Exploiting Functional Connectivity Inference for Efficient Root Cause Analysis

Abstract

A crucial step in remedying faults within network infrastructure is to determine their root cause. However, the large-scale, complex and dynamic nature of modern architecture makes root cause analysis challenging. Statistical approaches for causal inference are promising, however, their deployment has been historically limited due to their high time complexity. In this paper we propose a general framework for leveraging the concept of functional connectivity to reduce the computational overhead of causal inference algorithms. We demonstrate on synthetic data that our approach can achieve substantial speedups when combined with state-of-the-art causal discovery algorithms, with only a small cost in terms of loss of causal information in some cases.

Accelerating Causal Inference Based RCA Using Prior Knowledge From Functional Connectivity Inference

“…2A and 2B demonstrate that both PC and THP exhibit exponential time complexity, with THP revealing a markedly large computational overhead, taking 61hrs to complete on only a network size of 200 nodes. 1 However, by exploiting the prior knowledge provided by the FC inference, the computational overhead of both algorithms was reduced. This reduction was more pronounced for THP, decreasing the processing time on the largest network by a factor 200, from 61hrs to 900s on a network of 200 nodes.…”

“…This research was funded by Moogsoft Ltd. and describes patented features of its product.An early iteration of the framework was discussed in our Network Operations and Management Symposium poster[1].…”