We present PRR (Protective ReRoute), a transport technique for shortening user-visible outages that complements routing repair. It can be added to any transport to provide benefits in multipath networks. PRR responds to flow connectivity failure signals, e.g., retransmission timeouts, by changing the FlowLabel on packets of the flow, which causes switches and hosts to choose a different network path that may avoid the outage. To enable it, we shifted our IPv6 network architecture to use the FlowLabel, so that hosts can change the paths of their flows without application involvement. PRR is deployed fleetwide at Google for TCP and Pony Express, where it has been protecting all production traffic for several years. It is also available to our Cloud customers. We find it highly effective for real outages. In a measurement study on our network backbones, adding PRR reduced the cumulative region-pair outage time for RPC traffic by 63--84%. This is the equivalent of adding 0.4--0.8 "nines" of availability.

The load on wireless cellular networks is not uniformly distributed through the day, and is significantly higher during peak periods. In this context, we present MANTIS, a time-shifted prefetching solution that prefetches content during off-peak periods of network connectivity. We specifically focus on YouTube given that it represents a significant portion of overall wireless data-usage. We make the following contributions: first, we collect and analyze a real-life dataset of YouTube watch history from 206 users comprised of over 1.8 million videos spanning over a 1-year period and present insights on a typical user's viewing behavior; second, we develop an accurate prediction algorithm using a K-nearest neighbor classifier approach; third, we evaluate the prefetching algorithm on two different datasets and show that MANTIS is able to reduce the traffic during peak periods by 34%; and finally, we develop a proof-of-concept prototype for MANTIS and perform a user study.

The load on wireless cellular networks is not uniformly distributed through the day, and is significantly higher during peak-times. In this context, we present a time-shifted prefetching solution that prefetches content during off-peak periods of network connectivity. We specifically focus on YouTube as it represents a significant portion of overall cellular data-usage. We make the following contributions: first, we establish that a significant portion of a user's YouTube watch behavior is indeed predictable by analyzing a real-life dataset of YouTube watch history spanning a 1-year period, from 206 users comprised of over 1.8 million videos; second, we develop an accurate prediction algorithm using a K-nearest neighbor classifier approach; and finally, we evaluate the prefetching algorithm on two different datasets and show that MANTIS is able to reduce the traffic during peak periods by 34% for a typical user.

Mobilizing enterprise applications enable employees to perform their job functions on their smartphones, even when away from a Desktop. Among the different strategies used to mobilize web enterprise applications, application refactoring based services are gaining popularity due to their ease of deployment. Refactoring involves hosting the application as-is on the enterprise cloud and allowing a user to interact with it through a smartphone-optimized UI. These services require APIs provided by the applications to accurately map the smartphone UI to the web application UI.

Application Mobilization, or the ability of an enterprise employee to rely on mobile devices such as smartphones and tablets, to continue to perform business workflows even when mobile, is seen as a game changer to improve productivity. However, the practical adoption of enterprise mobility is very much in its in fancy, and seemingly has barriers. We posit that these barriers include heavy user-burden in accomplishing tasks (e.g. number of actions required to execute a workflow), high cost of mobile access (e.g. latency for content fetching), and irrelevance of available mobile functions (e.g. mobile app defeaturization done inappropriately).The novelty of our research is in a unified observe-patternize-mimic paradigm we explore to address these barriers, based on a simple question: could patterns in user-behavior be learned, and leveraged for reducing user-burden? If patterns are discovered, then we show that intelligent mimicking of these patterns at appropriate junctures can considerably relieve the mobile user burden. We motivate this paradigm through three application scenarios representing read, write, and act usage modalities.

More email is opened on mobile devices today than on other platforms [1]. At the same time, enterprises are constantly investing in approaches to improve employee productivity. In this paper, we consider the problem of automated information suggestions to assist in reply construction. The basic premise of the work is that a significant portion of the information content of a reply is likely to be present in prior emails. We first show that the premise is valid by analyzing both public and private email datasets. We then present a simple algorithm that relies on inverse document frequency (IDF) and keyword matching to provide relevant suggestions during reply construction. Through prototype evaluations done using the Email datasets, we show that the proposed algorithm has attractive benefits.

With the great success of LTE(-A) outdoor, LTE-based small cell technology has become popular and is penetrating indoor enterprise environment, co-existing with WiFi networks, to provide better user experience or Quality-of-Experience (QoE). However, accurate estimation of LTE links is challenging and critical to continue providing QoE for many enterprise applications (e.g., video/audio) and services (network selection). While prior work on LTE link throughput estimation depends mostly on a single factor (e.g., link rate), we argue that it needs to consider more factors to improve the estimation to meet increasing demands on QoE. In this paper, we propose a new metric, called Pulsar (Per-user LTE ShAre of Resources), that estimates per flow throughput in LTE networks by leveraging both underlying channel information and application traffic characteristics. Our extensive evaluation study through ns-3 shows that Pulsar reduces the estimation error more than 92%, compared to prior work, in various scenarios, while keeping estimation overhead low.

Multiple Description (MD) source coding is a technique that breaks a media stream into equally important sub-streams which can be sent over different paths for protection against channel errors in wireless networks. In this paper, we explore the possibility of sending the descriptions through different paths and intermediately merging them to exploit recovery of the corrupted descriptions from the uncorrupted ones before reaching the destination, thereby increasing the quality of received media at the destination. We first analytically model the end-to-end distortion of MD coded multipath transmission as a function of the path parameters and prove that intermediate recovery achieves an improvement of up to 9.2% in end-to-end distortion compared to traditional multipath transport. We then formulate the mesh route construction as a cross-layer optimization problem. Since the problem is highly complex, we propose an efficient heuristic routing strategy. We show that using this routing strategy, good paths (with up to 2 intermediate recovery nodes) can be constructed to achieve a lower distortion compared to the case without intermediate recovery.