US-12621206-B2 - Network configuration using coupled oscillators

Abstract

A system includes one or more processors and memory. The memory stores instructions for execution by the one or more processors, including instructions for: obtaining a configuration request for a communications network; configuring a network of models (e.g., oscillators or oscillators'settings) into an initial configuration representing the configuration request for the communications network; reading out a final configuration of the network of models, the final configuration representing a solution to the configuration request for the communications network; and providing information over the communications network according to the configuration request.

Inventors

• Stephen F. Bush

Assignees

• DOLBY INTELLECTUAL PROPERTY LICENSING, LLC

Dates

Publication Date

20260505

Application Date

20221220

Claims (20)

1. 1 . A method, comprising: obtaining a configuration request for a communications network; configuring a network of models into an initial configuration representing the configuration request for the communications network as a quantum program task, the network of models including a network of oscillators; reading out a final configuration of the network of models, the final configuration representing a solution to the configuration request for the communications network; and providing information over the communications network according to the configuration request.
2. 2 . The method of claim 1 , wherein the quantum program task includes a quadratic unconstrained binary optimization (QUBO) task.
3. 3 . The method of claim 1 , wherein configuring the network of models and reading out a final configuration of the network of models are performed in under an amount of time required for data communications.
4. 4 . The method of claim 1 , wherein the configuration request for the communications network is a scheduling request for a deterministic network.
5. 5 . The method of claim 4 , wherein the deterministic network is a self-organizing network (SON).
6. 6 . The method of claim 1 , wherein the configuration request is a time-sensitive network (TSN) scheduling request for a component of a 5G network.
7. 7 . The method of claim 1 , wherein the oscillators are pulse-coupled oscillators.
8. 8 . The method of claim 1 , wherein the oscillators are distributed across a 5G network and information to configure the network of models is sent over the 5G network.
9. 9 . The method of claim 1 , wherein the communications network is a 5G network.
10. 10 . The method of claim 1 , wherein the network of oscillators comprise oscillators selected from the group consisting of: micro-electro-mechanical system (MEMS) oscillators, nano-oscillators, electronic oscillators, crystal oscillators, and transmon.
11. 11 . A device, comprising: one or more processors; and a memory storing instructions for execution by the one or more processors, including instructions for: obtaining a configuration request for a communications network; configuring a network of models into an initial configuration representing the configuration request for the communications network as a quantum program task, the network of models including a network of oscillators; reading out a final configuration of the network of models, the final configuration representing a solution to the configuration request for the communications network; and providing information over the communications network according to the configuration request.
12. 12 . The device of claim 11 , wherein the quantum program task includes a quadratic unconstrained binary optimization (QUBO) task.
13. 13 . The device of claim 11 , wherein configuring the network of models and reading out a final configuration of the network of models are performed in under an amount of time required for data communications.
14. 14 . The device of claim 11 , wherein the oscillators are pulse-coupled oscillators.
15. 15 . The device of claim 11 , wherein the oscillators are distributed across a 5G network and information to configure the network of models is sent over the 5G network.
16. 16 . The device of claim 11 , wherein the network of oscillators comprise oscillators selected from the group consisting of: micro-electro-mechanical system (MEMS) oscillators, nano-oscillators, electronic oscillators, crystal oscillators, and transmon.
17. 17 . A device, comprising: a set of pulse-coupled oscillators; a processor; and a memory storing instructions for execution by the processor, including instructions for: obtaining a configuration information for a communications network from an external controller to configure the set of pulse-coupled oscillators as part of a network of models, wherein the configuration information represents a solution to a configuration request for the communications network based on maximum-likelihood estimation (MLE)-MIMO detection; and configuring the set of pulse-coupled oscillators based on the configuration information from the external controller.
18. 18 . The device of claim 17 , wherein the configuration information for the communications network is represented as a quantum program task, the quantum program task including a quadratic unconstrained binary optimization (QUBO) task.
19. 19 . The device of claim 17 , wherein operations of configuring the network of models and reading out a final configuration of the network of models are performed in under an amount of time required for data communications.
