Packet buffering using common time-indexed data repository across packet flows

By using a single jitter buffer and a common timer indexing packets in VoIP communication, the jitter problem in packet switching networks is solved, improving communication stability and user experience.

CN119013956APending Publication Date: 2024-11-22MICROSOFT TECHNOLOGY LICENSING LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202280092881.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-02-28
Filing Date
2022-11-04
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In VoIP communication, the packet switching network cannot guarantee that information is not discarded or delivered too late, resulting in jitter problems and affecting the communication experience of the end user.

Method used

A single jitter buffer is used to store and index packets from multiple sources, and the sending time is determined through a common timer and data repository, ensuring that packets are output at a constant rate and sequential order to mitigate jitter.

Benefits of technology

Effectively reduces packet latency differences, provides a clearer and stable communication experience, and reduces jitter buffer overhead per stream.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119013956A_ABST
    Figure CN119013956A_ABST
Patent Text Reader

Abstract

One or more packets are received by a network device at a receive time, each packet being one of a plurality of ordered packets in one of a plurality of streams received at the network device. A transmission time is determined by the network device for each received packet based on one timer common to the plurality of streams. Each packet is indexed by the network device through the determined transmission time in a data store common to the plurality of streams. All packets in the data store indexed to the particular time are transmitted by the network device at each particular time corresponding to the determined transmission time.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0001] Voice over Internet Protocol (VoIP) describes a set of technologies for delivering voice communications and multimedia sessions over IP networks such as the Internet. Although from a user's perspective, a VoIP session may be conducted similarly to a traditional telephone call, information is not transmitted over a circuit-switched network, but rather the information in digital form is packetized and transmitted in IP packets over a packet-switched network.

[0002] In contrast to circuit-switched networks, VoIP over packet-switched networks does not inherently guarantee that information will not be dropped (packet loss), delivered too late to be useful (excessive latency), or delivered out of order due to variations in the packet transfer time from source to destination. Packets sent from the same source do not always arrive at the destination at regular intervals, even if they are sent in a continuous stream. In VoIP, "jitter" is a measure of this variation in packet delay. Jitter can occur for a variety of reasons, such as network congestion, network timing drift, or network routing changes.

[0003] A "jitter buffer" is a data repository where packets can be received, stored, and then sent (e.g., to an output processor) at (almost) evenly spaced intervals, regardless of transmission time variations. A jitter buffer intentionally delays arriving packets so that the end user experiences a cleaner, less distorted connection. A jitter buffer mitigates jitter by buffering multiple packets to absorb the delay differences between them, and then outputting the packets in sequence at a (almost) constant rate. This gives more delayed packets a chance to catch up, so that all packets are output relatively smoothly. As with any type of buffering, the larger the jitter buffer, the longer the playout delay of the packets becomes.

[0004] There are two types of jitter buffers, static jitter buffers and dynamic jitter buffers. Static jitter buffers are usually pre-configured. Dynamic jitter buffers are software-based and can be configured to adapt to changes in network delays. Summary of the invention

[0005] A simplified overview of one or more aspects of the technology disclosed herein is presented below to provide a basic understanding of these aspects. The present disclosure is not an extensive overview of all anticipated aspects, and is neither intended to identify the key or key elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0006] In several examples, computer-implemented methods, devices, and tangible non-transitory computer-readable media for packet buffering are provided. In some examples, a network device receives one or more packets at a receive time, each packet being one of a plurality of ordered packets in one of a plurality of flows received at the network device. The network device determines a send time for each received packet based on a timer common to the plurality of flows. The network device indexes each packet by the determined send time in a data repository common to the plurality of flows. The network device sends all packets indexed to the particular time in the data repository at each particular time corresponding to the determined send time.

[0007] In some such examples, N is the depth of the data repository, and the maximum delay between the receive time and the send time is N. In some such examples, the data repository is: a hash table using the send time as a hash table key, or a ring timer using the send time modulo N as a ring timer key.

[0008] In some examples, the plurality of flows includes at least one hundred flows. In some examples, the network device is a session border controller. In some examples, the timer and data repository includes a timer and data repository combination for each processor of the plurality of processors of the network device.

[0009] To achieve the foregoing and related ends, one or more aspects include features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail certain illustrative features of one or more aspects. However, these features are merely indicative of some of the various ways in which the principles of the various aspects may be employed, and this specification is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is an illustration of an example of the present technology in a telecommunications context.

