US-12621707-B2 - Allocating radio access network resources based on predicted video encoding rates

US12621707B2US 12621707 B2US12621707 B2US 12621707B2US-12621707-B2

Abstract

Methods, apparatuses, and systems are described for allowing a radio access network to infer information about conversational video traffic without requiring signaling mechanisms that allow communication with conversational video applications. Methods, apparatuses, and systems described herein allow radio access network equipment to detect conversational video traffic, collect information about the conversational video traffic and as well as other network conditions, predict delays associated with the conversational video traffic, predict a likely encoding rate that will be used by the application that generates the conversational video traffic, and/or allocate resources to the conversational video traffic based on the likely encoding rates and/or other network conditions.

Inventors

Kamakshi Sridhar
Edward A. GRINSHPUN
Chuck PAYETTE

Assignees

NOKIA TECHNOLOGIES OY

Dates

Publication Date: 20260505
Application Date: 20180323

Claims (15)

1 . A method comprising: detecting that a data flow is associated with bidirectional video; determining, based on radio access network conditions, at least one predicted delay associated with the data flow, the at least one predicted delay comprising at least one of an uplink delay or a downlink delay; determining, based on the at least one predicted delay, and using a model configured to output predicted encoding rates based on application information or a lookup table including application-specific predicted encoding rates, at least one predicted encoding rate associated with the bidirectional video, wherein the determining of the at least one predicted encoding rate is further based on a predicted application that generates the data flow; and allocating radio access network resources to the data flow based on the at least one predicted encoding rate.
2 . The method of claim 1 , wherein the radio access network conditions comprises information indicating congestion.
3 . The method of claim 2 , wherein the information indicating the congestion comprises at least an available number of physical resource blocks per second for a bearer.
4 . The method of claim 1 , wherein the radio access network conditions comprises information indicating at least one channel condition.
5 . The method of claim 1 , wherein the radio access network conditions comprises information indicating throughput for the data flow.
6 . The method of claim 1 , wherein the at least one predicted delay includes a first end-to-end delay for a first direction of the data flow and a second end-to-end delay for a second direction of the data flow.
7 . The method of claim 1 , wherein the at least one predicted encoding rate comprises a first predicted encoding rate for an application executing on a first user equipment and a second predicted encoding rate for the application running on a second user equipment.
8 . A radio access network equipment comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the radio access network equipment to: detect that a data flow is associated with bidirectional video; determine, based on radio access network conditions, at least one predicted delay associated with the data flow, the at least one predicted delay comprising at least one of an uplink delay or a downlink delay; determine, based on the at least one predicted delay, and using a model configured to output predicted encoding rates based on application information or a lookup table including application-specific predicted encoding rates, at least one predicted encoding rate associated with the bidirectional video, wherein the determining of the at least one predicted encoding rate is further based on a predicted application that generates the data flow; and allocate radio access network resources to the data flow based on the at least one predicted encoding rate.
9 . The radio access network equipment of claim 8 , wherein the radio access network conditions comprises information indicating congestion.
10 . The radio access network equipment of claim 9 , wherein the information indicating the congestion comprises an available number of physical resource blocks per second for a bearer.
11 . The radio access network equipment of claim 8 , wherein the radio access network conditions comprises information indicating at least one channel condition.
12 . The radio access network equipment of claim 8 , wherein the radio access network conditions comprises information indicating throughput for the data flow.
13 . The radio access network equipment of claim 8 , wherein the at least one predicted delay includes a first end-to-end delay for a first direction of the data flow and a second end-to-end delay for a second direction of the data flow.
14 . The radio access network equipment of claim 8 , wherein the at least one predicted encoding rate comprises a first predicted encoding rate for an application running on a first user equipment and a second predicted encoding rate for the application running on a second user equipment.
