Showing papers by "Sonia Fahmy published in 2020"

RoCC: robust congestion control for RDMA

Abstract: In this paper, we present RoCC, a robust congestion control approach for datacenter networks based on RDMA. RoCC leverages switch queue size as an input to a PI controller, which computes the fair data rate of flows in the queue, signaling it to the flow sources. The PI parameters are self-tuning to guarantee stability, rapid convergence, and fair and near-optimal throughput in a wide range of congestion scenarios. Our simulation and DPDK implementation results show that RoCC can achieve up to 7× reduction in PFC frames generated under high average load levels, compared to DCQCN. At the same time, RoCC can achieve up to 8× lower tail latency, compared to DCQCN and HPCC. We also find that RoCC does not require PFC. The functional components of RoCC are implementable in P4-based and fixed-function switch ASICs.

Experience: towards automated customer issue resolution in cellular networks

Abstract: Cellular service carriers often employ reactive strategies to assist customers who experience non-outage related individual service degradation issues (e.g., service performance degradations that do not impact customers at scale and are likely caused by network provisioning issues for individual devices). Customers need to contact customer care to request assistance before these issues are resolved. This paper presents our experience with PACE (ProActive customer CarE), a novel, proactive system that monitors, troubleshoots and resolves individual service issues, without having to rely on customers to first contact customer care for assistance. PACE seeks to improve customer experience and care operation efficiency by automatically detecting individual (non-outage related) service issues, prioritizing repair actions by predicting customers who are likely to contact care to report their issues, and proactively triggering actions to resolve these issues. We develop three machine learning-based prediction models, and implement a fully automated system that integrates these prediction models and takes resolution actions for individual customers. We conduct a large-scale trace-driven evaluation using real-world data collected from a major cellular carrier in the US, and demonstrate that PACE is able to predict customers who are likely to contact care due to non-outage related individual service issues with high accuracy. We further deploy PACE into this cellular carrier network. Our field trial results show that PACE is effective in proactively resolving non-outage related individual customer service issues, improving customer experience, and reducing the need for customers to report their service issues.

Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations

Abstract: We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics. Making the problem harder, we assume that the states we wish to predict are unobserved in the training data. Specifically, given a parametric model over the transition rates of a CTMC and some known transition rates, we wish to extrapolate its steady state distribution to states that are unobserved. A technical roadblock to learn a CTMC from its steady state has been that the chain rule to compute gradients will not work over the arbitrarily long sequences necessary to reach steady state —from where the aggregate statistics are sampled. To overcome this optimization challenge, we propose ∞-SGD, a principled stochastic gradient descent method that uses randomly-stopped estimators to avoid infinite sums required by the steady state computation, while learning even when only a subset of the CTMC states can be observed. We apply ∞-SGD to a real-world testbed and synthetic experiments showcasing its accuracy, ability to extrapolate the steady state distribution to unobserved states under unobserved conditions (heavy loads, when training under light loads), and succeeding in difficult scenarios where even a tailor-made extension of existing methods fails.

Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations

Abstract: We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics. Making the problem harder, we assume that the states we wish to predict are unobserved in the training data. Specifically, given a parametric model over the transition rates of a CTMC and some known transition rates, we wish to extrapolate its steady state distribution to states that are unobserved. A technical roadblock to learn a CTMC from its steady state has been that the chain rule to compute gradients will not work over the arbitrarily long sequences necessary to reach steady state ---from where the aggregate statistics are sampled. To overcome this optimization challenge, we propose $\infty$-SGD, a principled stochastic gradient descent method that uses randomly-stopped estimators to avoid infinite sums required by the steady state computation, while learning even when only a subset of the CTMC states can be observed. We apply $\infty$-SGD to a real-world testbed and synthetic experiments showcasing its accuracy, ability to extrapolate the steady state distribution to unobserved states under unobserved conditions (heavy loads, when training under light loads), and succeeding in difficult scenarios where even a tailor-made extension of existing methods fails.