IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Providing Throughput and Fairness Guarantees in Virtualized WLANs Through Control Theory
Get PDFWith the increasing demand for mobile Internet access, WLAN virtualization is becoming a promising solution for sharing wireless infrastructure among multiple service providers. Unfortunately, few mechanisms have been devised to tackle this problem and the existing approaches fail in optimizing the limited bandwidth and providing virtual networks with fairness guarantees. In this paper, we propose a novel algorithm based on control theory to configure the virtual
WLANs with the goal of ensuring fairness in the resource distribution, while maximizing the total throughput.
Our algorithm works by adapting the contention window configuration of each virtual WLAN to the channel activity in order to ensure optimal operation. We conduct a control-theoretic analysis of our system to appropriately design the parameters of the controller and prove system stability, and undertake an extensive simulation study to show that our proposal optimizes performance under different types of traffic. The results show that the mechanism provides a fair resource distribution independent of the number of stations and their level of activity, and is able to react promptly to changes in the network conditions while ensuring stable operation.TRUEpu
On IEEE 802.3az Energy Efficiency in Web Hosting Centers
Get PDFThis letter presents results from our measurement
campaign conducted in a web hosting center in Madrid. We
collected traffic data to evaluate the potential power saving that could be achieved by replacing the company’s gigabit wired links with the newly released Energy Efficient Ethernet connections(IEEE 802.3az standard). Using traffic traces collected with high precision timestamps, we feed a simulator and use an analytical
model to compute the potential power saving achievable for the monitored link. We reveal that at least 80% of the power, consumed by links and network interfaces, can be saved more than 40% of the time. Furthermore, we show the importance of precise arrival time measurements by post-processing the collected traces to introduce random noise to the original timestamps.TRUEpu
Using Energy Efficient Ethernet (802.3az) in Web Hosting Centers
Get PDFThe contribution of this master thesis is twofold. First we present an analytical model of IEEE 802.3az and second we summarize the results of our measurement campaign conducted
in collaboration between Institute IMDEA Networks and InterHost. The analytical model uses simple traffic parameters to estimate the power consumption of the newly released standard for Energy Efficient Ethernet (EEE), namely IEEE 802.3az. With our measurements, we have characterized the behavior of the aggregate traffic flowing through one of the InterHost company’s firewalls at one of their web hosting centers located in Madrid, Spain. We used the collected data in order to evaluate the potential for power saving that could be achieved by replacing the company’s gigabit wired links with EEE connections. In the thesis, we plot the daily load and the potential power saving computed by simulating the measured traffic with an EEE link simulator as well. Using the presented model for
predicting the EEE power saving from few statistical traffic parameters, we show that the EEE power saving for 1000Base-T links can be estimated with good accuracy. Finally, to show the importance of precise measurements, we first collect high precision timestamps for packet arrivals by means of specialized high resolution hardware, then we post-process the collected traces and introduce uniformly distributed random noise to the original timestamps.
Results show that (i) substantial power saving could be achieved, higher that 40% in the peak hour and as high as 90% overnight, and that (ii) EEE power saving predictions
can be biased by timestamp errors and so, high precision hardware is needed. Last but not least, packet coalescing for EEE is discussed to further reduce the power consumption of links under medium to high load operation.Telematics EngineeringUniversidad Carlos III de Madrid, Spainpu
Obscure Giants: Detecting the Provider-Free ASes
Get PDFInternet routing depends on economic relationships between
ASes (Autonomous Systems). Despite extensive prior research of these relationships, their characterization remains imprecise. In this paper, we focus on provider-free ASes that reach the entire Internet without paying anyone for the traffic delivery. While the ground truth about PFS (set of the provider-free ASes) lies outside the public domain, we use trustworthy non-verifiable sources as a baseline for result validation. Straightforward extraction of PFS from public datasets of inter-AS economic relationships yields poor results. Then, we develop a more sophisticated Temporal Cone (TC) algorithm that relies on topological statistics (customer cones of ASes) and exploits the temporal diversity of the datasets. Our evaluation shows that the TC algorithm infers PFS from the same public datasets with a significantly higher accuracy. We also assess the sensitivity of the TC algorithm to its parameters.TRUEpu
Node Sampling Using Centrifugal Random Walks
No full textAlso in: XX Jornadas de Concurrencia y Sistemas Distribuidos, JCSD 2012, 13-15 June 2012, Pamplona, Spain.We propose distributed algorithms for sampling networks based on a new class of random walks that we call Centrifugal Random Walks (CRW). A CRW is a random walk that starts at a source and alwaysmoves away from it. We propose CRW algorithms for connected networks with arbitrary probability distributions, and for grids and networks with regular concentric connectivity with distance based distributions. All CRW sampling algorithms select a node with the exact probability distribution, do not need warm-up, and end in a number of hops bounded by the network diameter.TRUEpu
Network energy consumption models and energy efficient algorithms
