Valerio Luconi

Smartphone-based crowdsourcing for network monitoring: Opportunities, challenges, and a case study

Smartphone-based crowdsourcing fosters the rise of radically novel systems and applications in the context of network monitoring. This article discusses the most significant opportunities offered by this approach, and the major challenges that have to be faced. Our experience in building a smartphone-based crowdsourcing system, Portolan, is also included to provide a practical background to the discussion and to demonstrate the possible benefits.

A study on traceroute potentiality in revealing the Internet AS-level topology

Several works over the past few years have shown that the Internet AS-level topology is partially hidden from the current Internet measurement infrastructures. Most have focused on the incompleteness of the connectivity extracted from BGP data. A few have analysed the connectivity collected by traceroute measurement infrastructures showing the amount of connections introduced by traceroute campaigns. None, however, have investigated in detail the underlying rationale, i.e. the economic nature of the Internet. In this paper we fill this gap by analysing five traceroute infrastructures, found to be active in October 2013, with the p2c-distance metric, which is specifically designed to capture the complex economic dynamics that rule the Internet. We found that the traceroute infrastructures that currently run topology discovery measurements (Ark, DIMES and Portolan), together with BGP route collectors, are able to reveal the full connectivity of 23.50% of the Internet core ASes. This is a considerable improvement given that the BGP infrastructure alone is able to cover only 15.90% of the Internet core. This percentage could be increased up to 48.48% if the remaining two infrastructures (Dasu/Ono and RIPE Atlas) performed topology discovery campaigns. We also found that the placement of traceroute probes is not optimal from a topology discovery perspective, as it causes several probes to provide only redundant connectivity information. We show that the same number of traceroute probes optimally deployed, would be able to completely reveal the full AS connectivity of the Internet core.

Network sensing through smartphone-based crowdsourcing

Portolan is a crowdsourcing system, aimed at monitoring and measuring large-scale networks, that uses smartphones as mobile observation elements. Currently, Portolan is able to collect information about both wired and wireless networks, in particular it is used to obtain the graph of the Internet with unprecedented resolution and to associate performance indexes (received signal strength, maximum throughput) of cellular networks to geographic locations.

Lessons learned from the design, implementation, and management of a smartphone-based crowdsourcing system

Ubiquitousness of smartphones, when combined with the power of crowdsourcing, enables radically novel application scenarios, where a massive amount of mobile users scattered over wide geographical regions cooperate towards a single goal. Nevertheless these new possibilities come at the cost of additional complexity, such as the presence of humans in the control loop, scarce resources of mobile devices, increased management costs due the large number of users. In this paper we report and discuss the lessons learned from the design, implementation and management of Portolan, a smartphone-based crowdsourcing system aimed at monitoring large-scale networks.

Smartphone-based geolocation of Internet hosts

The location of Internet hosts is frequently used in distributed applications and networking services. Examples include customized advertising, distribution of content, and position-based security. Unfortunately the relationship between an IP address and its position is in general very weak. This motivates the study of measurement-based IP geolocation techniques, where the position of the target host is actively estimated using the delays between a number of landmarks and the target itself. This paper discusses an IP geolocation method based on crowdsourcing where the smartphones of users operate as landmarks. Since smartphones rely on wireless connections, a specific delay-distance model was derived to capture the characteristics of this novel operating scenario.

Measuring the Internet Topology with Smartphones

Despite the very well known smartphone issues such as on-off behaviour and battery/bandwidth limitations, in this paper we show that smartphones can be successfully employed in a crowdsourcing system to perform Internet AS-level topology discovery. We propose and illustrate a measurement methodology that takes these issues into account. We implemented such methodology in Portolan, our smartphone-based crowdsourcing system, and ran six months of measurements. We show that smartphones mobility allows to obtain measurements from 706 different ASes with just 200 active devices. Moreover, we show that our methodology manages to bring novelty with relatively few measurements. On average 27.75% of the AS links found by Portolan are not found by BGP measurements.

AS-Level Topology Discovery: Measurement strategies tailored for crowdsourcing systems

Abstract The rise of crowdsourcing systems for network measurements fosters the design of new measurement paradigms to cope with the limitations of such systems, i.e. devices with scarce resources. In this paper we address the problem of running active measurements for discovering the Internet topology at the autonomous system level of abstraction with crowdsourcing systems. We show how to obtain meaningful results with an extremely low number of measurements. We devise two classes of measurement strategies based on different approaches: topological and historical. We experimentally validate our strategies by comparing them with measurements collected with a broad strategy by Portolan, a crowdsourcing system based on mobile devices. We show that the number of measurements can be reduced up to over 80%, at the cost of a negligible loss of useful information. We finally provide pros and cons of the two classes of strategies along with a detailed analysis of the reasons why the (small) loss of information happens.

Smartphone-based crowdsourcing for estimating the bottleneck capacity in wireless networks

Crowdsourcing enables the fine-grained characterization and performance evaluation of todays large-scale networks using the power of the masses and distributed intelligence. This paper presents SmartProbe, a system that assesses the bottleneck capacity of Internet paths using smartphones, from a mobile crowdsourcing perspective. With SmartProbe measurement activities are more bandwidth efficient compared to similar systems, and a larger number of users can be supported. An application based on SmartProbe is also presented: georeferenced measurements are mapped and used to compare the performance of mobile broadband operators in wide areas. Results from one year of operation are included.

Geolocation of Internet Hosts Using Smartphones and Crowdsourcing

Knowing the position of an Internet host enables location-aware applications and services, such as restriction of content based on users position or customized advertising. Active IP geolocation techniques estimate the position of an Internet host using measurements of the end-to-end delay between the target and a number of landmarks (hosts whose positions are known in advance). We present an IP geolocation method that operates in a crowd sourcing perspective and uses mobile devices as landmarks, since their position can be easily computed using the GPS unit. A specific calibration has been included to take into account the particular operating environment which, differently from the past, includes the presence of wireless links.

Supporting the Development of Network-Aware Reactive Applications on Smartphones

In the last years, research about context-aware systems has been particularly intense. Nevertheless, most of the proposed approaches and systems failed to flow from research to industry. In this paper we propose ANARC, a library that eases the development of network-aware applications for smartphones. ANARC does not try to cope with all the possible meanings and variations of context, it instead focuses on a specific restriction: the network and associated properties. ANARC adopts a rule- and trigger-based approach: when the network context matches the one described in a rule, the corresponding notification is sent to the application level. Examples of use of the proposed library -- for mapping network coverage, detecting roaming regions of mobile operators, and monitoring WiFi access points -- are included to demonstrate the benefits of the proposed approach.