Estimating data transfer performance improvement that is expected to be achieved by a network optimization device
Systems and techniques are described for calculating performance improvement achieved and/or expected to be achieved by optimizing a network connection. Network characteristics can be measured for non-optimized network connections. Next, the network characteristics can be analyzed to obtain a set of non-optimized connection groups, wherein each non-optimized connection group corresponds to non-optimized network connections that have similar network characteristics. Network characteristics for an optimized network connection can be measured. Next, a non-optimized connection group can be identified based on the network characteristics that were measured for the optimized network connection. A performance improvement metric can then be calculated based on a throughput of the optimized network connection and corresponding throughputs of non-optimized network connections in the identified non-optimized connection group.
1. A method for estimating performance improvement that is achieved or that is expected to be achieved by optimizing a network connection, the method comprising:
measuring first network characteristics for a set of network connections that are not optimized;
analyzing the first network characteristics to obtain a set of connection groups, wherein each connection group corresponds to network connections that are not optimized and that have similar network characteristics;
measuring second network characteristics for an optimized network connection that is not in the set of network connections;
identifying a connection group corresponding to the optimized network connection based on the second network characteristics; and
calculating, by a computer, a performance improvement metric based on a throughput of the optimized network connection and corresponding throughputs of network connections that belong to the identified connection group, wherein the performance improvement metric represents a throughput improvement expected in a particular network connection belonging to the identified connection group when the particular network connection is optimized.
2. The method of claim 1 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using multivariable clustering.
3. The method of claim 1 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using a machine learning or a data analytic technique that groups elements that have similar attributes.
4. The method of claim 1 , wherein a network characteristic is one of: connection start time, connection end time, source internet protocol (IP) address, destination IP address, destination port, application name or identifier, byte volume, round trip time (RTT), and packet loss.
5. The method of claim 1 , wherein throughput of a given network connection is measured during a time period when a data rate of the given network connection is greater than a threshold.
6. The method of claim 1 , further comprising calculating an overall performance improvement metric for a network by calculating an average performance improvement metric over multiple network connections.
7. A non-transitory computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to perform a method for estimating performance improvement that is achieved or that is expected to be achieved by optimizing a network connection, the method comprising:
measuring first network characteristics for a set of network connections that are not optimized;
analyzing the first network characteristics to obtain a set of connection groups, wherein each connection group corresponds to network connections that are not optimized and that have similar network characteristics;
measuring second network characteristics for an optimized network connection that is not in the set of network connections;
identifying a connection group corresponding to the optimized network connection based on the second network characteristics; and
calculating a performance improvement metric based on a throughput of the optimized network connection and corresponding throughputs of network connections that belong to the identified connection group, wherein the performance improvement metric represents a throughput improvement expected in a particular network connection belonging to the identified connection group when the particular network connection is optimized.
8. The non-transitory computer-readable storage medium of claim 7 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using multivariable clustering.
9. The non-transitory computer-readable storage medium of claim 7 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using a machine learning or a data analytic technique that groups elements that have similar attributes.
10. The non-transitory computer-readable storage medium of claim 7 , wherein a network characteristic is one of: connection start time, connection end time, source internet protocol (IP) address, destination IP address, destination port, application name or identifier, byte volume, round trip time (RTT), and packet loss.
11. The non-transitory computer-readable storage medium of claim 7 , wherein throughput of a given network connection is measured during a time period when a data rate of the given network connection is greater than a threshold.
12. The non-transitory computer-readable storage medium of claim 7 , further comprising calculating an overall performance improvement metric for a network by calculating an average performance improvement metric over multiple network connections.
13. An apparatus, comprising:
a processor; and
a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the processor to perform a method for estimating performance improvement that is achieved or that is expected to be achieved by optimizing a network connection, the method comprising:
measuring first network characteristics for a set of network connections that are not optimized;
analyzing the first network characteristics to obtain a set of connection groups, wherein each connection group corresponds to network connections that are not optimized and that have similar network characteristics;
measuring second network characteristics for an optimized network connection that is not in the set of network connections;
identifying a connection group corresponding to the optimized network connection based on the second network characteristics; and
calculating a performance improvement metric based on a throughput of the optimized network connection and corresponding throughputs of network connections that belong to the identified connection group, wherein the performance improvement metric represents a throughput improvement expected in a particular network connection belonging to the identified connection group when the particular network connection is optimized.
14. The apparatus of claim 13 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using multivariable clustering.
15. The apparatus of claim 13 , wherein said analyzing the first network characteristics to obtain the set of connection groups compromises using a machine learning or a data analytic technique that groups elements that have similar attributes.
16. The apparatus of claim 13 , wherein a network characteristic is one of: connection start time, connection end time, source internet protocol (IP) address, destination IP address, destination port, application name or identifier, byte volume, round trip time (RTT), and packet loss.
17. The apparatus of claim 13 , wherein throughput of a given network connection is measured during a time period when a data rate of the given network connection is greater than a threshold.
18. The apparatus of claim 13 , further comprising calculating an overall performance improvement metric for a network by calculating an average performance improvement metric over multiple network connections.