Binary search-based approach in routing-metric agnostic topologies for node selection to enable effective learning machine mechanisms

An apparatus, comprising:

• one or more network interfaces that communicate with a network;
• a processor coupled to the one or more network interfaces and configured to execute a process;
• and
• a memory configured to store program instructions which contain the process executable by the processor, the process comprising:
• polling nodes in the network for Quality of Service (QoS) measurements;
• detecting a QoS anomaly that affects a plurality of potentially faulty nodes based on the QoS measurements, wherein the plurality of potentially faulty nodes includes a plurality of areas of the network where a faulty node causing the QoS anomaly potentially lies;
• computing a path, which traverses the plurality of potentially faulty nodes, from a first endpoint to a second endpoint, wherein a root node of the network is the first endpoint, and a node of the plurality of potentially faulty nodes is the second endpoint;
• computing a median node of the plurality of potentially faulty nodes that is located at a point along the path between the first endpoint and the second endpoint;
• receiving time-stamped packets from the median node;
• updating the first endpoint and the second endpoint of the path based on the received time-stamped packets to narrow down the plurality of areas of the network where the faulty node causing the QoS anomaly potentially lies, such that an amount of potentially faulty nodes is reduced;
• comparing the received time-stamped packets with previous values to determine whether further narrowing of the plurality of areas of the network should continue or whether a faulty area has been found;
• and
• in response to determining that the faulty area has been found, identifying the faulty node from the reduced amount of potentially faulty nodes.

A tangible non-transitory computer readable medium storing program instructions that cause a computer to execute a process, the process comprising:

• polling nodes in a network for Quality of Service (QoS) measurements;
• detecting a QoS anomaly that affects a plurality of potentially faulty nodes based on the QoS measurements, wherein the plurality of potentially faulty nodes includes a plurality of areas of the network where a faulty node causing the QoS anomaly potentially lies;
• computing a path, which traverses the plurality of potentially faulty nodes, from a first endpoint to a second endpoint, wherein a root node of the network is the first endpoint, and a node of the plurality of potentially faulty nodes is the second endpoint;
• computing a median node of the plurality of potentially faulty nodes that is located at a point along the path between the first endpoint and the second endpoint;
• receiving time-stamped packets from the median node;
• updating the first endpoint and the second endpoint of the path based on the received time-stamped packets to narrow down the plurality of areas of the network where the faulty node causing the QoS anomaly potentially lies, such that an amount of potentially faulty nodes is reduced;
• comparing the received time-stamped packets with previous values to determine whether further narrowing of the plurality of areas of the network should continue or whether a faulty area has been found;
• and
• in response to determining that the faulty area has been found, identifying the faulty node from the reduced amount of potentially faulty nodes.