No abstract

Abstract-While real-time service assurance is critical for emerging telecom cloud services, understanding and predicting performance metrics for such services is hard. In this paper, we pursue an approach based upon statistical learning whereby the behavior of the target system is learned from observations. We use methods that learn from device statistics and predict metrics for services running on these devices. Specifically, we collect statistics from a Linux kernel of a server machine and predict client-side metrics for a video-streaming service (VLC). The fact that we collect thousands of kernel variables, while omitting service instrumentation, makes our approach serviceindependent and unique. While our current lab configuration is simple, our results, gained through extensive experimentation, prove the feasibility of accurately predicting client-side metrics, such as video frame rates and RTP packet rates, often within 10-15% error (NMAE), also under high computational load and across traces from different scenarios.

No abstract

Maximizing connection availability in wavelength division multiplexing (WDM) networks is critical because even small disruptions can cause huge data losses. However, there is a trade-off between the level of network survivability and the cost related to the backup resources to be provided. One-hundred percent survivability can be achieved by dedicated path protection (DPP) with multiple prereserved protection paths for each provisioned connection, i.e., DPP (1∶N). Unfortunately, the blocking probability performance of DPP (1∶N) is negatively affected by the large number of prereserved backup wavelengths standing by unutilized. On the other hand, path restoration (PR)-based solutions ensure good blocking performance at the expense of lower connection availability. The work in this paper aims at finding hybrid network survivability strategies that combine the benefits of both techniques (i.e., high availability with low blocking rate). More specifically, the paper focuses on a double link failure scenario and proposes two strategies. The first one couples DPP (1∶1) with path restoration (referred to as DPP PR) to minimize the number of dropped connections. The second scheme adds the concept of backup reprovisioning (BR), referred to as DPP BR PR, in order to further increase the connection availability achieved by DPP PR. Integer linear programming models for the implementation of the proposed schemes are formulated. Extensive performance evaluation conducted in a path-computation-elementbased WDM network scenario shows that DPP BR PR and DPP PR can significantly lower the blocking probability value compared to DPP (1∶2) without compromising too much in terms of connection availability.

Abstract-Predicting the performance of cloud services is intrinsically hard. In this work, we pursue an approach based upon statistical learning, whereby the behaviour of a system is learned from observations. Specifically, our testbed implementation collects device statistics from a server cluster and uses a regression method that accurately predicts, in real-time, clientside service metrics for a video streaming service running on the cluster. The method is service-agnostic in the sense that it takes as input operating-systems statistics instead of servicelevel metrics. We show that feature set reduction significantly improves prediction accuracy in our case, while simultaneously reducing model computation time. We also discuss design and implementation of a real-time analytics engine, which processes streams of device statistics and service metrics from testbed sensors and produces model predictions through online learning.