Our technical reports are published as Technical Reports by IMDEA Networks (ISSN to be determined). We employ our TRs as a means of time-stamping as yet unpublished scientific work: when one of our papers is submitted to a conference or journal for peer review, the authors release a dated TR version of the paper through this webpage.
Volumen I (2012)
- Cardona Juan Camilo and Stanojevic Rade and Cuevas Rubén (2012)
On Weather and Internet Traffic Demand - Technical Report ( )
The weather is known to have a major impact on demand of utilities such as electricity or gas. Given that the Internet usage is strongly tied with human activity, one could guess the existence of similar correlation between its traffic demand and the weather conditions. In this paper, empirical in nature, we demonstrate and quantify such correlation between weather conditions and the Internet traffic demand on different time-scales (from hourly to yearly). For that purpose we collect and use the data from 8 Internet eXchange Points (IXP), geographically spread on 5 different continents, as indicators of the Internet demand in those particular areas. We observe that the seasonal traffic demand variability exists in the locations with large yearly variations in temperature, while the traffic demand in locations close to the equator (with low variability of temperature) is season independent. Using a fine-grain dataset, from three European IXPs, we show that precipitation increases the traffic demand for up to 6%, and somewhat surprisingly that in regards to the impact of precipitation on the demand all major types of ISPs (mobile, residential, content, etc.) observe very similar behavior. One of the implications of the observed time-of-the-day dependent impact of the precipitation is that precipitation has a mild impact on the IP transit costs. Finally, we hint on the possible benefits of the seasonal variations on the energy-proportional computing and scheduling large-scale software releases. - Wang Qing and Rengarajan Balaji (2012)
Recouping Opportunistic Gain in Dense Base Station Layouts Through Energy-Aware User Cooperation ( )
To meet the increasing demand for wireless capacity, future networks are likely to consist of dense layouts of small cells. Thus, the number of concurrent users served by each base station is likely to be small resulting in diminished gains from opportunistic scheduling, particularly under dynamic traffic loads. We propose user-initiated traffic spreading, that is transparent to base stations, in order to extract higher opportunistic gain and improve downlink performance. For a specified tradeoff between energy consumption and performance, we characterize the optimal policy by modelling the system as a Markov decision process and also present a tractable heuristic that yields significant performance gains even in multi-user scenarios. Our simulations show that, in the performance-centric case, average delays can be lowered by up to 25% even in homogeneous scenarios where users have identical channel distribution, and up to 51% with heterogeneous users. Further, we show that the bulk of the performance improvement can be achieved with very small increase in energy consumption, e.g., in an energy-sensitive scenario, up to 73% of the performance improvement can typically be achieved at 14% of the energy cost of the performance-centric case.
Volumen I (2011)
- Fernández Anta Antonio and Mosteiro Miguel A. and Muñoz Jorge Ramón (2011)
Unbounded Contention Resolution in Multiple-Access Channels ( TR-IMDEA Networks-2011-1 )
A frequent problem in settings where a unique resource must be shared among users is how to resolve the contention that arises when all of them must use it, but the resource allows only for one user each time. The application of efficient solutions for this problem spans a myriad of settings such as radio communication networks or databases. For the case where the number of users is unknown but fixed, recent work has yielded fruitful results for local area networks and radio networks, although either the solution is suboptimal or a (possibly loose) upper bound on the number of users needs to be known. In this paper, we present the first (two) protocols for contention resolution in radio networks that are asymptotically optimal (with high probability), work without collision detection, and do not require information about the number of contenders. The protocols are evaluated and contrasted with the previous work by extensive simulations. These show that the complexity bounds obtained by the analysis are rather tight, and that the two protocols proposed have small and predictable complexity for all system sizes (unlike previous proposals). - Hasan Syed and Gorinsky Sergey (2011)
Obscure Giants: Detecting the Provider-Free ASes ( TR-IMDEA Networks-2011-3 )
Internet 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. - Mozo Alberto and Lopéz-Presa José Luis and Fernández Anta Antonio (2011)
B-Neck: a distributed and quiescent max-min fair algorithm ( TR-IMDEA Networks-2011-2 )
The problem of fairly distributing a network capacity among a set of sessions has been widely studied. In this problem, each session connects via a single path a source and a destination, and its objective is to maximize its as- signed transmission rate (i.e., its throughput). Since the links of the network have limited bandwidth, some form of criterion has to be defined to fairly distribute them among the sessions. A popular criterion is max-min fairness that, in short, guarantees that each session i gets a rate λi such that no session s can increase λs without causing another session s′ to end up with a rate λs′< λs. Many max-min fair algorithms have been proposed, both centralized and distributed. However, to our knowledge, all proposed distributed algorithms require control packets being continuously transmitted to recompute the max-min fair rates when needed. In this paper we propose B-Neck, a max-min fair distributed algorithm that is also quiescent. This means that, in absence of changes (i.e., session arrivals or departures), once the max-min rates have been computed B-Neck stops generating network traffic. As far as we know, B-Neck is the first max-min fair distributed algorithm that does not require a continuous injection of control traffic to compute the rates. When changes occur, affected sessions are asynchronously informed of their new rate (i.e., sessions do not need to poll the network for changes). The correctness of B-Neck is formally proved, and extensive simulations are conducted. In them it is shown that B-Neck converges relatively fast and behaves nicely in presence of sessions arriving and departing. - Stanojevic Rade and Castro Ignacio and Gorinsky Sergey (2011)
CIPT: Using Tuangou to Reduce IP Transit Costs ( TR-IMDEA Networks-2011-4 )
A majority of ISPs (Internet Service Providers) support connectivity to the entireInternet by transiting their traffic via other providers. Although the transit prices per Mbps decline steadily, the overall transit costs of these ISPs remain high or even increase, due to the traffic growth. The discontent of the ISPs with the high transit costs has yielded notable innovations such as peering, content distribution networks, multicast, and peer-to-peer localization. While the above solutions tackle the problem by reducing the transit traffic, this paper explores a novel approach that reduces the transit costs without altering the traffic. In the proposed CIPT (Cooperative IP Transit), multiple ISPs cooperate to jointly purchase IP (Internet Protocol) transit in bulk. The aggregate transit costs decrease due to the economies-of-scale effect of typical subadditive pricing as well as burstable billing: not all ISPs transit their peak traffic during the same period. To distribute the aggregate savings among the CIPT partners, we propose Shapley-value sharing of the CIPT transit costs. Using public data about IP traffic and transit prices, we quantitatively evaluate CIPT and show that significant savings can be achieved, both in relative and absolute terms. We also discuss the organizational embodiment, relationship with transit providers, traffic confidentiality, and other aspects of CIPT.