Industrial Internet of Things applications need strict Quality of Service guarantees, including when they use wireless networks. While existing standardization efforts, such as Deterministic Networks (IETF) and Time-Sensitive Networking (TSN), have focused mainly on wired networks, more recent activities address wireless networks, like the Reliable and Available Wireless (RAW) Working Group of the IETF. Duplicating packets over multiple paths can improve availability and reliability, but this can potentially result in more out-of-order packets. Existing reordering algorithms, including two recently standardized by the IETF, are not always well suited to wireless networks. As a result, guaranteeing a bounded end-to-end latency and/or maximum consecutive packet losses is still particularly challenging. We propose a novel packet reordering algorithm for deterministic networking that includes wireless segments to achieve lower end-to-end latency while providing high end-to-end reliability. We simulate a 6TiSCH wireless network to compare its performance with the existing ones. Furthermore, we also extend existing Network Calculus bounds on the reordering timer to obtain path-dependent values that can reduce the average latency. We also introduce a probabilistic model to compute the reordering ratio when there are no retransmissions that fits the simulation results.

A Participatory Cloud Infrastructure (PCI) is a collaborative framework designed to host services for a virtual community thanks to residential devices contributed by its members. In this work, we deploy on these devices a photo-sharing application based on microservices. The placement of services on devices significantly influences the overall performance of the application. To address this concern, we present a heuristic able to find a placement that approximates the ideal application response-time in constant time. Our proposed approach has undergone validation within a real infrastructure, revealing the necessity for dynamic adjustments of service placements. Consequently, we introduce a comprehensive adaptation process for placement and an associated specialized strategy.

International audience

Today's network operators strive to create self-healing cellular networks that have a fully automated troubleshooting management process. To this end, the network monitoring system should be capable of detecting issues, diagnosing them, and triggering the adequate recovery action. In this paper, we propose an unsupervised solution to diagnose the root causes of network issues. As monitoring systems collect a large number of logs from the different devices in their networks, it is possible to determine which connections resulted in a poor user experience and apply a failed/successful label. Our solution, Automatic Root Cause Diagnosis (ARCD), analyzes labeled connection logs to identify the major contributors to the network inefficiency (e.g., a faulty core device) as well as the incompatibilities between different elements (e.g., make and model of a phone not being able to access a service). We evaluate the effectiveness of our solution by using logs from three different real cellular networks. In each case, ARCD was able to identify the major contributors and the most widespread incompatibilities. In the three cases, the precision (detection accuracy) and the recall (detection rate) are higher than 90%.

It is now feasible for consumers to buy inexpensive devices that can be installed at home and accessed remotely thanks to an Internet connection. Such a simple "self-hosting" can be an alternative to traditional cloud providers, especially for privacy-conscious users. We discuss how a community of users can pool their devices in order to host microservices-based applications, where each microservice is deployed on a different device. The performance of such an application depends heavily on the computing and network resources that are available and on the placement of each microservice. Finding the placement that minimizes the application response time is an NP-hard problem. We show that, thanks to well known optimization techniques (Particle Swarm Optimization), it is possible to quickly find a service placement resulting in a response time close to the optimal one. Thanks to an emulation platform, we evaluate the robustness of this solution to changes in the Quality of Service under conditions typical of a residential access network.

For a successful and efficient network supervision, an Anomaly Detection System is essential. In this paper, our goal is to develop a simple, practical, and application-domain specific approach to identify anomalies in the input/output data of network probes. Since data are periodic and continuously evolving, it is not possible to use threshold-based approaches. We propose an algorithm based on pattern recognition to help mobile operators detect anomalies in real time. The algorithm is unsupervised and easily configurable with a small number of tuning parameters. After weeks of deployment in a production network monitoring system, we obtain satisfactory results: we detect major anomalies with low error rate.

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 operator's 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.

In this paper, we present experimental results on WebRTC voice quality as a function of LTE radio coverage. Different LTE radio conditions were tested by varying the radio path loss (with fast fading) in controlled test lab conditions. Voice quality was evaluated at different speech coding bit rates in terms of POLQA score and mouth-to-ear delay. Results show that, with acknowledged mode (AM) data transmission over LTE, degraded radio coverage translate essentially into increased end-to-end delay and jitter, with virtually no packet loss up to the coverage limit. Voice quality is analyzed by studying the influence of the specific jitter buffer used in WebRTC endpoints.