[0011] Figure 2 is a flow chart of an example method of packet buffering according to examples of the techniques disclosed herein.

[0012] Figure 3 is a continuing example of packet buffering according to examples of the technology disclosed herein.

[0013] Figure 4 is a continuing example of packet buffering according to examples of the technology disclosed herein.

[0014] Figure 5 is a continuing example of packet buffering according to examples of the technology disclosed herein.

[0015] Figure 6is a schematic diagram of an example of an apparatus for performing the functions described herein. DETAILED DESCRIPTION

[0016] The specific embodiments described below in conjunction with the accompanying drawings are intended to be descriptions of various configurations and are not intended to represent the only configurations in which the concepts described herein can be practiced. For the purpose of providing a thorough understanding of various concepts, the specific embodiments include specific details. However, it is apparent to those skilled in the art that these concepts can be practiced without these specific details. In some cases, well-known components are shown in block diagram form to avoid blurring these concepts.

[0017] Typically, jitter buffers are used on end-user devices (e.g., smartphones). Such end-user devices typically handle one or a small number of flows at a time, and employ a separate jitter buffer for each flow. Each jitter buffer determines how much delay to apply to each incoming packet - a subject outside the scope of this application. Each jitter buffer operates its own clock / timer (although derived from the device-wide clock, it is distinct from it) and its own data store. Maintaining a per-flow jitter buffer with its own clock / timer and data store, and checking each buffer at any given time to see if there are packets to transmit, can introduce significant overhead to the VoIP process.

[0018] Now go to Figures 1 to 6 , which depicts examples with reference to one or more components and one or more methods that can perform the actions or operations described herein. Although the operations described below are presented in a particular order and / or performed by example components, in some examples, the order of the actions and the components that perform the actions may vary depending on the implementation. In addition, in some examples, one or more of the actions, functions, and / or described components may be performed by a specially programmed processor, a processor that executes specially programmed software or computer-readable media, or by any other combination of hardware components and / or software components that can perform the described actions or functions.

[0019] refer to Figure 1, which illustrates an example of the technology disclosed herein in the context of a conceptual architecture 100. Examples of the technology disclosed herein partially address the above challenges by storing all packets of multiple packet streams 120 from one or more sources 110 in a single jitter buffer 130 before sending the packets to one or more destinations 140. The communication network 99 between the (multiple) source 110, the jitter buffer 130, and the (multiple) destination 140 is characterized by variations in the transmission time between the (multiple) source 110 and the jitter buffer 130. The jitter buffer 130 includes a common data repository 134 of indexed packets 150, wherein each indexed packet 150 is indexed by a determined transmission time. A common clock 132 is used to track the current time, for transmission time determination 136, and for transmitting 138 all indexed packets 150 indexed to the determined transmission time.

[0020] Although the determined transmission time is identified by a single point in time, in practice, the determined transmission time corresponds to a period from the determined transmission time to the next granularity time of the jitter buffer. For example, the period may be equal to the granularity of the transmission time determination 136, e.g., one millisecond. The granularity of the data repository 134 should be sufficiently precise so that the indexed packets 150 can be properly indexed, e.g., at least as precise as the granularity of the transmission time determination 136, and sufficiently precise so that any errors introduced are tolerable.

[0021] refer to Figure 2 , and continuing with the previous figures for context, an example method 200 for packet buffering according to the techniques disclosed herein is shown. In such a method, a network device receives one or more packets at a receive time - block 210. Each packet is one of a plurality of ordered packets in one of a plurality of flows received at the network device.

[0022] refer to Figure 3 , and continuing with reference to the previous figures for context, a continuing example method 300 is shown at time t=0. In the continuing example, the jitter buffer 130 is part of a session border controller (SBC).

[0023] An SBC is a network device deployed to protect Session Initiation Protocol (SIP)-based voice on a VoIP network. Although some SBCs are deployed at the boundary between two service provider networks, such devices (and related equipment) can be deployed between a service provider's access network and a backbone network to provide services to residential and / or enterprise customers. A "session" can be a call between two or more parties. Each call includes one or more signaling message exchanges that control the call, and one or more call media streams that carry audio, video or other data for the call, as well as information about call statistics and quality. These packet streams (e.g., packet stream 120) together constitute a session. Some SBCs or SBC-like devices handle thousands (or even tens of thousands) of calls / packet streams simultaneously.

