Methods and Apparatus for Using a Layered Gear to Analyze and Manage Real-time Network Quality of Service Transmission for Mobile Devices on Public Networks

• US 20120314599A1
• Filed: 06/09/2012
• Published: 12/13/2012
• Est. Priority Date: 06/08/2011
• Status: Active Grant

• Current Assignee: Citrix Systems, Inc. (Cloud Software Group)
• Original Assignee: Framehawk LLC
• Inventors: Vilke, Stephen D., Willis, Rudy, Selvidge, James, Hinks, Paul
• Granted Patent: US 8,774,043 B2
• Time in Patent Office: Days
• US Class Current: 370/252
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04L 47/196 Integration of transport layer protocols, e.g. TCP and UDP
• CPC Class Codes: H04L 47/25 with rate being modified by the source upon detecting a change of network conditions

Abstract

Methods and apparatus for providing layered gear mechanism to analyze network loss and latency conditions includes bundling data into data packets of varying depths, at a source with data packets of each depth belonging to a particular data type. The data packets of varying depths are transmitted in layers over a network, to a destination. Information for the transmitted data packets for each layer is collected constantly and analyzed as the data progresses along the network to identify corresponding network transmission characteristics. The transmission of subsequent data packets for anyone of the layers is adjusted based on the network transmission characteristics. The adjusting is repeated one or more times based on the analyzed information for the transmitted data packets. The transition metrics for each layer is utilized for relative analysis of transmission metrics across the layers to set the adjusting.

Claims

1. A processor-implemented method for providing layered gear mechanism to analyze network loss and latency conditions, comprising:

bundling data into data packets of varying depths at a source, by a processor, the data packets of each depth belonging to a particular type of data;

transmitting, by the processor, the data packets of varying depths in layers over a network to a destination, each layer corresponding to each depth;

collecting information for the transmitted data packets for each layer as the data packets progress along the network;

analyzing the collected information for the data packets of each layer to identify network transmission characteristics of each layer, the network transmission characteristics identifying transmission metrics for each layer; and

adjusting transmission of subsequent data packets for anyone of the layers based on the network transmission characteristics, the adjusting is repeated one or more times based on the analyzed information for the transmitted data packets, the transmission metrics for each layer utilized for relative analysis of transmission metrics across the layers to set the adjusting.

2. The method of claim 1, wherein the transmitting of the data packets comply with a compliance rule specified for the network, the compliance rule identifying one or more recipes for packaging information for each type of data.

3. The method of claim 1, wherein the data packets include payload data and housekeeping data that comply with transmission protocol of the network, the housekeeping data providing information on the payload data enclosed within the data packet.

4. The method of claim 2, wherein the bundling of data packets at varying depth further includes,

determining a type of data to be transmitted in each of the layers;

identifying a pre-defined depth for each type of data in each layer based on the compliance rules; and

configuring the data in each layer to the corresponding pre-defined depth to generate corresponding data packets.

5. The method of claim 4, wherein bundling further includes,

cycling through recipes for each data type to calibrate the depth of the data packets in each layer, the calibrated depth used in bundling the data packets for transmission,

the cycling through different recipes is performed periodically.

6. The method of claim 1, wherein collecting information further includes,

determining input count of the data packets in each layer transmitted from the source to the destination over the network;

determining output count of the data packets in the respective layers returned in a response from the destination to the source; and

computing difference between the input count and the output count for each layer of the data packets transmitted over the network, the difference used in the analyzing to identify network transmission characteristics of each layer.

7. The method of claim 1, wherein collecting information further includes,

determining a fractional linear combination of data packets of varying depths represented in the different layers for a specific time;

determining the input cadence and the output cadence for the data packets in each layer within the fractional linear combination of packets; and

computing data packet differentials at each layer for the specific time by computing difference between the input cadence and the output cadence of the corresponding data packets in each layer of the fractional linear combination of data packets.

8. The method of claim 7, wherein analyzing further includes,

analyzing the data packet differentials at each layer and across the layers within the fractional linear combination of data packets collected for the specific time to determine network transmission characteristics, the network transmission characteristic identifying a stochastic problem or a deterministic problem.

9. The method of claim 7, further includes,

computing data packet differentials at each layer and across the layers of the fractional linear combination of data packets collected periodically;

and

generating a statistical model for the data packet differentials for each layer and across the layers, the statistical model providing network transmission characteristics of each layer.

10. The method of claim 9, wherein analyzing further includes,

analyzing the statistical model to identify a pattern in the network transmission characteristics in each layer;

and

determining the identified pattern in each layer to be a stochastic pattern or deterministic pattern.

11. The method of claim 10, wherein adjusting transmission of subsequent data packets further includes,

when the identified pattern of a specific layer is a deterministic pattern,

adjusting the subsequent transmission of the data packets at the specific layer iteratively to adjust the network transmission characteristics at the specific layer.

12. The method of claim 10, wherein adjusting transmission of subsequent data packets further includes,

when the identified pattern of a specific layer is a stochastic pattern,

adjusting subsequent transmission of the data packets at the specific depth by including additional data packets at the depth for the particular type of data in the specific layer, the additional data packets used in adjusting the network transmission characteristics for the specific layer.

13. The method of claim 10, wherein adjusting transmission of subsequent data packets further includes,

when the identified pattern of a specific layer is a stochastic problem,

determining type of data at the specific layer;

and

continuing transmission of the subsequent data packets without adjusting the transmission for the specific layer, the continuing transmission adjusting the network transmission characteristics for the specific layer.

