Framework for automated application-to-network root cause analysis
A computing system comprising a memory and processing circuitry may perform the techniques. The memory may store time series data comprising measurements of one or more performance indicators. The processing circuitry may determine, based on the time series data, an anomaly in the performance of the network system, and create, based on the time series data, a knowledge graph. The processing circuitry may determine, in response to detecting the anomaly, and based on the knowledge graph and a machine learning (ML) model trained with previous time series data, a causality graph. The processing circuitry may determine a weighting for each edge in the causality graph, determine, based on the edges in the causality graph, a candidate root cause associated with the anomalies, and determine a ranking of the candidate root cause based on the weighting. The analysis framework system may output at least a portion of the ranking.
1. A method comprising:
receiving, by an analysis framework system from devices of a network system, time series data comprising measurements of one or more performance indicators;
determining, by the analysis framework system and based on the time series data, one or more anomalies in a performance of the network system;
creating, based on the time series data, a knowledge graph comprising first nodes in the network system referenced in the time series, the first nodes representing elements residing at one or more of a plurality of network service layers associated with the network system;
determining, by the analysis framework system in response to detecting the one or more anomalies, and based on the knowledge graph and a machine learning (ML) model trained with previous time series data, a causality graph, wherein the causality graph includes second nodes associated with the performance indicators, wherein edges between the first nodes and the second nodes indicate relationships between the first nodes and the second nodes, and wherein the knowledge graph and the causality graph each includes edges between one or more of the first nodes and one or more of the second nodes that are associated with elements residing at different network service layers of the plurality of network service layers;
determining a weighting for each of the edges in the causality graph;
determining, based on the edges in the causality graph, one or more candidate root causes associated with the one or more anomalies;
determining a ranking of the one or more candidate root causes based on the weighting of the edges in the causality graph; and
outputting at least a portion of the ranking.
2. The method of claim 1 , wherein outputting comprises outputting, for display, the at least the portion of the ranking.
3. The method of claim 1 , further comprising:
in response to determining the one or more anomalies and prior to determining the causality graph, pruning the knowledge graph to remove first nodes that are more than a threshold distance away from the first nodes of the knowledge graph that are associated with the one or more anomalies,
wherein determining the causality graph comprises determining the causality graph based on the pruned knowledge graph.
4. The method of claim 1 ,
wherein the machine learning model comprises a first machine learning model, and
wherein determining the one or more anomalies comprises determining the one or more anomalies based on passing the time series data through a second machine learning model trained on the previous time series data.
5. The method of claim 1 , wherein determining the one or more anomalies comprises determining the one or more anomalies based on static rules.
6. The method of claim 1 , wherein the network service layers include an application layer, a compute layer, a pod layer, a device layer, and a fabric layer.
7. The method of claim 1 , wherein determining the causality graph comprises determining the causality graph using a Granger causality algorithm.
8. The method of claim 1 , wherein determining the weighting of the edges in the causality graph comprises determining Pearson coefficients of the edges.
9. The method of claim 1 , wherein determining the weighting of an edge of the edges in the causality graph comprises determining the weighting based on an anomaly status of neighbor nodes to a first node associated with the edge.
10. The method of claim 1 , wherein determining the weighting of an edge of the edges in the causality graph comprises determining the weighting of the edge according to a count of persistent events associated with the edge.
11. A computing system comprising:
a memory configured to store time series data comprising measurements of one or more performance indicators received from devices of a network system; and
processing circuitry configured to execute an analysis framework system, the analysis framework system configured to:
determine, based on the time series data, one or more anomalies in a performance of the network system;
create, based on the time series data, a knowledge graph comprising first nodes in the network system referenced in the time series, the first nodes representing elements residing at one or more of a plurality of network service layers associated with the network system;
determine, in response to detecting the one or more anomalies, and based on the knowledge graph and a machine learning (ML) model trained with previous time series data, a causality graph, wherein the causality graph includes second nodes associated with the performance indicators, wherein edges between the first nodes and the second nodes indicate relationships between the first nodes and the second nodes, and wherein the knowledge graph and the causality graph each includes edges between one or more of the first nodes and one or more of the second nodes that are associated with elements residing at different network service layers of the plurality of network service layers;
determine a weighting for each of the edges in the causality graph;
determine, based on the edges in the causality graph, one or more candidate root causes associated with the one or more anomalies;
determine a ranking of the one or more candidate root causes based on the weighting of the edges in the causality graph; and
output at least a portion of the ranking.
12. The computing system of claim 11 , wherein the processing circuitry is configured to output, for display, the at least the portion of the ranking.
13. The computing system of claim 11 ,
wherein the processing circuitry is further configured to, in response to determining the one or more anomalies and prior to determining the causality graph, prune the knowledge graph to remove first nodes that are more than a threshold distance away from the first nodes of the knowledge graph that are associated with the one or more anomalies, and
wherein the processing circuitry is configured to determine the causality graph based on the pruned knowledge graph.
14. The computing system of claim 11 ,
wherein the machine learning model comprises a first machine learning model, and
wherein the processing circuitry is configured to determine the one or more anomalies based on passing the time series data through a second machine learning model trained on the previous time series data.
15. The computing system of claim 11 , wherein the processing circuitry is configured to determine the one or more anomalies based on static rules.
16. The computing system of claim 11 , wherein the network service layers include an application layer, a compute layer, a pod layer, a device layer, and a fabric layer.
17. The computing system of claim 11 , wherein the processing circuitry is configured to determine the causality graph using a Granger causality algorithm.
18. The computing system of claim 11 , wherein the processing circuitry is configured to determine Pearson coefficients of the edges.
19. The computing system of claim 11 , wherein the processing circuitry is configured to determine the weighting based on an anomaly status of neighbor nodes to a first node associated with the edge.
20. Non-transitory computer-readable storage media having instructions stored thereon that, when executed, cause one or more processors to execute a framework analysis system, wherein the framework analysis system is configured to:
receive, from one or more devices of a network system, time series data comprising measurements of one or more performance indicators;
determine, based on the time series data, one or more anomalies in a performance of the network system;
create, based on the time series data, a knowledge graph comprising first nodes in the network system referenced in the time series, the first nodes representing elements residing at one or more of a plurality of network service layers associated with the network system;
determine, in response to detecting the one or more anomalies, and based on the knowledge graph and a machine learning (ML) model trained with previous time series data, a causality graph, wherein the causality graph includes second nodes associated with the performance indicators, wherein edges between the first nodes and the second nodes indicate relationships between the first nodes and the second nodes, and wherein the knowledge graph and the causality graph each includes edges between one or more of the first nodes and one or more of the second nodes that are associated with elements residing at different network service layers of the plurality of network service layers;
determine a weighting for each of the edges in the causality graph;
determine, based on the edges in the causality graph, one or more candidate root causes associated with the one or more anomalies;
determine a ranking of the one or more candidate root causes based on the weighting of the edges in the causality graph; and
output at least a portion of the ranking.