Emir Halepovic

Can you GET me now?: estimating the time-to-first-byte of HTTP transactions with passive measurements

Cellular network operators have a compelling interest to monitor HTTP transaction latency because it is an important component of the user experience. Existing techniques to monitor latency require active probing or use passive analysis to estimate round trip time (RTT). Unfortunately, it is impractical to use active probing to monitor entire cellular networks, and RTT is only one component of HTTP latency in cellular networks. This paper presents a new passive technique to estimate HTTP transaction latency that overcomes the scaling and completeness limitations of prior approaches. We validate our technique in an operational cellular network and present results for traffic in the wild.

TM 3 : flexible t ransport-layer m ulti-pipe m ultiplexing m iddlebox without head-of-line blocking

A primary design decision in HTTP/2, the successor of HTTP/1.1, is object multiplexing. While multiplexing improves web performance in many scenarios, it still has several drawbacks due to complex cross-layer interactions. In this paper, we propose a novel multiplexing architecture called TM3 that overcomes many of these limitations. TM3 strategically leverages multiple concurrent multiplexing pipes in a transparent manner, and eliminates various types of head-of-line blocking that can severely impact user experience. TM3 works beyond HTTP over TCP and applies to a wide range of application and transport protocols. Extensive evaluations on LTE and wired networks show that TM3 substantially improves performance e.g., reduces web page load time by an average of 24% compared to SPDY, which is the basis for HTTP/2. For lossy links and concurrent transfers, the improvements are more pronounced: compared to SPDY, TM3 achieves up to 42% of average PLT reduction under losses and up to 90% if concurrent transfers exist.

OSCAR: an optimized stall-cautious adaptive bitrate streaming algorithm for mobile networks

The design of an adaptive video client for mobile users is challenged by the frequent changes in operating conditions. Such conditions present a seemingly insurmountable challenge to adaptation algorithms, which may fail to find a balance between video rate, stalls, and rate-switching. In an effort to achieve the ideal balance, we design OSCAR, a novel adaptive streaming algorithm whose adaptation decisions are optimized to avoid stalls while maintaining high video quality. Our performance evaluation, using real video and channel traces from both 3G and 4G networks, shows that OSCAR achieves the highest percentage of stall-free sessions while maintaining a high quality video in comparison to the state-of-the-art algorithms.

Back to the Future: Throughput Prediction For Cellular Networks using Radio KPIs

The availability of reliable predictions for cellular throughput would offer a fundamental change in the way applications are designed and operated. Numerous cellular applications, including video streaming and VoIP, embed logic that attempts to estimate achievable throughput and adapt their behaviour accordingly. We believe that providing applications with reliable predictions several seconds into the future would enable profoundly better adaptation decisions and dramatically benefit demanding applications like mobile virtual and augmented reality. The question we pose and seek to address is whether such reliable predictions are possible. We conduct a preliminary study of throughput prediction in a cellular environment using statistical machine learning techniques. An accurate prediction can be very challenging in large scale cellular environments because they are characterized by highly fluctuating channel conditions. Using simulations and real-world experiments, we study how prediction error varies as a function of prediction horizon, and granularity of available data. In particular, our simulation experiments show that the prediction error for mobile devices can be reduced significantly by combining measurements from the network with measurements from the end device. Our results indicate that it is possible to accurately predict achievable throughput up to 8 sec in the future where 50th percentile of all errors are less than 15% for mobile and 2% for static devices.