14. The method of claim 1, transmitting data packets further includes,

generating a set of dummy data packets of varying depths, the dummy data packets having dummy payload data, the dummy data packets of each depth belong to particular type of data;

transmitting the dummy data packets of varying depths in layers with the data packets as a pulse; and

monitoring reaction on the network for the transmitted pulse of dummy data packets, the monitored reaction providing information for the data packets in each layer to identify network transmission characteristics of each layer, the network transmission characteristics identifying streaming tolerance of the network.

15. The method of claim 14, wherein the generation and transmission of the dummy data packets and monitoring reaction are performed periodically to determine if the streaming tolerance of the network transmission characteristics of the network fluctuates over time.

16. A non-transitory computer readable medium having program instructions embedded therein, which when executed by a server of a computing system provides layered gear mechanism to analyze network loss and latency conditions, the program instructions comprising:

program instructions for bundling data into data packets of varying depths at a source, by a processor, the data packets of each depth belonging to a particular type of data;

program instructions for transmitting, by the processor, the data packets of varying depths in layers over a network to a destination, each layer corresponding to each depth;

program instructions for collecting information for the transmitted data packets for each layer as the data packets progress along the network;

program instructions for analyzing the collected information for the data packets of each layer to identify network transmission characteristics of each layer, the network transmission characteristics identifying transmission metrics for each layer; and

program instructions for adjusting transmission of subsequent data packets for anyone of the layers based on the network transmission characteristics, the adjusting is repeated one or more times based on the analyzed information for the transmitted data packets, the transmission metrics for each layer utilized for relative analysis of transmission metrics across the layers to set the adjusting.

17. The computer readable medium of claim 16, wherein program instructions for collecting information further includes,

program instructions for determining a fractional linear combination of data packets of varying depths represented in the different layers for a specific time;

program instructions for determining the input cadence and the output cadence for the data packets in each layer within the fractional linear combination of packets; and

program instructions for computing data packet differentials at each layer for the specific time by computing difference between the input cadence and the output cadence of the corresponding data packets in each layer of the fractional linear combination of data packets.

18. The computer readable medium of claim 17, wherein program instructions for analyzing further includes,

program instructions for analyzing the data packet differentials at each layer and across the layers within the fractional linear combination of data packets collected for the specific time to determine network transmission characteristics, the network transmission characteristic identifying a stochastic characteristic or a deterministic characteristic.

19. The computer readable medium of claim 17, further includes,

program instructions for computing data packet differentials at each layer and across the layers of the fractional linear combination of data packets collected;

program instructions for generating a statistical model for the data packet differentials for each layer and across the layers, the statistical model providing network transmission characteristics of each layer;

program instructions for analyzing the statistical model to identify a pattern in the network transmission characteristics in each layer; and

program instructions for determining the identified pattern in each layer to be a stochastic pattern or deterministic pattern.

20. The computer readable medium of claim 19, wherein program instructions for adjusting transmission of subsequent data packets further includes,

when the identified pattern of a specific layer is a deterministic pattern,

program instructions for adjusting the subsequent transmission of the data packets at the specific layer iteratively to adjust the network transmission characteristics at the specific layer.

21. The computer readable medium of claim 19, wherein program instructions for adjusting transmission of subsequent data packets further includes,

when the identified pattern of a specific layer is a stochastic pattern,

program instructions for adjusting subsequent transmission of the data packets at the specific depth by including additional data packets at the depth for the particular type of data in the specific layer, the additional data packets used in adjusting the network transmission characteristics for the specific layer.

22. The computer readable medium of claim 16, wherein program instructions for transmitting data further includes,

program instructions for generating a set of dummy data packets of varying depths, the dummy data packets having dummy payload data, the dummy data packets of each depth belong to particular type of data;

program instructions for transmitting the dummy data packets of varying depths in layers with the data packets as a pulse; and

program instructions for monitoring reaction on the network for the transmitted pulse of dummy data packets, the monitored reaction providing information for the data packets in each layer to identify network transmission characteristics of each layer, the network transmission characteristics identifying streaming tolerance of the network.

23. The computer readable medium of claim 22, wherein the generation and transmission of the dummy data packets and monitoring reaction are performed periodically to determine if the streaming tolerance of the network transmission characteristics of the network fluctuates over time.

24. A processor-implemented method for providing layered gearing mechanism to analyze network loss and latency conditions, comprising:

bundling data into data packets of varying depths at a source, by a processor, the data packets of each depth belonging to a particular type of data, the data packets include payload data and housekeeping data;

transmitting, by the processor, the data packets of varying depths in layers over a network to a destination, each layer corresponding to each depth;

receiving response data packets for each layer of the transmitted data packets from the destination, the response data packets including housekeeping data;

collecting information for the transmitted data packets for each layer as the data packets progress along the network;

analyzing the response data packets received from the destination and the collected information for the data packets of each layer to identify network transmission characteristics of each layer, the network transmission characteristics identifying transmission metrics for each layer; and

adjusting transmission of subsequent data packets for anyone of the layers based on the network transmission characteristics, the adjusting is repeated one or more times based on the analyzed information for the transmitted data packets, the transmission metrics for each layer utilized for relative analysis of transmission metrics across the layers to set the adjusting.

25. The method of claim 24, wherein the network transmission characteristics include any one or combination from a group consisting of streaming tolerance for various types of data, standing wave propagation patterns, loss characteristics of consistency, lost characteristics of spike tolerance, loss and latency characteristics of oscillation patterns, statistical likelihood of various size loss holes, ebb and flow patterns of loss/latency.