IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Power-efficient Assignment of Virtual Machines to Physical Machines
Get PDFWorkshop held in conjunction with PODC 2014.Motivated by current trends in cloud computing, we study a version of the generalized assignment problem where a set of virtual processors has to be implemented by a set of identical processors. For literature consistency, we say that a set of virtual machines (VMs) is assigned to a set of physical machines (PMs). The optimization criteria is to minimize the power consumed by all the PMs. We term the problem Virtual Machine Assignment (VMA). Crucial differences with previous work include a variable number of PMs, that each VM must be assigned to exactly one PM (i.e., VMs cannot be implemented fractionally), and a minimum power
consumption for each active PM. Such infrastructure may be strictly constrained in the number of PMs or in the PMs’ capacity, depending on how costly (in terms of power consumption) it is to add a new PM to the system or to heavily load some of the existing PMs. Low usage or ample budget yields models where PM capacity and/or the number of PMs may be assumed unbounded for all practical purposes. We study four VMA problems depending on whether the capacity or the number of PMs is bounded or not. Specifically, we study hardness and online competitiveness for a variety of cases. To the best of our knowledge, this is the first comprehensive study of the VMA problem for this cost function.TRUEpu
Energy-Efficient Optimization for Distributed Opportunistic Scheduling
No full textDistributed Opportunistic Scheduling (DOS) exploits multiuser diversity in wireless networks without the requirement of a central scheduler. With DOS, users take their own scheduling decisions based on a local observation of the channel to maximize performance. While DOS has been used in the past to optimize throughput-related figures, in this paper we use DOS to optimize the energy performance of the network. We first derive the optimal configuration for the homogeneous scenario, where all devices share the same power consumption behavior, and then propose a heuristic to address the heterogeneous scenario, where devices have different power consumption figures. Simulation results confirm the effectiveness of our approaches.pu
BER Enhancements for Practical Interference Alignment in the Frequency Domain
No full textThe K user interference alignment scheme with symbol extensions proposed by Cadambe and Jafar achieves K/2 degree of freedom in theory for high signal-to-noise ratios (SNRs). However, lower SNR ranges appear in many practical scenarios. Thus, further improvements of the Cadambe-Jafar scheme are demanded to enable interference alignment in more realistic settings. In this work, we propose a new precoding vector optimization that improves bit error rates (BER) using zero-forcing at the receivers. Furthermore, we compare and combine our approach with existing performance enhancement techniques for interference alignment such as orthonormalizing the precoding matrices or using lattice decoding instead of zero-forcing at the receiver. Finally, we implement interference alignment with symbol extension in the frequency domain along with the presented BER enhancement techniques on a soft-ware defined radio platform to validate our approaches. Both simulation results and testbed measurements show significant BER improvements for different M -QAM schemes compared to the original interference alignment mechanism. Moreover, our precoding optimization scheme based on zero-forcing outperforms lattice decoding in practical systems due to its lower sensitivity to real-world effects.TRUEpu
Collaborative Consumption for Mobile Broadband: A Quantitative Study
Get PDFMobile broadband is predominantly priced following tiered plans that involve a certain prepaid commit volume and additional metered volume priced at a higher penalty rate. An individual's demand, however, may vary wildly from month to month and thus users inevitably purchase packages that are either too small or too large for their needs. By collaborating in predefined closed (eg, family) or open groups (eg, through tethering) users can reduce both the amount of paid-but-left-unused capacity or the high penalty rates. In this paper we present a quantitative study of collaborative consumption using data from 40K mobile subscribers and tariffs from ten operators around the world. We show that small 2-person family plans offer modest expected savings in the range of 3\% to 14\%, whereas getting more substantial savings requires rather impractically large groups of approximately 10 people or more. Going over to open groups, where users can freely trade their data capacity, we characterize the impact of the secondary market price on the user costs and the operator revenues, and show that Telcos might be better off to embrace secondary markets (eg, let them integrate with billing), and thus have some control on, as opposed to letting them operate unsupervised through tethering. The latter may severely harm the revenues of a Telco, in an uncontrolled manner, especially in densely populated areas.TRUEpu
A Measurement-based Analysis of the Energy Consumption of Data Center Servers
Get PDFEnergy consumption is a growing issue in data centers, impacting their economic viability and their public image. In this work we empirically characterize the power and energy consumed by different types of servers. In particular, in order to understand the behavior of their energy and power consumption, we perform measurements in different servers. In each of them, we exhaustively measure the power consumed by the CPU, the disk, and the network interface under different configurations, identifying the optimal operational levels. One interesting conclusion of our study is that the curve that defines the minimal CPU power as a function of the load is neither linear nor purely convex as has been previously assumed. Moreover, we find that the efficiency of the various server components can be maximized by tuning the CPU frequency and the number of active cores as a function of the system and network load, while the block size of I/O operations should be always maximized by applications. We also show how to estimate the energy consumed by an application as a function of some simple parameters, like the CPU load, and the disk and network activity. We validate the proposed approach by accurately estimating the energy of a map-reduce computation in a Hadoop platform.TRUEpu
From Africa to Africa: AS-level topology snapshot
No full textOver the last years, an extensive amount of initiatives has been taken by African telecom actors to increase the number of high capacity backbones, and interconnection infrastructures such as Internet eXchange Points.