[0024] Although the continuing examples explain the invention in the context of a jitter buffer in an SBC, the techniques disclosed herein can be used in any situation involving a jitter buffer that handles a large number of call / packet flows. Although the continuing examples reference VoIP, note that VoIP can contain not only packets for voice, but also packets for other media and protocols. Jitter buffers are equally applicable to other media streams over IP (e.g., video) and voice over other protocols (e.g., TDM).

[0025] In the continued example, the time granularity for the jitter buffer 130 data repository 134 is 1 ms, and the maximum depth of the jitter buffer 130 data repository 134 is 10 ms. In some actual implementations, the time granularity is also 1 ms, but the jitter buffer maximum depth can be much larger, such as 8000 ms. In the continued example, four (4) streams 120 are received at the jitter buffer 130. Specifically, at t=0, one packet is received for each stream: 1 x (0,*),2 k (0,*),3 a (0,*) and 4 w (0,*) - where: packet = <stream> (<receive time>, <determined send time>), e.g., 4 w (0, *), where "*" indicates that the sending time has not yet been determined. In the continued example, at t=0, the sending time has not been determined.

[0026] In some examples, jitter buffer 130 is deployed in a physical or virtual device (such as device 600 described below), and jitter buffer component 612 of device 600 provides means for receiving one or more packets at a receive time.

[0027] Reference again Figure 2, the network device determines the sending time for each received packet based on a timer common to multiple flows - block 220. Figure 3 In the continued example of , the transmit time determination 136 determines to use the clock 132 (which is common in each packet stream 120) to transmit the stream 4 packet at t = 1, the stream 2 packet and the stream 3 packet at t = 2, and the stream 1 packet at t = 0. The specific transmit time determination method is not covered in this application, and many known methods can be used.

[0028] In some examples, the jitter buffer component 612 of the device 600 provides a means for determining a transmission time for each received packet based on a timer common to the multiple flows.

[0029] Reference again Figure 2 , the network device indexes each packet by the determined transmission time in a data repository common to the multiple flows - block 230. Figure 3 Continuing with the example of FIG. 1 , the jitter buffer 130 uses the determined transmission time as an index to store the indexed packets 150 in the common data repository 134 as: 1 at t=3 ms x (0,4); 2 at t = 2ms k (0,2) and 3 a (0,2); and 4 at t = 1ms w (0,1).

[0030] Specifically, the jitter buffer 130 implements a hash table of packets with the send time as a key. Other types of indexes can be used, for example, a ring timer using the send time modulo N as the ring timer key, where N is the depth of the ring timer. Typically, N is the depth of the data repository, and the maximum delay between the receive time and the send time is N. In some examples, both the common timer 132 and the common data repository 134 are used for each of the multiple processors in the network device. In addition, note that although the time index of the continued example is cyclic, for example, time index "0" is after time index "9", in the continued example, the receive time is not a cyclic time.

[0031] In some examples, the jitter buffer component 612 of the device 600 provides a means for indexing each packet by the determined transmission time in a data repository common to multiple flows.

[0032] Reference again Figure 2 , the network device transmits all packets indexed to the specific time in the data repository at each specific time corresponding to the determined transmission time - block 240. Figure 4, and continuing with the previous figures for context, a continuing example method 400 is shown at time t=1. In the continuing example at t=1 ms, the jitter buffer 130 sends 4 w (0,1)(by Figure 4 In addition, as described with respect to block 210, jitter buffer 130 receives packet 3 b (1,*) and 4 z (1, *). In addition, as described with respect to block 220, jitter buffer 130 determines the transmit time for each newly received packet - index 3 b (1,2) for sending at t=2, and index 4 z (1,0) is used to send at t=10 (corresponding to Figures 3 to 5 Note that "jitter buffer 130 sends" includes elements of the SBC outside of the instruction and data storage repositories that are physically interfaced with the communications network 99.

[0033] In some examples, the jitter buffer component 612 of the device 600 provides a means for transmitting all packets in the data store indexed to the specific time at each specific time corresponding to the determined transmission time.

[0034] refer to Figure 5 , and continuing with the previous figures for context, a continuation of the example method 500 is shown at time t=2. In the continuation example at t=2 ms, the jitter buffer 130 sends 2 k (0,2),3 a (0,2) and 3 b (1,2)(by Figure 5 In addition, as described with respect to block 210, jitter buffer 130 receives packet 2 m (2,*) and 2 n (2, *). In addition, as described with respect to block 220, jitter buffer 130 determines the transmit time for each newly received packet - index 2 m (2,4) for sending at t=4, and index 2 n (2,*) is used to send at t=5.

