INTELLIGENT MOBILITY APPLICATION PROFILING TOOL

• US 20120151041A1
• Filed: 12/14/2010
• Published: 06/14/2012
• Est. Priority Date: 12/14/2010
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gerber, Alexandre, Mao, Zhuoqing, Qian, Feng, Sen, Subhabrata, Spatscheck, Oliver, Wang, Zhaoguang
• Granted Patent: US 8,527,627 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04W 24/08 Testing, supervising or monitoring using real traffic
• CPC Class Codes: H04W 4/50 Service provisioning or reconfiguring
• CPC Class Codes: H04W 52/0229 where the received signal is a wanted signal
• CPC Class Codes: H04W 52/0232 according to average transmission signal activity
• CPC Class Codes: H04W 76/27 Transitions between radio resource control [RRC] states
• CPC Class Codes: H04W 8/22 Processing or transfer of terminal data, e.g. status or physical capabilities
• CPC Class Codes: Y02D 30/00 Reducing energy consumption in communication networks
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

Systems and methods for analyzing mobile device applications within a wireless data network are presented herein. More particularly, described herein is a novel Intelligent Mobility Application Profiling Tool (iMAP) and/or other mechanisms, systems and methods for profiling and benchmarking applications associated with mobile devices in a wireless data network. Various systems and methods described herein expose cross-layer interaction associated with a network device in order to profile an application on the network device with respect to energy efficiency, performance, and functionality. As described herein, radio resource control (RRC) analysis can be performed to infer RRC states associated with a given application, identify tail time, etc. Further, analyzers are employed for various layers, including transmission control protocol (TCP) and/or hypertext transfer protocol (HTTP), as well as to analyze communication bursts associated with a given application. Analysis results are subsequently utilized to deliver application profiling results to a user.

Claims

1. A method, comprising:

executing, using at least one processor, computer-readable instructions for performing acts, comprising;

obtaining network activity data relating to at least one network device;

analyzing cross-layer interaction associated with the network activity data between at least one of a radio resource control (RRC) layer, a transport layer, or an application layer; and

identifying bursts indicated within the network activity data and triggering factors of the bursts based at least in part on the cross-layer interaction associated with the network activity data.

2. The method of claim 1, further comprising:

generating a report relating to the cross-layer interaction associated with the network activity data, the bursts indicated within the network activity data and the triggering factors of the bursts.

3. The method of claim 1, wherein the analyzing comprises:

inferring respective RRC states associated with the network activity data based at least in part on radio link control (RLC) buffer characteristics of the at least one network device.

4. The method of claim 3, further comprising:

determining energy consumption of the bursts indicated within the network activity data as a function of the respective RRC states associated with respective network activity data of the network activity data corresponding to the bursts and carrier power functions corresponding to the respective RRC states.

5. The method of claim 4, further comprising:

quantifying energy efficiency of the at least one network device based at least in part on the energy consumption of the bursts indicated within the network activity data.

6. The method of claim 1, further comprising:

analyzing resource usage efficiency of the bursts indicated within the network activity data; and

generating a report relating to at least one suggested burst combination that yields a greater resource usage efficiency than the resource usage efficiency of the bursts indicated within the network activity data.

7. The method of claim 1, wherein the obtaining comprises:

obtaining a set of packet traces from the at least one network device.

8. The method of claim 7, wherein the obtaining further comprises:

identifying at least one target application associated with the at least one network device; and

identifying packet traces within the set of packet traces that relate to the at least one target application.

9. The method of claim 1, wherein the obtaining comprises:

obtaining information relating to at least one of user input events, application activities, or system information relating to the at least one network device.

10. The method of claim 1, wherein the analyzing comprises:

performing Transmission Control Protocol (TCP) analysis with respect to the network activity data at least in part by extracting respective TCP flows from the network activity data and identifying properties of respective packets associated with the respective TCP flows.

11. The method of claim 1, wherein the analyzing comprises:

performing Hypertext Transfer Protocol (HTTP) analysis with respect to the network activity data at least in part by reassembling respective Transmission Control Protocol (TCP) flows corresponding to the network activity data, parsing the respective TCP flows according to an HTTP protocol, and identifying relationships between the respective packets of the respective TCP flows and at least one of HTTP requests or HTTP responses.

12. The method of claim 1, wherein the identifying comprises:

identifying the triggering factors of the respective bursts based on information within the network activity data relating to at least one of burst size, burst duration, user input events, burst payload size, packet direction, or Transmission Control Protocol (TCP) properties associated with the respective bursts.

13. The method of claim 1, wherein the identifying comprises:

identifying respective periodic bursts indicated within the network activity data.

14. The method of claim 1, further comprising:

benchmarking the network activity data with respect to at least one of amount of transferred data, network activity duration, ratio of tail time to network activity duration, energy consumption, ratio of energy consumption to data transferred, state promotion ratio, or ratio of data transferred to data consumed.

15. A system, comprising:

a data collection component configured to obtain information relating to communication activity of at least one network device;

an activity analysis component configured to conduct cross-layer analysis of the information obtained by the data collection component with respect to at least one of a radio resource control (RRC) layer, a transport layer, or an application layer;

a burst analysis component configured to identify communication bursts within the communication activity of the at least one network device and to infer triggers of the communication bursts; and

an application profiling component configured to profile at least one application associated with the at least one network device based at least in part on the cross-layer analysis conducted by the activity analysis component and the bursts identified by the burst analysis component.

16. The system of claim 15, wherein the activity analysis component is further configured to identify respective RRC state transitions associated with the communication activity of the at least one network device based on the information obtained by the data collection component.

17. The system of claim 15, wherein the application profiling component is further configured to relate one or more bursts of the communication bursts analyzed by the burst analysis component to the least one application associated with the at least one network device, to analyze resource usage efficiency of the one or more bursts relating to the at least one application, and to identify at least one suggested burst combination based on the resource usage efficiency of the one or more bursts relating to the at least one application.

18. The system of claim 15, wherein the burst analysis component is further configured to analyze energy consumption associated with the communication bursts based at least in part on RRC states associated with the communication bursts and to determine energy efficiency of the at least one network device as a function of the energy consumption associated with the communication bursts.

19. The system of claim 15, wherein the activity analysis component comprises:

a Transmission Control Protocol (TCP) analysis component configured to extract respective TCP flows from the information obtained from the data collection component and to identify properties of respective packets associated with the respective TCP flows; and

a Hypertext Transfer Protocol (HTTP) analysis component configured to reassemble the respective TCP flows, to parse the respective TCP flows according to an HTTP protocol, and to identify relationships between the respective packets of the respective TCP flows and at least one of HTTP requests or HTTP responses.

20. A computer program product, comprising:

a computer-readable storage medium, comprising;

code for causing a computer to obtain network device operation data including packet trace data and user input data;

code for causing a computer to analyze the network device operation data on a radio resource control (RRC) layer, a transport layer and an application layer with respect to at least one network device application;

code for causing a computer to identify bursts within the network device operation data;

code for causing a computer to identify triggering factors of the bursts within the network device operation data based at least in part on the analysis of the network device operation data; and

code for causing a computer to generate a performance profile of the at least one network device application based at least in part on the analysis of the network device operation data, the bursts within the network device operation data, and the triggering factors of the bursts.