Abstract: A method for anomaly detection and troubleshooting in a network includes parsing a network service descriptor (NSD) describing a network service (NS) to be deployed in the network. Monitoring data including time series of service-level metrics and resource-level metrics of network functions (NFs) of the NS are received from different domains of the network. Representations of the time series from the different domains are learned with a common dimensionality. An NS signature of the NS is computed as a cross-correlation matrix comprising cross-correlations between the service-level metrics and the resource-level metrics of the NFs. Embeddings of the NS signature are learned using a model and determining a reconstruction error of the model. It is determined whether the NS is anomalous based on the reconstruction error of the model. The NS is identified as a target for the troubleshooting in a case that the NS was determined to be anomalous.

Abstract: A method for anomaly detection of cloud services based on mining time-evolving graphs includes steps of receiving tracing data for a plurality of micro-services of the deployed cloud service, wherein the tracing data defines relationships between the plurality of micro-services of the deployed cloud service at a plurality of different time intervals, computing a functional graph based on the tracing data for each of the plurality of different time intervals, wherein nodes of each functional graph include the plurality of micro-services and wherein links between the nodes represent relationships between the plurality of micro-services, comparing the functional graphs for each of the plurality of time intervals to determine an anomaly score for each of the functional graphs, and detecting a presence of one or more anomalies based on the anomaly scores.

Abstract: A method for anomaly detection of cloud services based on mining time-evolving graphs includes steps of receiving tracing data for a plurality of micro-services of the deployed cloud service, wherein the tracing data defines relationships between the plurality of micro-services of the deployed cloud service at a plurality of different time intervals, computing a functional graph based on the tracing data for each of the plurality of different time intervals, wherein nodes of each functional graph include the plurality of micro-services and wherein links between the nodes represent relationships between the plurality of micro-services, comparing the functional graphs for each of the plurality of time intervals to determine an anomaly score for each of the functional graphs, and detecting a presence of one or more anomalies based on the anomaly scores.

Abstract: A method for anomaly detection and troubleshooting in a network includes parsing a network service descriptor (NSD) describing a network service (NS) to be deployed in the network. Monitoring data including time series of service-level metrics and resource-level metrics of network functions (NFs) of the NS are received from different domains of the network. Representations of the time series from the different domains are learned with a common dimensionality. An NS signature of the NS is computed as a cross-correlation matrix comprising cross-correlations between the service-level metrics and the resource-level metrics of the NFs. Embeddings of the NS signature are learned using a model and determining a reconstruction error of the model. It is determined whether the NS is anomalous based on the reconstruction error of the model. The NS is identified as a target for the troubleshooting in a case that the NS was determined to be anomalous.