[0035] Figure 6 An example of a device 600 is shown. In one aspect, the device 600 may include a processor 602, which may be similar to the processor 602 for carrying out processing functions associated with one or more components and functions described herein. The processor 602 may include a single or multiple processors or a multi-core processor. In addition, the processor 602 may be implemented as an integrated processing system and / or a distributed processing system.

[0036] The device 600 may also include a memory 604, such as for storing a local version of an operating system (or its components) and / or applications (such as streaming applications / services, etc.) executed by the processor 602, related instructions, parameters, etc. The memory 604 may include computer-usable memory types such as random access memory (RAM), read-only memory (ROM), tapes, magnetic disks, optical disks, volatile memory, non-volatile memory, and any combination thereof.

[0037] Additionally, the device 600 may include a communication component 606 that provides for establishing and maintaining communications with one or more other devices, parties, entities, etc. utilizing hardware, software, and services as described herein. The communication component 606 may facilitate communications between components on the device 600 and between the device 600 and external devices, such as devices located across a communication network and / or devices connected in series or locally to the device 600. For example, the communication component 606 may include one or more buses and may also include a transmit chain component and a receive chain component associated with a wireless or wired transmitter and receiver, respectively, operable to interface with external devices.

[0038] In addition, the device 600 may include a data repository 608, which may be any suitable combination of hardware and / or software that provides mass storage of information, databases, and programs employed in conjunction with the various aspects described herein. For example, the data repository 608 may be or may include a data repository for an operating system (or components thereof), applications, related parameters, etc. that are not currently executed by the processor 602. In addition, the data repository 608 may be a data repository for the streaming application / service 612 and / or one or more other components of the device 600.

[0039] Device 600 may optionally include user interface component 610, which is operable to receive input from the user of device 600 and is also operable to generate output for presenting to the user. User interface component 610 may include one or more input devices, including but not limited to keyboard, numeric keypad, mouse, touch-sensitive display, navigation key, function key, microphone, voice recognition component, gesture recognition component, depth sensor, gaze tracking sensor, switch / button, any other mechanism that can receive input from the user, or any combination thereof. In addition, user interface component 610 may include one or more output devices, including but not limited to display, speaker, tactile feedback mechanism, printer, any other mechanism that can present output to the user, or any combination thereof. For example, user interface 610 can present streaming content for user consumption (e.g., on the display of device 600, the audio output of device 600, etc.).

[0040] The device 600 may additionally include a jitter buffer component 612, which may be similar to or may include the jitter buffer 130. In this regard, the device 600 may be operable to perform a role in packet buffering, as described herein.

[0041] As an example, an element, or any part of an element, or any combination of elements can be implemented with a "processing system" including one or more processors. Examples of processors include microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform various functions described throughout the disclosure. One or more processors in a processing system can execute software. Software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software groupings, routines, subroutines, objects, executable files, execution threads, processes, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or other.

[0042] Thus, in one or more aspects, one or more of the described functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on a computer-readable medium or encoded as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available media that can be accessed by a computer.

[0043] By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. As used herein, magnetic disks and optical disks include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVDs), and floppy disks, wherein magnetic disks typically reproduce data magnetically, while optical disks reproduce data optically with lasers. Combinations of the foregoing should also be included within the scope of computer-readable media.

[0044] As a first additional example, the technology disclosed herein includes a method, device, and non-transitory computer-readable medium storing instructions for packet buffering thereon. In such an example, a network device receives one or more packets at a receiving time, each packet being one of a plurality of ordered packets in one of a plurality of streams received at the network device. The network device determines a sending time based on a timer common to a plurality of streams for each received packet. The network device indexes each packet by the determined sending time in a data repository common to a plurality of streams. The network device sends all packets indexed to the specific time in the data repository at each specific time corresponding to the determined sending time.

[0045] A second additional example includes the first additional example, wherein N is a depth of the data repository, and a maximum delay between a receive time and a send time is N.

[0046] A third additional example includes the previous additional examples, wherein the data storage repository is: a hash table using the send time as a hash table key, or a ring timer using the send time modulo N as a ring timer key.

[0047] A fourth additional example includes the previous additional example, wherein the plurality of streams includes at least one hundred streams.

[0048] A fifth additional example includes the previous additional examples, wherein the network device is a session border controller.