20. 20 . The device of claim 17 , wherein the set of pulse-coupled oscillators is configured to execute a self-organizing network (SON) algorithm to configure the set of pulse-coupled oscillator into an initial configuration representing a network configuration problem, read out a final state of the set of pulse-coupled oscillator, the configuration information is generated based on the final state.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application is a 371 National Entry of International Patent Application No. PCT/US2022/082004, filed Dec. 20, 2022, which claims the benefit of priority to U.S. Provisional Patent Application Ser. No. 63/291,501, filed Dec. 20, 2021 and U.S. Provisional Patent Application Ser. No. 63/292,228, filed Dec. 21, 2021, which are incorporated herein by reference in their entirety. TECHNICAL FIELD The present disclosure relates generally to solving network configuration problems using a network of coupled oscillators (e.g., an Ising machine), such as configuring a schedule for a deterministic network (e.g., a time-sensitive network (TSN)) using a network of coupled oscillators, MIMO detection (e.g., in a 5G network) and precoding to minimize variance for TSN traffic. BACKGROUND Some applications such as industrial automation and manufacturing require ubiquitous and seamless connectivity with strict, deterministic timing requirements for communications between various devices or components (e.g., an industrial controller, a sensor, an actuator, etc.) of the application. To meet such requirements, a TSN system, which provides deterministic communication with relatively stringent quality of service (QOS) parameters, such as latency, jitter and reliability requirements for data traffic, may be integrated with a 5G wireless communication system, which provides a high reliability service, such as an ultra-reliable low latency communication (URLLC) service. TSN scheduling (or more generally, scheduling within a deterministic network), however, is an NP computational problem, and thus conventional methods for calculating TSN schedules are time-consuming and resource intensive. These and other difficult optimization problems, such as MIMO detection (e.g., in a 5G network) and precoding to minimize variance for TSN traffic are addressed by the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS Certain features of the subject technology are set forth in the appended claims. However, for purpose of explanation, several aspects of the subject technology are set forth in the following figures. FIG. 1 illustrates an example of a conventional integrated TSN-5G system 100 in accordance with one or more implementations. FIG. 2 illustrates distribution of a network of oscillators for solving a network configuration problem in a self-organizing network environment as specified by 3GPP (e.g., a TSN scheduling problem, a MIMO detection problem, an SVN problem, etc.). FIG. 3 illustrates distribution of a network of oscillators for solving a network configuration problem in a 5G system (5GS), in accordance with some embodiments. FIG. 4 illustrates a schematic diagram of rapid rescheduling in a TSN network using a network of oscillators, in accordance with some embodiments. FIG. 5 illustrates a network of oscillators, in accordance with some embodiments. FIGS. 6A-6B are flow diagrams illustrating a method of solving a network configuration request, in accordance with some embodiments. FIG. 7 illustrates an electronic system with which one or more implementations of the subject technology may be implemented. FIG. 8 illustrates a general functional framework to implement network configuration techniques using AI/ML, in accordance with some embodiments. DETAILED DESCRIPTION The detailed description set forth below is intended as a description of various configurations of the subject technology and is not intended to represent the only configurations in which the subject technology can be practiced. The appended drawings are incorporated herein and constitute a part of the detailed description. The detailed description includes specific details for the purpose of providing a thorough understanding of the subject technology. However, the subject technology is not limited to the specific details set forth herein and can be practiced using one or more other implementations. In one or more implementations, structures and components are shown in block diagram form in order to avoid obscuring the concepts of the subject technology. As noted above, for some applications such as, but not limited to, industrial automation, manufacturing, and aerospace and automotive in-vehicle communications, a TSN system, which provides deterministic communication may be integrated with a fifth-generation (5G) wireless communication system, which provides flexibility and an ultra-reliable low latency communication (URLLC) service. TSN scheduling, however, is an NP computational problem, and thus conventional methods for calculating TSN schedules are time-consuming and resource intensive. These problems are reduced or mitigated by representing a TSN scheduling problem (or other network configuration problem) through a network of coupled oscillators (e.g., an Ising machine). In accordance with some embodiments, a TSN scheduling request includes a network topology, information about sources (talkers) and destinations (liste