Statistical traffic classification with adaptive boundaries in a broadband data communications network
An approach for classification of a data traffic session over a data communications network is provided. A network device receives data packets of the data traffic session. The network device determines a plurality statistical factors that characterize the data traffic session based on the received data packets. The network device analyzes the determined statistical factors in relation to a plurality of classification variables, and classifies the data traffic session as being one of a plurality of session priority types based on the analysis, wherein each of a plurality of subsets of the classification variables delineates the plurality of session priority types over a continuum with respect to a corresponding one of the statistical factors.
1. A method for classification of a data traffic session over a data communications network, comprising:
receiving, by a network device of the data communications network, a plurality of data packets of the data traffic session;
determining, by the network device, a plurality of statistical factors that characterize the data traffic session based on the received data packets of the data traffic session;
analyzing, by the network device, the determined statistical factors for the data traffic session in relation to a plurality of classification variables; and
classifying, by the network device, the data traffic session as being one of a plurality of data traffic types/classes based on the analysis of the determined statistical factors for the data traffic session in relation to the plurality of classification variables; and
wherein each of a plurality of subsets of the classification variables reflect boundaries that delineate the plurality of data traffic types/classes over a continuum with respect to a corresponding one of the statistical factors.
2. The method according to claim 1 , wherein the plurality of statistical factors comprise metrics or factors that are identifiable by one or more of data extracted from the received data packets and a determination of characteristics exhibited by the received data packets, and that reflect or indicate a data traffic or priority type of the respective data traffic session.
3. The method according to claim 1 , wherein the plurality of statistical factors comprise one or more of Average Throughput, Maximum Throughput, Session Duration, ON-Duration, OFF-Duration, ON-OFF Ratio, Average ON-Duration, Average OFF-Duration, and Volume, wherein the Average Throughput is a throughput rate over a time period from a start of the data traffic session to a time that the throughput rate is determined, the Maximum Throughput is a highest throughput rate measured during a respective sampling period of the data traffic session, the Session Duration is a time duration from the start of the data traffic session to a most recent state update, the ON-Duration is an accumulated time during which data packets are received over the Session Duration, the OFF-Duration is an accumulated time during which the data packets are not received over the Session Duration, ON-OFF ration is a ratio of the ON-Duration and OFF-Duration, Average ON-Duration is an average of ON time over the Session Duration, Average OFF-Duration is an average of OFF time over the Session Duration, and Volume is a volume of data packets received over a respective time period.
4. The method according to claim 1 , wherein each classification variable of each of the plurality of subsets reflects a threshold between two respective data traffic types/classes with respect to the corresponding statistical factor.
5. The method according to claim 1 , further comprising:
modifying one or more of the classification variables of each of one or more of the plurality of subsets, based on one or more traffic conditions of the data communications network, to adjust the respective boundaries that delineate the plurality of data traffic types/classes over the continuum with respect to the corresponding one of the statistical factors.
6. The method according to claim 5 , wherein the one or more traffic conditions of the data communications network include one or more of bandwidth utilization within each of the data traffic types/classes, bandwidth allocation to each of the data traffic types/classes and network congestion.
7. The method according to claim 5 , wherein the one or more of the classification variables of each of one or more of the plurality of subsets are modified on a periodic basis.
8. The method according to claim 5 , wherein the one or more of the classification variables of each of one or more of the plurality of subsets are modified in order to dynamically adjust the respective boundaries for one or more data traffic types/classes of higher priority than other of the data traffic types/classes to prevent a respective reserved bandwidth level for each of the one or more data traffic types/classes of higher priority from being exceeded.
9. The method according to claim 1 , further comprising:
determining a unique session ID for the data traffic session based one or more identification factors including one or more of source address, source port number, destination address, destination port number and protocol type.
10. A network apparatus for classification of a data traffic session over a data communications network, comprising:
a receiver configured to receive a plurality of data packets of the data traffic session; and
one or more processors configured to (i) determine a plurality of statistical factors that characterize the data traffic session based on the received data packets of the data traffic session, (ii) analyze the determined statistical factors for the data traffic session in relation to a plurality of classification variables, and (iii) classify the data traffic session as being one of a plurality of data traffic types/classes based on the analysis of the determined statistical factors for the data traffic session in relation to the plurality of classification variables; and
wherein each of a plurality of subsets of the classification variables reflect boundaries that delineate the plurality of data traffic types/classes over a continuum with respect to a corresponding one of the statistical factors.
11. The network apparatus according to claim 10 , wherein the plurality of statistical factors comprise metrics or factors that are identifiable by one or more of data extracted from the received data packets and a determination of characteristics exhibited by the received data packets, and that reflect or indicate a data traffic or priority type of the respective data traffic session.
12. The network apparatus according to claim 10 , wherein the plurality of statistical factors comprise one or more of Average Throughput, Maximum Throughput, Session Duration, ON-Duration, OFF-Duration, ON-OFF Ratio, Average ON-Duration, Average OFF-Duration, and Volume, wherein the Average Throughput is a throughput rate over a time period from a start of the data traffic session to a time that the throughput rate is determined, the Maximum Throughput is a highest throughput rate measured during a respective sampling period of the data traffic session, the Session Duration is a time duration from the start of the data traffic session to a most recent state update, the ON-Duration is an accumulated time during which data packets are received over the Session Duration, the OFF-Duration is an accumulated time during which the data packets are not received over the Session Duration, ON-OFF ration is a ratio of the ON-Duration and OFF-Duration, Average ON-Duration is an average of ON time over the Session Duration, Average OFF-Duration is an average of OFF time over the Session Duration, and Volume is a volume of data packets received over a respective time period.
13. The network apparatus according to claim 10 , wherein each classification variable of each of the plurality of subsets reflects a threshold between two respective data traffic types/classes with respect to the corresponding statistical factor.
14. The network apparatus according to claim 10 , wherein the one or more processors is/are further configured to modify one or more of the classification variables of each of one or more of the plurality of subsets, based on one or more traffic conditions of the data communications network, to adjust the respective boundaries that delineate the plurality of data traffic types/classes over the continuum with respect to the corresponding one of the statistical factors.
15. The network apparatus according to claim 14 , wherein the one or more traffic conditions of the data communications network include one or more of bandwidth utilization within each of the data traffic types/classes, bandwidth allocation to each of the data traffic types/classes and network congestion.
16. The network apparatus according to claim 14 , wherein the one or more processors is/are configured to modify the one or more of the classification variables of each of one or more of the plurality of subsets are modified on a periodic basis.
17. The network apparatus according to claim 14 , wherein the one or more of the classification variables of each of one or more of the plurality of subsets are modified in order to dynamically adjust the respective boundaries for one or more data traffic types/classes of higher priority than other of the data traffic types/classes to prevent a respective reserved bandwidth level for each of the one or more data traffic types/classes of higher priority from being exceeded.
18. The network apparatus according to claim 10 , wherein the one or more processors is/are further configured to determine a unique session ID for the data traffic session based one or more identification factors including one or more of source address, source port number, destination address, destination port number and protocol type.