Incident Management for Explainable and Automated Root Cause Analysis in Cloud Data Centers

Effective root cause analysis (RCA) of performance issues in modern cloud environ- ments remains a hard problem. Traditional RCA tracks complex issues by their signatures known as problem incidents. Common approaches to incident discovery rely mainly on expertise of users who define environment-specific set of alerts and >target detection of problems through their occurrence in the monitoring system. Adequately modeling of all possible problem patterns for nowadays extremely sophisticated data center applications is a very complex task. It may result in alert/event storms including large numbers of non-indicative precautions. Thus, the crucial task for the incident-based RCA is reduction of redundant recommendations by prioritizing those events subject to importance/impact criteria or by deriving their meaningful groupings into separable situations. In this paper, we consider automation of incident discovery based on rule induction algorithms that retrieve conditions directly from monitoring datasets without consuming the sys- tem events. Rule-learning algorithms are very flexible and powerful for many regression and classification problems, with high-level explainability. Since annotated or labeled data sets are mostly unavailable in this area of technology, we discuss data self-labelling principles which allow transforming originally unsupervised learning tasks into classification problems with further application of rule induction methods to incident detection.

Fast but Not Furious. When Sped Up Bit Rate of Information Drives Rule Induction

The language abilities of young and adult learners range from memorizing specific items to finding statistical regularities between them (item-bound generalization) and generalizing rules to novel instances (category-based generalization). Both external factors, such as input variability, and internal factors, such as cognitive limitations, have been shown to drive these abilities. However, the exact dynamics between these factors and circumstances under which rule induction emerges remain largely underspecified. Here, we extend our information-theoretic model (Radulescu et al., 2019), based on Shannon’s noisy-channel coding theory, which adds into the “formula” for rule induction the crucial dimension of time: the rate of encoding information by a time-sensitive mechanism. The goal of this study is to test the channel capacity-based hypothesis of our model: if the input entropy per second is higher than the maximum rate of information transmission (bits/second), which is determined by the channel capacity, the encoding method moves gradually from item-bound generalization to a more efficient category-based generalization, so as to avoid exceeding the channel capacity. We ran two artificial grammar experiments with adults, in which we sped up the bit rate of information transmission, crucially not by an arbitrary amount but by a factor calculated using the channel capacity formula on previous data. We found that increased bit rate of information transmission in a repetition-based XXY grammar drove the tendency of learners toward category-based generalization, as predicted by our model. Conversely, we found that increased bit rate of information transmission in complex non-adjacent dependency aXb grammar impeded the item-bound generalization of the specific a_b frames, and led to poorer learning, at least judging by our accuracy assessment method. This finding could show that, since increasing the bit rate of information precipitates a change from item-bound to category-based generalization, it impedes the item-bound generalization of the specific a_b frames, and that it facilitates category-based generalization both for the intervening Xs and possibly for a/b categories. Thus, sped up bit rate does not mean that an unrestrainedly increasing bit rate drives rule induction in any context, or grammar. Rather, it is the specific dynamics between the input entropy and the maximum rate of information transmission.

A Rule Induction Framework on the Effect of ‘Negative’ Attributes to Academic Performance

Attaining high retention rates among engineering institutions is a predominant is-sue. A significant portion of engineering students face challenges of retention. Academic advising was implemented to resolve the issue. Decision support sys-tems were developed to support the endeavor. Machine learning have been inte-grated among such systems in predicting student performance accurately. Most works, however, rely on a black box model approach. Rule induction generates simpler if-then rules, exhibiting clearer understanding. As most research works considered attributes for positive academic performance, there is the need to con-sider ‘negative’ attributes. ‘Negative’ attributes are critical indicators to possibility of failure. This work applied rule induction techniques for course grade predic-tion using ‘negative’ attributes. The dataset is the academic performance of 48 mechanical engineering students taking a machine design course. Students’ at-tributes on workload, course repetition, and incurred absences are the predictors. This work implemented two rule induction techniques, rough set theory (RST) and adaptive neuro fuzzy inference system (FIS). Both models attained a classifi-cation accuracy of 70.83% with better performance for course grades of ‘Pass’ and ‘High’. RST generated 16 crisp rules while ANFIS generated 27 fuzzy rules, yielding significant insights. Results of this study can be used for comparative analysis of student traits between institutions. The illustrated framework can be used in formulating linguistic rules of other institutions.