MIMIC: Using passive network measurements to estimate HTTP-based adaptive video QoE metrics

HTTP-based Adaptive Streaming (HAS) has seen a major growth in the cellular networks. As a key application and network demand driver, user-perceived Quality of Experience (QoE) of video streaming contributes to the overall user satisfaction. Therefore, it becomes critical for the cellular network operators to understand the QoE of video streams. It can help with long-term network planning and provisioning and QoE-aware traffic management. However, tracking QoE is challenging as network operators do not have direct access to the video streaming apps, user devices or servers. In this paper, we provide a methodology that uses passive network measurements of unencrypted HAS video streams to estimate three key video QoE metrics — average bitrate, re-buffering ratio and bitrate switches. Our approach relies on the semantics of HAS to model a video session on the client. We first develop and validate our methodology through controlled experiments in the lab. Then, we conduct a large-scale validation of our approach using network data from a major cellular operator and ground truth QoE metrics from a large video service. We accurately predict the value of average bitrate within a relative error of 10% for 70%–90% of video sessions and re-buffering ratio within 1 percentage point for 65–90% of sessions. We further quantify the network overhead due to video chunk replacement and observe that a significant number of sessions have a high overhead of 20% or more. Finally, we highlight several challenges with video QoE metrics estimation in a large-scale monitoring system.

Incorporating Prediction into Adaptive Streaming Algorithms: A QoE Perspective

Streaming over the wireless channel is challenging due to rapid fluctuations in available throughput. Encouraged by recent advances in cellular throughput prediction based on radio link metrics, we examine the impact on Quality of Experience (QoE) when using prediction within existing algorithms based on the DASH standard. By design, DASH algorithms estimate available throughput at the application level from chunk rates and then apply some averaging function. We investigate alternatives for modifying these algorithms, by providing the algorithms direct predictions in place of estimates or feeding predictions in place of measurement samples. In addition, we explore different prediction horizons going from one to three chunk durations. Furthermore, we induce different levels of error to ideal prediction values to analyse deterioration in user QoE as a function of average error. We find that by applying accurate prediction to three algorithms, user QoE can improve up to 55% depending on the algorithm in use. Furthermore having longer horizon positively affects QoE metrics. Accurate predictions have the most significant impact on stall performance by completely eliminating them. Prediction also improves switching behaviour significantly and longer prediction horizons enable a client to promptly reduce quality and avoid stalls when the throughput drops for a relatively long time that can deplete the buffer. For all algorithms, a 3-chunk horizon strikes the best balance between different QoE metrics and, as a result, achieving highest user QoE. While error-induced predictions significantly lower user QoE in certain situations, on average, they provide 15% improvement over DASH algorithms without any prediction.

FlexStream: Towards Flexible Adaptive Video Streaming on End Devices using Extreme SDN

We present FlexStream, a programmable framework realized by implementing Software-Defined Networking (SDN) functionality on end devices. FlexStream exploits the benefits of both centralized and distributed components to achieve dynamic management of end devices, as required and in accordance with specified policies. We evaluate FlexStream on one example use case -- the adaptive video streaming, where bandwidth control is employed to drive selection of video bitrates, improve stability and increase robustness against background traffic. When applied to competing streaming clients, FlexStream reduces bitrate switching by 81%, stall duration by 92%, and startup delay by 44%, while improving fairness among players. In addition, we report the first implementation of SDN-based control in Android devices running in real Wi-Fi and live cellular networks.

Connected cars in cellular network: a measurement study

Connected cars are a rapidly growing segment of Internet of Things (IoT). While they already use cellular networks to support emergency response, in-car WiFi hotspots and infotainment, there is also a push towards updating their firmware over-the-air (FOTA). With millions of connected cars expected to be deployed over the next several years, and more importantly persist in the network for a long time, it is important to understand their behavior, usage patterns, and impact --- both in terms of their experience, as well as other users. Using one million connected cars on a production cellular network, we conduct network-scale measurements of over one billion radio connections to understand various aspects including their spatial and temporal connectivity patterns, the network conditions they face, use and handovers across various radio frequencies and mobility patterns. Our measurement study reveals that connected cars have distinct sets of characteristics, including those similar to regular smartphones (e.g. overall diurnal pattern), those similar to IoT devices (e.g. mostly short network sessions), but also some that belong to neither type (e.g. high mobility). These insights are invaluable in understanding and modeling connected cars in a cellular network and in designing strategies to manage their data demand.