The goal of this work is to shed light on the state of inter-domain routing in the continent, and monitor its evolution. For this purpose, we deployed 18 RIPE Atlas probes in 11 countries, targeting ISPs where no probes were present. We performed active measurements among a total 116 similar probes hosted in 63 ISPs, covering 28 countries. The measurement campaign lasted 4 months.
We provide the first snapshot of the Intra-African Internet connectivity, and highlight its characteristics. Our results show a large proportion of long paths, in terms of number of intermediate ISPs and Round Trip Times, even for pairs of ASes located in the same region, or even country.
Approximately 80% of the paths between our monitored AS pairs were found to be served via other continents.
We finally discuss transit habits of the studied ASes, based on their business profile, the official language of the country where they operate, and the location of the country they are based in. We highlight the benefits of local peering on the perceived quality of service.
We hope to observe, in our further works, the success of projects aiming at fostering IXPs establishment in the studied area, essentials to attract CDNs, improve quality of service for local users, and reduce the transit costs of local operators.FALSEpu
Microloop prevention by introducting a local convergence delay
Get PDFThis document describes a mechanism for link-state routing protocols to prevent local transient forwarding loops in case of link failure. This mechanism Proposes a two-steps convergence by introducing a delay between the convergence of the node adjacent to the topology change and the network wide convergence. As this mechanism delays the IGP convergence it may only be used for planned maintenance or when fast reroute protects the traffic between the link failure and the IGP convergence. Simulations using real network topologies have been performed and show that local loops are a significant portion (>50%) of the total forwarding loops.pu
Modeling and Analyzing Gamification Behavior with Badges
Get PDFThis manuscript is focused in two of the most prominent techniques for the next years for education advancement, which are learning analytics and gamification. There are a lot of research works in both of these lines independently, but not many research papers combine both techniques in order to improve the educational experience. One of the most used gamification techniques is the use of badges as a reward for making specific student actions. The analysis of users’ interactions and behaviors with the badge system can be used to improve the learning process. We present four high level indicators related to the behavior of students with a badge system and we particularize it for the Khan Academy platform. An extensive analysis of 291 different students interacting with the Khan Academy badge system is done processing real data from freshmen courses at Universidad Carlos III de Madrid. This analysis includes an overview of the global usage of badges, correlations between the badge indicators and other indicators related to the learning process and a Two-Step Cluster Analysis to group students by their badge preferences in order to personalize future experiences.Telematics EngineeringUniversidad Carlos III de Madrid, Spainpu
Asymptotic Competitive Analysis of Task Scheduling Algorithms on a Fault-Prone Machine
Get PDF(Part of a collaborative work with A. Fernández Anta (1), C. Georgiou (3)and D.R. Kowalski (4))
1 IMDEA Networks Institute,
2 Universidad Carlos III de Madrid,
3 University of Cyprus,
4 University of LiverpoolTRUEpu