[0049] A sixth additional example includes the previous additional examples, wherein the timer and data store comprises one timer and data store combination for each processor of the plurality of processors of the network device.

[0050] The previous description is provided to enable those skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein, but should conform to the full scope consistent with the language claims, wherein unless specifically stated otherwise, reference to an element in the singular is not intended to mean "one and only one", but rather "one or more". Unless otherwise specifically stated, the term "some" refers to one or more. All structural and functional equivalents of the elements of the various aspects described herein known or later known to those of ordinary skill in the art are contemplated and intended to be covered by the claims. In addition, the contents disclosed herein are not intended to be dedicated to the public, regardless of whether these disclosures are explicitly stated in the claims. Unless a claim element is explicitly stated using the phrase "parts for...", a claim element should not be interpreted as a device plus function.

Claims

1. A computer-implemented method comprising: receiving, by a network device at a receive time, one or more packets, each packet being one of a plurality of ordered packets in one of a plurality of flows received at the network device; Determining, by the network device, a sending time for each received packet based on a timer common to the plurality of flows; indexing, by the network device, each packet by the determined sending time in a data repository common to the plurality of flows, wherein N is a depth of the data repository and a maximum delay between a receiving time and a sending time is N, and the data repository is a hash table using the sending time as a hash table key; as well as All packets indexed to the specific time in the data storage repository are sent by the network device at each specific time corresponding to the determined sending time.

2. The method of claim 1, wherein the plurality of streams comprises at least one hundred streams. The method of claim 1 , wherein the network device is a session border controller.

4. The method of claim 1, wherein the timer and the data repository comprise one timer and data repository combination for each of a plurality of processors of the network device.

5. A network device for packet buffering, comprising: Memory; as well as at least one processor coupled to the memory, the memory comprising instructions executable by the at least one processor to cause the apparatus to: receiving, by a network device at a receive time, one or more packets, each packet being one of a plurality of ordered packets in one of a plurality of flows received at the network device; Determining, by the network device, a sending time for each received packet based on a timer common to the plurality of flows; indexing, by the network device, each packet by the determined sending time in a data repository common to the plurality of flows, wherein N is a depth of the data repository and a maximum delay between a receiving time and a sending time is N, and the data repository is a hash table using the sending time as a hash table key; as well as All packets indexed to the specific time in the data storage repository are sent by the network device at each specific time corresponding to the determined sending time.

6. The apparatus of claim 5, wherein the plurality of streams comprises at least one hundred streams.

7. The device of claim 5, wherein the network device is a session border controller.

8. The device of claim 5, wherein the timer and the data repository comprise one timer and data repository combination for each of a plurality of processors of the network device.

9. A computer-readable medium having instructions stored thereon, wherein when the instructions are executed by at least one computing device, the at least one computing device performs operations, the operations comprising: receiving, by a network device at a receive time, one or more packets, each packet being one of a plurality of ordered packets in one of a plurality of flows received at the network device; Determining, by the network device, a sending time for each received packet based on a timer common to the plurality of flows; indexing, by the network device, each packet by the determined sending time in a data repository common to the plurality of flows, wherein N is a depth of the data repository and a maximum delay between a receiving time and a sending time is N, and the data repository is a hash table using the sending time as a hash table key; as well as All packets indexed to the specific time in the data storage repository are sent by the network device at each specific time corresponding to the determined sending time.

10. The computer-readable medium of claim 9, wherein the plurality of streams comprises at least one hundred streams.

11. The computer-readable medium of claim 9, wherein the network device is a session border controller.

12. The computer-readable medium of claim 9, wherein the timer and the data repository comprise one timer and data repository combination for each of a plurality of processors of the network device.

13. A network device for packet buffering, comprising: means for receiving, by a network device, one or more packets at a receive time, each packet being one of a plurality of ordered packets in one of a plurality of flows received at the network device; means for determining, by the network device, a sending time for each received packet based on a timer common to the plurality of flows; means for indexing, by the network device, each packet by the determined send time in a data repository common to the plurality of flows, wherein N is a depth of the data repository and a maximum delay between a receive time and a send time is N, and the data repository is a hash table using a send time as a hash table key; as well as Means for transmitting, by the network device at each specific time corresponding to the determined transmission time, all packets in the data repository indexed to the specific time.

14. The apparatus of claim 13, wherein the plurality of streams comprises at least one hundred streams.

15. The device of claim 13, wherein the network device is a session border controller.