15 . One or more non-transitory computer readable media containing instructions that, when executed by one or more processors of radio access network equipment, cause the radio access network equipment to: detect that a data flow is associated with bidirectional video; determine, based on radio access network conditions, at least one predicted delay associated with the data flow, the at least one predicted delay comprising at least one of an uplink delay or a downlink delay; determine, based on the at least one predicted delay, and using a model configured to output predicted encoding rates based on application information or a lookup table including application-specific predicted encoding rates, at least one predicted encoding rate associated with the bidirectional video, wherein the determining of the at least one predicted encoding rate is further based on a predicted application that generates the data flow; and allocate radio access network resources to the data flow based on the at least one predicted encoding rate.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application is a 371 application of PCT Patent Application Serial No. PCT/US2018/023969, entitled “ALLOCATING RADIO ACCESS NETWORK RESOURCES BASED ON PREDICTED VIDEO ENCODING RATES”, and filed on Mar. 23, 2018, the entirety of which is incorporated by reference herein. BACKGROUND In recent years, wireless and other networks have been serving increasing traffic from smartphones and other devices. A growing portion of this traffic includes bidirectional video (e.g., conversational video) and other multimedia data flows that are latency-sensitive. Techniques for allocating sufficient network resources to this latency-sensitive traffic to-date have often been ineffective or difficult to implement. SUMMARY The following summary is not intended to identify key or critical elements of the disclosure nor to delineate the scope of the disclosure. The following summary merely presents some concepts of the disclosure in a simplified form as a prelude to the description below. Methods, apparatuses, and systems for improving quality of service for such latency-sensitive traffic are described herein. Many different applications may generate conversational video and other latency-sensitive traffic. Wireless radio access networks (RANs) typically handle conversational video traffic in the same way as traffic that is not latency-sensitive (e.g., using best effort delivery). Because such conversational video traffic is often encrypted, the RAN may not know whether traffic is conversational video or some other type of traffic, and thus may not be able to optimally allocate resources to conversational video traffic in order to improve quality of service for that traffic. Without some signaling mechanism that would allow a particular application generating conversational video traffic (or other such latency-sensitive traffic) to notify the RAN that the traffic is latency-sensitive, the RAN may have no way to distinguish between latency-sensitive and other traffic. Adopting a signaling standard for communicating between conversational video applications and RANs would be difficult due to the large number of such applications, the various technologies used by different RANs, and other factors. Conversational video applications running on user equipment typically set an encoding rate, which determines the data throughput, based on the end-end delay for prior packets in the conversational video session. A first user equipment sends out packets to a second user equipment and vice versa, and as the second user equipment receives packets, it will send out receiver reports on periodic intervals to the first user equipment, and vice versa. The periodicity may vary for different applications and may not be standardized. When the first user equipment, for example, receives these reports, it will decide the encoding rate for subsequent time intervals. If a reported end-to-end delay is high, the conversational video application on the user equipment may lower its encoding rates in order to avoid losing packets due to network congestion. If the reported end-to-end delay is low, the conversational video application on the user equipment may raise its encoding rates in order to provide better quality video. Because of the periodicity of the reporting and the iterative adjustment process, encoding rates may be adjusted gradually over time. Because of the lack of signaling mechanisms, the RAN may be unaware of the upcoming encoding rate changes, which may prevent it from taking any pre-emptive action to ensure better quality of service for the adjusted video traffic. Methods, apparatuses, and systems described herein allow a RAN to infer information about conversational video traffic without requiring signaling mechanisms that allow communication with conversational video applications. Methods, apparatuses, and systems described herein allow RAN equipment to detect conversational video traffic, collect information about the conversational video traffic and as well as other network conditions, predict delays associated with the conversational video traffic, predict a likely encoding rate that will be used by the application that generates the conversational video traffic, and allocate resources to the conversational video traffic based on the likely encoding rates and other network conditions. BRIEF DESCRIPTION OF THE DRAWINGS The present disclosure is accompanied by figures in which like reference numerals indicate similar elements and in which: FIG. 1 illustrates a network environment including user equipment connected via wireless radio access networks and other networks. FIGS. 2a and 2b illustrate data flows between user equipment connected to various access networks. FIG. 3 illustrates components of a radio access network and connections to user equipment. FIGS. 4a, 4b, and 4c illustrate example models for calculating predictions as described herein. FIG. 5 illustrates a method for allocati