Search

EP-4742745-A1 - A SCHEDULER PREVENTING A DISTRIBUTED REAL-TIME APPLICATION FROM FREEZING

EP4742745A1EP 4742745 A1EP4742745 A1EP 4742745A1EP-4742745-A1

Abstract

A method for operating a scheduler of an access point of a radio access network, RAN, wherein a distributed real-time application transmits a functional minimum data rate of the distributed real-time application to a scheduler of an access point of a RAN, the access point forwarding data packets transmitted by the distributed real-time application via a wireless connection provided by the access point; the scheduler successively signals determined target bitrates to the distributed real-time application and the distributed real-time application dynamically adjusts a data rate of the transmitted data packets at an offset below the signaled target bitrates; the scheduler measures the offset and normally determines a target bitrate at the measured offset above a determined best effort bitrate for the wireless connection; and the scheduler exceptionally determines the target bitrate to be a minimum target bitrate when the normally determined target bitrate is lower than the exceptionally determined minimum target bitrate, the minimum target bitrate being determined at the measured offset above the transmitted functional minimum data rate; an access point for a RAN, a RAN and a computer program product.

Inventors

  • SCHNIEDERS, DOMINIK

Assignees

  • Deutsche Telekom AG

Dates

Publication Date
20260513
Application Date
20241108

Claims (15)

  1. A method for operating a scheduler (100) of an access point (10) of a radio access network, RAN, (1), wherein - a distributed real-time application (4) transmits a functional minimum data rate (42) of the distributed real-time application (4) to a scheduler (100) of an access point (10) of a RAN (1), the access point (10) forwarding data packets (40) transmitted by the distributed real-time application (4) via a wireless connection (20) provided by the access point (10); - the scheduler (100) successively signals determined target bitrates (52) to the distributed real-time application (4) and the distributed real-time application (4) dynamically adjusts a data rate (400) of the transmitted data packets (40) at an offset (5) below the signaled target bitrates (52); - the scheduler (100) measures the offset (5) and normally determines a target bitrate (52) at the measured offset (5) above a determined best effort bitrate (50) for the wireless connection (20); - the scheduler (100) exceptionally determines the target bitrate (52) to be a minimum target bitrate (52) when the normally determined target bitrate (52) is lower than the minimum target bitrate (52), the minimum target bitrate (52) being determined at the measured offset (5) above the transmitted functional minimum data rate (42); - the scheduler (100) further determines a maximum transient response amplitude of the data rate (400) falling below a signaled target bitrate (52) and signals a sequence of consecutively determined transitory target bitrates (520, 521, 522) gradually decreasing from a most recent normally determined target bitrate (52) to the minimum target bitrate (52) when the determined maximum transient response amplitude exceeds the measured offset (5).
  2. The method according to claim 1, wherein the scheduler (100) determines the best effort bitrate (50) based on a fair allocation of spectral resources of the access point (10) and on radio conditions of the wireless connection (20).
  3. The method according to claim 1 or 2, wherein determining the maximum transient response amplitude comprises calculating a data rate difference of a data rate (400) corresponding to the minimum target bitrate (52) from a data rate (400) corresponding to the most recent signaled target bitrate (52) and multiplying the calculated data rate difference with a transient response factor determined using a lookup table created by the scheduler (100), each row of the lookup table comprising a target bitrate difference and a transient response factor associated with the target bitrate difference.
  4. The method according to claim 3, wherein determining the transient response factor comprises immediately retrieving the transient response factor from the lookup table when the lookup table comprises a row with the target bitrate difference.
  5. The method according to claim 3 or 4, wherein determining the transient response factor comprises linearly interpolating the transient response factor from transient response factors of at least two rows of the lookup table when the lookup table does not comprise a row with the target bitrate difference.
  6. The method according to one of claims 3 to 5, wherein the scheduler (100) creates the lookup table by successively signaling a plurality of pairs of respective first target bitrates (52) and second target bitrates (52) and, for each pair, measuring a first data rate of the application (4) at the signaled first target bitrate (52) and a lowest second data rate of the application (4) after signaling the second target bitrate (52), calculating a target bitrate difference of the second target bitrate (52) from the first target bitrate (52), a data rate difference of the lowest second data rate of the application (4) from the first data rate of the application (4) and the transient response factor as a ratio of the data rate difference over the target bitrate difference, and adding the calculated bitrate difference and the calculated transient factor to the lookup table as a row of the lookup table.
  7. The method according to one of claims 1 to 6, wherein each determined transitory target bitrate (520, 521, 522) is signaled at a determined delay (525) after a recently signaled transitory target bitrate (520, 521, 522).
  8. The method according to claims 1 to 7, wherein the scheduler (100) determines the delay (525) as a time interval from signaling a transitory target bitrate (520, 521, 522) to measuring a successive lowest data rate of the distributed real-time application (4).
  9. The method according to one of claims 1 to 8, wherein the signaled sequence of transitory target bitrates (520, 521, 522) end when the recently signaled transitory target bitrate (520, 521, 522) equals the functional minimum data rate increased by the measured offset.
  10. The method according to one of claims 1 to 9, wherein the scheduler (100) determines each transitory target bitrate (520, 521, 522) lower than or equaling the best effort bitrate increased by the measured offset.
  11. The method according to one of claims 1 to 10, wherein the scheduler (100) determines the target bitrate (52) as an output bitrate of a virtual queue defined by the scheduler (100).
  12. The method according to one of claims 1 to 11, wherein determining the best effort bitrate (50) comprises assigning a priority to the transmitted data packets (40), allocating spectral resources to the wireless connection (20) corresponding to the assigned priority and determining a priority bitrate (51) dependent on the allocated spectral resources and on radio conditions of the wireless connection (20).
  13. An access point (10) for a radio access network, RAN, comprising a computing device executing a scheduler (100) configured for carrying out a method according to one of claims 1 to 12. together with a distributed real-time application (4).
  14. A radio access network, RAN, comprising an access point (10) according to claim 13.
  15. A computer program product, comprising a digital storage media with a program code, the program code causing a computing device to operate a scheduler (100) cooperating with a distributed real-time application (4) in a method according to one of claims 1 to 12 when being executed by a processor of the computing device.

