One way latency estimation without clock synchronization
A method for determining whether clock skew may exist between a sending node and a remote node during two-way network testing (using protocols such as TWAMP), and a computational method for revising measured latency data to compensate for clock differences. The method for compensating for clock skew comprises monitoring the network latency between two nodes during a defined time interval. When clock skew is detected, a flag is set, and, after the time interval has completed, clock skew S is estimated using the minimum latency values for the interval. The recorded latency values for the interval are then revised using the calculated clock skew S, and one-way latency results reported. The improved accuracy can be achieved with only on a few computations after the data have been collected. This a posteriori approach saves on computational resources, which can be at a premium for network testing equipment.
1. A method for revising latency measurements in a communication network comprising at least two nodes, a near node and a far node, comprising:
sending time stamped data from the near node to the far node, receiving corresponding return time stamped data at the near node from the far node during a defined time interval and time stamping the data received;
determining minimum, maximum, and average values for both far end latency and near end latency from the time stamped data received from the far node over the defined time interval;
calculating a clock offset for the far node relative to the near node using a minimum value for far end latency and a minimum value for near end latency;
determining revised minimum, maximum, and average values for far end latency and near end latency from the previously determined values using the calculated clock offset; and
reporting the revised minimum, maximum, and average values for far end latency and near end latency to a network operator to indicate network performance corresponding to the defined time interval.
2. The method of claim 1 , wherein:
the time stamped data sent from the near node to the far node comprises data packets formatted according to a standard latency testing protocol.
3. The method of claim 2 , wherein:
the standard latency testing protocol is one of a Two-Way Active Measurement Protocol (TWAMP) or a Y.1731 ETH-DM test.
4. The method of claim 1 , further comprising:
the steps of sending time stamped data and of determining values for latency occur repeatedly within the defined time interval.
5. The method of claim 1 , wherein:
the defined time interval corresponds to a predetermined network performance reporting interval.
6. The method of claim 1 , wherein:
the defined time interval is less than or equal to 5 minutes in duration.
7. The method of claim 1 , wherein:
the calculation of the clock offset, and
the determination of the revised minimum, maximum, and average values for the far end latency and the near end latency using the calculated clock offset,
occur after the defined time interval has ended.
8. The method of claim 1 , additionally comprising:
conducting limit checks on the revised minimum, maximum, and average values for the far end latency and the near end latency.
9. The method of claim 8 , wherein:
the limit checks comprise at least one of:
checking that the revised values of L FE (min) and L NE (min) are both≥0;
checking that the revised values of L FE (min) and L NE (min) are both≤L RT (min);
checking that the revised values of L FE (max) and L NE (max) are both≤L RT (max);
checking that the revised values of L NE (ave)≥L NE (min);
checking that the revised values of L NE (ave)≤L NE (max);
checking that the revised values of L FE (ave)≥L FE (min);
checking that the revised values of L FE (ave)≤L FE (max).
10. The method of claim 1 , wherein:
the calculation of the clock offset for the far node relative to the near node uses a minimum value for far end latency and a minimum value for near end latency from a time interval prior to the defined time interval.
11. The method of claim 1 , wherein:
the calculation of the clock offset for the far node relative to the near node uses a minimum value for far end latency and a minimum value for near end latency from the defined time interval.
12. The method of claim 11 , wherein:
the calculation of the clock offset occurs after completion of the defined time interval.
13. The method of claim 1 , additionally comprising:
during a prior time interval occurring before the defined time interval,
sending time stamped data from the near node to the far node, and receiving corresponding return time stamped data at the near node from the far node;
determining minimum, maximum, and average values for both far end latency and near end latency from the time stamped data received from the far node over the prior time interval; and
checking for anomalies in timestamped data and the minimum, maximum, and average values for the far end latency and the near end latency when compared to round trip latency.
14. The method of claim 13 , wherein:
the step of checking for anomalies comprises at least one of:
checking that the timestamps are sequential; or
checking that both far end latency and near end latency are less than round trip latency; or
checking that neither far end latency or near end latency have negative values.
15. The method of claim 13 , wherein:
the time stamped data sent from the near node to the far node during the prior time interval comprises data packets formatted according to a standard latency testing protocol.
16. The method of claim 15 , wherein:
the standard latency testing protocol is one of a Two-Way Active Measurement Protocol (TWAMP) or a Y.1731 ETH-DM test.
17. The method of claim 1 , wherein:
the reporting of the revised minimum, maximum, and average values for far end latency and near end latency to a network operator,
comprises displaying the latency results on a screen connected to the near node.
18. The method of claim 1 , wherein:
the reporting of the revised minimum, maximum, and average values for far end latency and near end latency to a network operator,
comprises sending a report to a remote location through the Internet.
19. A system comprising:
memory;
one or more processors coupled to the memory, the memory being loaded with computer instructions to test a communications network comprising at least two nodes, a near node and a far node, the computer instructions, when executed on the one or more processors, implement operations comprising:
sending time stamped data from the near node to the far node, receiving corresponding return time stamped data at the near node from the far node during a defined time interval and time stamping the data received;
determining minimum, maximum, and average values for both far end latency and near end latency from the time stamped data received from the far node over the defined time interval;
calculating a clock offset for the far node relative to the near node using a minimum value for far end latency and a minimum value for near end latency;
determining revised minimum, maximum, and average values for far end latency and near end latency from the previously determined values using the calculated clock offset; and
reporting the revised minimum, maximum, and average values for far end latency and near end latency to a network operator to indicate network performance corresponding to the defined time interval.
20. A non-transitory computer readable storage medium impressed with computer program instructions to test a communications network comprising at least two nodes, a near node and a far node, the computer instructions, when executed on one or more processors, implement operations comprising:
sending time stamped data from the near node to the far node, receiving corresponding return time stamped data at the near node from the far node during a defined time interval and time stamping the data received;
determining minimum, maximum, and average values for both far end latency and near end latency from the time stamped data received from the far node over the defined time interval;
calculating a clock offset for the far node relative to the near node using a minimum value for far end latency and a minimum value for near end latency;
determining revised minimum, maximum, and average values for far end latency and near end latency from the previously determined values using the calculated clock offset; and
reporting the revised minimum, maximum, and average values for far end latency and near end latency to a network operator to indicate network performance corresponding to the defined time interval.