No full textEnergy consumption is a momentous problem that severely challenges further design and application of networks. While most researches work on a local view of some aspects (e.g. some devices used in networks) of the energy consumption problems in networks, there has been scarce research on a global view to reduce the amount of energy consumed at a network level (e.g. routing, network deployment). Energy consumption problem is investigated from network routing aspect in this paper. Energy consumption optimization strategies are developed from the aspect of network routing on the network system level. Combining three traffic arrival modes and three energy adaptation modes, optimized network energy consumption models are presented first. Further some energy efficient routing algorithms are developed for specific system models including the Continuous Flow with Speed Scaling model with bandwidth constraint, and the Continuous Flow with Rate Adaptation model. A model and corresponding algorithm for bi-criteria system are also developed so that a trade-off can be made between energy consumption and network delay. While the models can help understand the energy consumption optimization problems from the aspect of network routing on the network system level, the energy efficient routing algorithms can significantly reduce the energy consumed for network packet transmission. Keywords energy consumption; system model; energy efficient algorithm; optimization; network latency; green computing Background Energy consumption is rapidly increasing with the expanding of network size. Methods to reduce the energy consumption of network elements have drawn significant research interest during the past few years. However, there has been scarce research on algorithms to globally reduce the amount of energy consumed at a network level. This paper constructs five energy consumption system models and presents some energy efficiency scheduling algorithms for some specific system models. The research results of this paper will be useful to devise the energy efficiency algorithms in network. This work is supported by National Natural of Science Foundation of China (Nos. 61020106002). This project aims to provide better energy efficiency and performance in computing networks and information systems. Our group has working on the energy efficiency in computer networks and datacenter. Many good papers have been published in respectable international conferences and journals, such as IEEE Symposium on Foundations of Computer Science (FOCS), IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC), Journal of ACM, IEEE Transaction serial, and Journal of Parallel and Distributed Computing.pu
Energy-performance trade-off in dense WLANs: A queuing study
Get PDFThe increasing concern about the energy consumption of communication networks is driving the research community to identify approaches to save energy in the networks of
today. For instance, considering wireless local area networks (WLANs), the activation of network resources can be driven by the user demand, avoiding having to always power on all Access Points (APs). In this paper, we consider a portion of a dense WLAN system, where many APs are deployed to provide sufficient capacity to serve a large number of active users during peak traffic hours. To provide large capacity, a number of APs are colocated in the same position and provide identical coverage; we say that these APs belong to the same group, and they serve users in the same area. The areas covered by different groups only partially overlap, so that some active users can only be served by a group of APs, but a fraction of active users can be served by several groups. Due to daily variations
of the number of active users accessing the WLAN, some APs can be switched off to save energy when not all the capacity is needed. The main focus of our study is the investigation of the type of algorithm that should be used for the association of active users with APs in order to increase the amount of saved energy in dense WLANs. Results show that when some system state information is available, such as the number of users associated with each AP, the energy consumption can decrease up to 20%. Furthermore, our study gives comprehensive insights on the trade-off between the opposite needs to save energy and provide quality of service to the users.TRUEpu
Greening the Internet: Energy-Optimal File Distribution
Get PDFDespite file distribution applications are responsible for a major portion of the current Internet traffic, so far little effort has been dedicated to study file distribution from the point of view of energy efficiency. In this paper, we present the first extensive and detailed theoretical study for the problem of energy efficiency in file distribution. Specifically, we first demonstrate that the general problem of minimizing energy consumption in file distribution is NP-hard. For restricted versions of the problem, we derive tight lower bounds on energy consumption, and we design a family of algorithms that achieve these bounds. Our results prove that through collaborative p2p schemes up to 50% energy savings are achievable with respect to the best available centralized file distribution scheme. Through simulation, we show that even in heterogeneous settings (e.g., considering network congestion, and link variability across hosts) our collaborative algorithms always achieve significant energy savings with respect to the power consumption of centralized file distribution systems.TRUEpu
Analysis of power saving with continuous connectivity
Get PDFAlways-on mobile users need high bandwidth channels with negligible access delay and limited power consumption. Such a continuous connectivity mode requires the management of high-speed channels, which can turn into substantial operational costs (i.e., power consumption rate) even in presence of low traffic, unless a power saving mechanism is
enforced. In this paper, we analyze the impact of 3GPP-defined power saving mechanisms on the performance of users with continuous connectivity. We develop a model for packet transmission and operational costs. We model each downlink mobile user’s traffic by means of an M/G/1 queue, and the base station’s downlink traffic as an M/G/1 PS queue
with multiple classes and inhomogeneous vacations. The model is validated through packet-level simulations. Our results show that consistent power saving can be achieved
in the wireless access network, as high as 75% for mobiles and 55% for base stations.TRUEpu