this, PPP obtains an ordered list of popular prefixes through traffic inspection, and configures the resulting prefix rank in the BGP routers to prioritize the processing and advertisement of BGP routes. We model the benefits of PPP over traditional BGP processing in terms of traffic loss for both generic and a Zipf traffic distribution, and we consider the impact of sampling in the process of obtaining the prefix rank. Applying the mechanism to real traffic traces obtained from WIDE, we show that PPP reduces the amount of traffic lost by an order of magnitude, even when we configure it to use conservative sampling rates. We prototype our proposal in Quagga to show the feasibility of its implementation, and we observe similar traffic loss reduction. PPP can be deployed incrementally, as it is implemented purely as a change in the router-internal BGP processing behavior.
- 14 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 67 (4) , 1459-1475
A Distributed Autonomous Organization for Internet Address Management
The current system to manage the global pool of IP addresses is centralized in five transnational organizations, known as regional internet registries (RIRs). Each of them manages the address pool for many countries. In this paper, we present InBlock, a distributed autonomous organization that provides the decentralized management of IP addresses. The InBlock also fulfills the same objectives as those fulfilled by the current IP address allocation organizations, i.e., uniqueness, fairness, conservation, aggregation, registration, and minimized overhead. The InBlock is implemented as a set of blockchain’s smart contracts in Ethereum, and it implements all the functions needed for the management of a global pool of addresses without any human intervention. Any entity may request an allocation of addresses to the InBlock registry by performing a (crypto)currency transfer to the InBlock. The fee required, along with the annual renewal fee, serves as a mechanism to deter stockpiling and other wasteful practices. As with any novel technology, there are many open questions about the usage of blockchains to build an IP address registry. For this reason, we believe that practical experimentation is required in order to have hands-on experience, so we propose to conduct an experiment on the InBlock as a starting point to inform about the future directions in this space.
- 14 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 67 (4) , 1459-1475
A Distributed Autonomous Organization for Internet Address Management
The current system to manage the global pool of IP addresses is centralized in five transnational organizations, known as regional internet registries (RIRs). Each of them manages the address pool for many countries. In this paper, we present InBlock, a distributed autonomous organization that provides the decentralized management of IP addresses. The InBlock also fulfills the same objectives as those fulfilled by the current IP address allocation organizations, i.e., uniqueness, fairness, conservation, aggregation, registration, and minimized overhead. The InBlock is implemented as a set of blockchain’s smart contracts in Ethereum, and it implements all the functions needed for the management of a global pool of addresses without any human intervention. Any entity may request an allocation of addresses to the InBlock registry by performing a (crypto)currency transfer to the InBlock. The fee required, along with the annual renewal fee, serves as a mechanism to deter stockpiling and other wasteful practices. As with any novel technology, there are many open questions about the usage of blockchains to build an IP address registry. For this reason, we believe that practical experimentation is required in order to have hands-on experience, so we propose to conduct an experiment on the InBlock as a starting point to inform about the future directions in this space.
- 19 April 2016
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 10 (4) , 925-944
Energy-optimal collaborative file distribution in wired networks
- 19 April 2016
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 10 (4) , 925-944
Energy-optimal collaborative file distribution in wired networks
- Open Access
Designing Low Cost and Energy Efficient Access Network for the Developing World
Internet is growing rapidly in the developing world now. Our survey of four networks in India, all having at least one thousand users, suggest that both installation cost and recurring cost due to power consumption pose a challenge in its deployment in developing countries. In this paper, we first model the access design problem by dividing the users in two types 1) those that may access the network anytime and 2) those who need it only during office hours on working days. The problem is formulated as a binary integer linear program which turns out to be NP-hard. We then give a distributed heuristic for network design. We evaluate our model and heuristic using real data collected from IIT Kanpur LAN for more than 50 days. Results show that even in a tree topology -- which is a common characteristic of all networks who participated in our study, our design can reduce the energy consumption of the network by up to 11% in residential-cum-office environments and up to 22% in office-only environments in comparison with current methods without giving up on the performance. The extra cost incurred due to our design can be compensated in less than an year by saving in electricity bill of the network.
Open AccessDesigning Low Cost and Energy Efficient Access Network for the Developing World
Internet is growing rapidly in the developing world now. Our survey of four networks in India, all having at least one thousand users, suggest that both installation cost and recurring cost due to power consumption pose a challenge in its deployment in developing countries. In this paper, we first model the access design problem by dividing the users in two types 1) those that may access the network anytime and 2) those who need it only during office hours on working days. The problem is formulated as a binary integer linear program which turns out to be NP-hard. We then give a distributed heuristic for network design. We evaluate our model and heuristic using real data collected from IIT Kanpur LAN for more than 50 days. Results show that even in a tree topology -- which is a common characteristic of all networks who participated in our study, our design can reduce the energy consumption of the network by up to 11% in residential-cum-office environments and up to 22% in office-only environments in comparison with current methods without giving up on the performance. The extra cost incurred due to our design can be compensated in less than an year by saving in electricity bill of the network.