Long-Term Adaptation and Distributed Detection of Local Network Changes

Abstract

Abstract-We present a statistical approach to distributed detection of local latency shifts in networked systems. For this purpose, response delay measurements are performed between neighbouring nodes via probing. The expected probe response delay on each connection is statistically modelled via parameter estimation. Adaptation to drifting delays is accounted for by the use of overlapping models, such that previous models are partially used as input to future models. Based on the symmetric Kullback-Leibler divergence metric, latency shifts can be detected by comparing the estimated parameters of the current and previous models. In order to reduce the number of detection alarms, thresholds for divergence and convergence are used.The method that we propose can be applied to many types of statistical distributions, and requires only constant memory compared to e.g., sliding window techniques and decay functions. Therefore, the method is applicable in various kinds of network equipment with limited capacity, such as sensor networks, mobile ad hoc networks etc. We have investigated the behaviour of the method for different model parameters. Further, we have tested the detection performance in network simulations, for both gradual and abrupt shifts in the probe response delay. The results indicate that over 90% of the shifts can be detected. Undetected shifts are mainly the effects of long convergence processes triggered by previous shifts. The overall performance depends on the characteristics of the shifts and the configuration of the model parameters.

A Distributed Spatio-Temporal Event Correlation Protocol for Multi-Layer Virtual Networks

“…[14], [17]). When an event E (l) ij is reported in layer l, involved nodes n li and n lj defines the endpoints n s , n e of the affected topology T (l) ij , along with the time t w everything was known to be functional in node n li towards n lj and the time of the detected event t f , where t w < t f .…”

Machine Learning-Based Link Fault Identification and Localization in Complex Networks

“…In [13], [14], the authors presented a consolidated taxonomy on different techniques that have been developed for localizing link faults. These techniques are broadly categorized as rule-based techniques [15], [16], case-based techniques [17], [18], probability-based techniques [19]- [22] and model-based techniques [23], [24]. The rule-based techniques rely on a knowledge base developed by the system experts, which is essentially a set of if-then statements i.e., the rules of the system.…”

Translation of probabilistic QoS in hierarchical and decentralized settings

“…The parameter estimates can also be used as feedback to the QoS translation layer, either by request for optimization purposes, or for triggering a re-optimization due to changed network conditions. For example, probabilistic management mechanisms capable of detecting changes in observed network behaviour could trigger a re-optimization based on a new set of parameter estimates representing the new network behaviour [15].…”