Description

The invention relates to a method for operating a scheduler of an access point of a radio access network, RAN, wherein a distributed real-time application transmits a functional minimum data rate of the distributed real-time application to a scheduler of an access point of a RAN, the access point forwarding data packets transmitted by the distributed real-time application via a wireless connection provided by the access point; the scheduler successively signals determined target bitrates to the distributed real-time application and the distributed real-time application dynamically adjusts a data rate of the transmitted data packets at an offset below the signaled target bitrates; the scheduler measures the offset and normally determines a target bitrate at the measured offset above a determined best effort bitrate for the wireless connection; and the scheduler exceptionally determines the target bitrate to be a minimum target bitrate when the normally determined target bitrate is lower than the minimum target bitrate, the minimum target bitrate being determined at the measured offset above the transmitted functional minimum data rate. The invention further relates to an access point for a RAN, a RAN and a computer program product. Methods of the above-mentioned type are known in the state of the art and are used to provide distributed real-time applications with a low and stable latency of the wireless connection. The latency herein indicates an unavoidable transmission delay related to the wireless connection. A stability of the latency corresponds to a low volatility of the latency wherein the volatility of the latency is usually referred to as a jitter. For instance, the scheduler may signal the target bitrate indirectly by applying a low latency low loss scalable throughput, L4S, algorithm to a queue controlled by the scheduler. The L4S algorithm is specified by RFC 9330 and uses an explicit congestion notification, ECN, protocol exploiting bits of an internet protocol, IP, header of the data packets for signaling a filling level of the queue. In greater detail, a sender of the distributed real-time application transmits the data packets via the wireless connection at the data rate, the data rate immediately depending on a size and an incidence, i.e. a frequency of the transmitted data packets. The scheduler provides a percentage of the transmitted data packets with a mark, the percentage indicating the filling level of the queue. A receiver of the distributed real-time application receives the transmitted data packets, measures the percentage of received marked data packets and causes the sender to reduce the data rate until few or no more marked data packets are received. Alternatively the target bitrate may be signaled directly via an application programming interface, API, of the distributed real-time application. The determined best effort bitrate takes into account competing distributed applications connected to the access node and simultaneously transmitting data packets via respective wireless connections. The sender is executed by a first node and the receiver is executed by a second node remote from the first node, the sender and the receiver transmitting data packets via the wireless connection. Alternatively, the first node may execute the receiver while the second node may execute the sender. Of course, the first node and the second node may also alternate in executing the sender and the receiver, respectively, during execution of the distributed real-time application. The distributed real-time application, herein, may also be a near-real-time application and requires a low and stable latency in order to function properly. Autonomous driving, online gaming and video calling are exemplary distributed real-time applications. The real-time application defines a minimum functional data rate being a data rate allowing just a minimum function of the distributed real-time application. In other words, the distributed real-time application does not function at data rates below the functional minimum data rate. In case the data rate falls below the functional minimum data rate the real-time application freezes, i.e., at least temporarily stops functioning. Thus, the scheduler generally determines the target bitrates at the measured offset above the transmitted minimum functional minimum data rate in order to reliably prevent the data rate to be adjusted below the functional minimum data rate and the distributed real-time application from freezing. While, by doing so, the scheduler ensures the distributed real-time application to function properly, the scheduler might eventually disadvantage further wireless connections of competing distributed applications temporarily. The distributed real-time application may provide an application programming interface, API, to be connected to by the scheduler, the functional minimum data rate being transmitted via the API. However, the distributed real-time applic