Simulations are an essential tool for studying wire- less networks, yet great care must be taken when choosing the simulation parameters, in order to have results reflecting what would happen in a real network. Thanks to extensive traces containing scan results collected by pedestrian users in an urban setting, we select the parameters of different NS-3 modules so that the results obtained match what we observed in a real setting, contrary to what happens if one uses the default values of these modules. We extend the NS-3 simulator in order to faithfully simulate the scanning phase and in order to dynamically change the IP address assigned to Mobile Stations. Finally, we use the simulation parameters that have produced realistic results to analyze what happens when the Access Point density changes.

Today, WiFi networks are widely deployed all over the world, with high Access Point (AP) density in urban areas. Both end-users and network operators are trying to exploit this density by combining multiple APs into “community networks,” in order to share Internet connectivity, and possibly other services. WiFi networks suffer from decentralized management and a lack of coordination in frequency allocation and power control. In order to better use and configure these uncoordinated deployments, the first step is to characterize them. This paper presents a collaborative platform, where mobile stations collect simple network measurements (e.g., the presence of an AP) and send these measurements to a central system. By gathering and processing several network measurements from different mobile users, the platform characterizes the network deployment. This paper presents two applications: 1) minimal AP set, to reduce the energy needed to provide WiFi coverage in a given area, and 2) optimal scanning parameters, to minimize the time a mobile station needs for the network discovery. These two applications show the system's viability to solve particular problems of community networks.

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.

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.

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.

Adaptive streaming addresses the increasing and heterogeneous demand of multimedia content over the Internet by offering several encoded versions for each video sequence. Each version (or representation) is characterized by a resolution and a bit rate, and it is aimed at a specific set of users, like TV or mobile phone clients. While most existing works on adaptive streaming deal with effective playout-buffer control strategies on the client side, in this article we take a providers' perspective and propose solutions to improve user satisfaction by optimizing the set of available representations. We formulate an integer linear program that maximizes users' average satisfaction, taking into account network dynamics, type of video content, and user population characteristics. The solution of the optimization is a set of encoding parameters corresponding to the representations set that maximizes user satisfaction. We evaluate this solution by simulating multiple adaptive streaming sessions characterized by realistic network statistics, showing that the proposed solution outperforms commonly used vendor recommendations, in terms of user satisfaction but also in terms of fairness and outage probability. The simulation results show that video content information as well as network constraints and users' statistics play a crucial role in selecting proper encoding parameters to provide fairness among users and to reduce network resource usage. We finally propose a few theoretical guidelines that can be used, in realistic settings, to choose the encoding parameters based on the user characteristics, the network capacity and the type of video content.

Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over the Internet by offering several streams for each video. Each stream has a different resolution and bit rate, aimed at a specific set of users, e.g., TV, mobile phone. While most existing works on adaptive streaming deal with optimal playout-control strategies at the client side, in this paper we concentrate on the providers' side, showing how to improve user satisfaction by optimizing the encoding parameters. We formulate an integer linear program that maximizes users' average satisfaction, taking into account the network characteristics, the type of video content, and the user population. The solution of the optimization is a set of encoding parameters that outperforms commonly used vendor recommendations, in terms of user satisfaction and total delivery cost. Results show that video content information as well as network constraints and users' statistics play a crucial role in selecting proper encoding parameters to provide fairness among users and reduce network usage. By combining patterns common to several representative cases, we propose a few practical guidelines that can be used to choose the encoding parameters based on the user base characteristics, the network capacity and the type of video content.

Using simulations, we analyze the performance of new TCP variants currently used in the Internet and that gradually replacing TCP NewReno, as they are already activated by default in operating systems or network equipment. We compare these new variants using some metrics that have been recently standardized in order to evaluate new congestion control mechanisms. We observe a trade-off between more aggressive variants that have good performances but a bad impact on the network state and the other flows, and fairer variants with lower performances.

In a peer-to-peer network, nodes are typically required to route packets for each other. This leads to a problem of "free-loaders", nodes that use the network but refuse to route other nodes' packets. In this paper we study ways of designing incentives to discourage free-loading. We model the interactions between nodes as a "random matching game", and describe a simple reputation system that provides incentives for good behavior. Under certain assumptions, we obtain a stable subgame-perfect equilibrium. We use simulations to investigate the robustness of this scheme in the presence of noise and malicious nodes, and we examine some of the design trade-offs. We also evaluate some possible adversarial strategies, and discuss how our results might apply to real peer-to-peer systems.