Alberto Blanc

Transcoding live adaptive video streams at a massive scale in the cloud

More and more users are watching online videos produced by non-professional sources (e.g., gamers, teachers of online courses, witnesses of public events) by using an increasingly diverse set of devices to access the videos (e.g., smartphones, tablets, HDTV). Live streaming service providers can combine adaptive streaming technologies and cloud computing to satisfy this demand. In this paper, we study the problem of preparing live video streams for delivery using cloud computing infrastructure, e.g., how many representations to use and the corresponding parameters (resolution and bit-rate). We present an integer linear program (ILP) to maximize the average user quality of experience (QoE) and a heuristic algorithm that can scale to large number of videos and users. We also introduce two new datasets: one characterizing a popular live streaming provider (Twitch) and another characterizing the computing resources needed to transcode a video. They are used to set up realistic test scenarios. We compare the performance of the optimal ILP solution with current industry standards, showing that the latter are sub-optimal. The solution of the ILP also shows the importance of the type of video on the optimal streaming preparation. By taking advantage of this, the proposed heuristic can efficiently satisfy a time varying demand with an almost constant amount of computing resources.

Urban 802.11 Community Networks for Mobile Users: Current Deployments and Prospectives

Few years ago some network operators launched a new service called Community Networks, where each subscriber shares its residential Internet connection with other subscribers of the same operator via his 802.11 access point. Due to the high access point density in urban areas, community networks have the potential to offer high data rate wireless Internet access for mobile users, going beyond the currently available hot-spots, which are typically deployed in a limited number of isolated locations (e.g., airports, cafes). Unlike cellular networks, the locations of community network access points is not centrally planned. We evaluate existing community networks using a participatory sensing application called Wi2Me. First, we analyze different metrics in order to characterize community networks. Second, we take advantage of this unique 802.11 network (in terms of density and coverage) to study how mobility can be supported by identifying drawbacks and proposing some possible solutions.

Wi2Me: A Mobile Sensing Platform for Wireless Heterogeneous Networks

With the increasing popularity of WiFi technologies, mobile users may now take advantage of heterogeneous wireless networks. In contrast to cellular networks, community networks, based on sharing WiFi residential accesses, show a high access points density in urban areas but uncontrolled performance. We present Wi2Me Traces Explorer, an extensible mobile sensing application to characterize current deployments. This application allows any mobile user to gather not only access point locations but also their performance in terms of bandwidth, link quality and successful connection rate.

Access Point discovery in 802.11 networks

This paper analyzes the scanning process in IEEE 802.11 networks in an urban setting characterized by a high Access Point (AP) density. Most of these APs belong to a community network, known as a collection of APs announcing the same network name (Service Set Identifier or SSID). The owner of an AP can optionally configure the community network of his/her AP, resulting in an irregular topology for each community network as there is no central planning authority. We investigate the relationship between the time spent in each channel while scanning for available APs and the number of AP actually detected. In particular we show that, in order to discover all available APs at a given location, we need to combine the results of multiple scans. Based on this result we argue that the efficiency of the scanning process could be greatly improved by using a database shared by all the users of a community network, containing the available APs at different locations.

Minimal access point set in urban area Wifi networks

Faced by the large number of deployed Wifi Access Points (AP), many research efforts focus on energy savings in Wireless Local Networks. One of the most promising solutions for improving energy efficiency is the Sleep Mode approach, which is especially effective in dense deployments. It is based on switching off the APs while they are not in use, in order to avoid unnecessary energy consumption. In this paper we evaluate the potential of switching off APs using real measurements taken in a dense urban area. We collected traces for more than 20 hours, confirming the high density of currently deployed APs in such an environment. Based on these traces, we evaluate how many APs can be switched off while maintaining the same coverage. To this end, we propose two algorithms that select the minimum set of APs needed to provide full coverage. We compute several performance parameters, and evaluate the proposed algorithms in terms of the number of selected APs, and the coverage they provide. Our results show that between 4.25% and 10.91% of the detected APs are sufficient to provide the same coverage, depending on the data set, the mobile terminal and the AP selection algorithm.

Instantaneous throughput prediction in cellular networks: Which information is needed?

Downlink data rates can vary significantly in cellular networks, with a potentially non-negligible effect on the user experience. Content providers address this problem by using different representations (e.g., picture resolution, video resolution and rate) of the same content and switch among these based on measurements collected during the connection. If it were possible to know the achievable data rate before the connection establishment, content providers could choose the most appropriate representation from the very beginning. We have conducted a measurement campaign involving 60 users connected to a production network in France, to determine whether it is possible to predict the achievable data rate using measurements collected, before establishing the connection to the content provider, on the operators network and on the mobile node. We show that it is indeed possible to exploit these measurements to predict, with a reasonable accuracy, the achievable data rate.

Delay and quality metrics in Voice over LTE (VoLTE) networks: An end-terminal perspective

In this paper we evaluate metrics specified in 3GPP to characterize trade-offs between delay and quality of Voice over LTE (VoLTE) mobile phones in various network conditions. We report test results on clock accuracy, terminal delay in uplink and downlink under error-free conditions, as well as delay and quality in the presence of packet losses and network jitter. We discuss how the underlying methodology intended for delay testing can be extended to evaluate de-jitter buffer performance using a black-box approach, and how to model VoLTE packet delay/loss characteristics in a realistic way.

Handover triggering in IEEE 802.11 networks

The current and future IEEE 802.11 deployment could potentially offer wireless Internet connectivity to mobile users. The limited AP radio coverage forces mobile devices to perform frequent handovers while current operating systems lack efficient mechanisms to manage AP transition. Thus we propose an anticipation-based handover solution that uses a Kalman filter to predict the short term evolution of the received power. This mechanism allows a mobile device to proactively start scanning and executing a handover as soon as better APs are available. We implement our mechanism in Android and we show that our solution provides a better wireless connection.

Computing end-to-end QoS paths in the Internet considering multiple alliances

Value added services like VoIP, videoconferencing and IPTV need end-to-end Quality of Service (QoS) guarantees in order to work correctly. As the Internet is a collection of Autonomous Systems (AS), most of the time the communication endpoints belong to different ASes, so that all the ASes traversed by the communication must cooperate in order to offer end-to-end guarantees. Yet each AS is usually unwilling to disclose any detail about its internal network. To address this confidentiality issue we propose a system where each AS publishes a list of offers, specifying the QoS guarantees between its entry and exit points, without specifying anything else about its internal network. As proposed in several works, it is also possible for ASes to form alliances, which can be seen as “macro ASes” that publish the available offers between the entry and exit points of the alliance. In this paper we present ACQA, an algorithm that can find end-to-end paths satisfying given QoS constraints by combining the offers of several alliances and/or ASes.

Predicting file downloading time in cellular network: Large-Scale analysis of machine learning approaches

Abstract Downlink data rates can vary significantly in cellular networks, with a potentially non-negligible effect on the user experience. Content providers address this problem by using different representations (e.g., picture resolution, video resolution and rate) of the same content and switch among these based on measurements collected during the connection. Knowing the achievable data rate before the connection establishment should definitely help content providers to choose the most appropriate representation from the very beginning. We have conducted several large measurement campaigns involving a panel of users connected to a production network in France, to determine whether it is possible to predict the achievable data rate using measurements collected, before establishing the connection to the content provider, on the operator’s network and on the mobile node. We establish evidence that it is indeed possible to exploit these measurements to predict, with an acceptable accuracy, the achievable data rate. We thus introduce cooperation strategies between the mobile user, the network operator and the content provider to implement such anticipatory solution.