We introduce ConfSeer, an automated system that detects potential configuration issues or deviations from identified best practices by leveraging a knowledge base (KB) of technical solutions. The intuition is that these KB articles describe the configuration problems and their fixes so if the system can accurately understand them, it can automatically pinpoint both the errors and their resolution. Unfortunately, finding an accurate match is difficult because (a) the KB articles are written in natural language text, and (b) configuration files typically contain a large number of parameters with a high value range. Thus, expert-driven manual troubleshooting is not scalable. While there are several state-of-the-art techniques proposed for individual tasks such as keyword matching, concept determination and entity resolution, none offer a practical end-to-end solution to detect problems in machine configurations. In this paper, we describe our experiences building ConfSeer using a novel combinations of ideas from natural language processing, information retrieval and interactive learning. ConfSeer powers the recommendation engine behind Microsoft Operations Management Suite that proposes fixes for software configuration errors. The system has been running in production for about a year to proactively find misconfigurations on tens of thousands of servers. Our evaluation of ConfSeer against an expert-defined rule-based commercial system, an expert survey and web search engines shows that it achieves 80%-97.5% accuracy and incurs low runtime overheads.

The objective of joint source channel coding (JSCC) is to optimally allocate the available channel bandwidth between source coding and channel coding in order to minimize the average distortion in the presence of packet losses. Unlike previous research, which focuses on determining distortion-optimized methods for JSCC using either assumptions about the rate-distortion (R-D) curve properties of source data (e.g., convexity) or experimental R-D data, we explicitly employ the analytical operational R-D model of a three-dimensional wavelet video coder to solve the JSCC problem. Using this model, we formulated the JSCC optimization as a nonlinear programming (NP) problem. By expressing the NP problem in terms of a dynamic programming equation, we derived the necessary conditions that facilitate the search for global optimal solutions. In this letter, we focus on finding the optimal JSCC problem for subband video coding and not on deriving computationally efficient methods for JSCC.

Based on our statistical investigation of a typical 3D (t+2D/2D+t) wavelet codec, we present a unified mathematical model to describe its rate-distortion (RD) behavior. We assess the quantization distortion of the reconstructed video frames by tracking the quantization noise along the 3D wavelet decomposition trees. The minimum bit rate to achieve this distortion is estimated by the unconditional entropy of the quantizer. Experimental results show that the model captures sequence characteristics accurately and reveals the relationship between wavelet decomposition levels and the overall RD performance.