US-12621822-B2 - Multiple user multiple input multiple output scheduler for fixed wireless access

Abstract

Methods and systems for implementing MU-MIMO scheduling in a network are provided. The method begins with determining at least one signal condition metric for a plurality of signals used for communication between a base station and a plurality of devices. A machine learning model is trained to determine whether a device is a mobile device or a fixed wireless device using training data. The training data comprises at least one signal condition metric for the plurality of signals. Users may connect to the network by a mobile connection or through a fixed connection. An output of the machine learning model is then used to predict a type of connection to the network for each device of the plurality of devices. Then, based on the type of connection, MU-MIMO pairings are assigned to at least a portion of the plurality of devices.

Inventors

• Akin Ozozlu
• Nagi A. Mansour

Assignees

• T-MOBILE INNOVATIONS LLC

Dates

Publication Date

20260505

Application Date

20230425

Claims (20)

1. 1 . A method of multiple user, multiple input, multiple output (MU-MIMO) scheduling in a network, the method comprising: determining at least one signal condition metric for a plurality of signals used for communication between a base station and a plurality of devices; training a machine learning model to determine whether each device of the plurality of devices is a mobile device or a fixed wireless device using training data, the training data comprising the at least one signal condition metric for the plurality of signals; using an output of the machine learning model to predict a type of connection to the network for the each device of the plurality of devices; and based on the type of connection, assigning MU-MIMO pairings to at least a portion of the plurality of devices.
2. 2 . The method of claim 1 , wherein a first device of the plurality of devices is determined to be a fixed wireless device.
3. 3 . The method of claim 2 , wherein the fixed wireless device uses a fixed wireless access point.
4. 4 . The method of claim 2 , wherein the fixed wireless device uses fixed customer premises equipment.
5. 5 . The method of claim 1 , wherein a first device of the plurality of devices is determined to be a mobile device.
6. 6 . The method of claim 1 , wherein the machine learning module determines a type of the plurality of devices based on a fluctuation of the at least one signal condition metric for each device of the plurality of devices.
7. 7 . The method of claim 1 , wherein the at least one signal condition metric comprises at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), or an angle of arrival.
8. 8 . The method of claim 6 , wherein the machine learning module learns the fluctuation of the at least one signal condition metric relative to a mean signal metric of the at least one signal condition metric for the plurality of signals.
9. 9 . The method of claim 6 , wherein the machine learning module learns the fluctuation of the at least one signal condition metric relative to a standard deviation of the at least one signal condition metric for the plurality of signals.
10. 10 . The method of claim 1 , wherein each signal of the plurality of signals uses a same frequency and is sent at a same time to the plurality of devices.
11. 11 . A system for multiple user, multiple input, multiple output (MU-MIMO) scheduling, in a network, comprising: a base station having one or more antennas for receiving a plurality of signals used for communication between the base station and a plurality of devices; a machine learning module configured to communicate with the base station, wherein the machine learning module is trained to determine whether a device is a mobile device or a fixed wireless device using training data, the training data comprising at least one signal condition metric for the plurality of signals; and a scheduler configured to communicate with the machine learning module and the base station, the scheduler using an output of the machine learning module to predict a type of connection to the network for the plurality of devices, wherein the scheduler assigns MU-MIMO pairings to at least a portion of the plurality of devices.
12. 12 . The system of claim 11 , further comprising an artificial intelligence (AI) module configured to communicate with the machine learning module and the scheduler.
13. 13 . The system of claim 11 , wherein an AI module instructs the scheduler to revise a schedule of a downlink signal to the plurality of devices.
14. 14 . The system of claim 13 , wherein the revision is based on a change in the at least one signal condition metric.
15. 15 . The system of claim 14 , wherein the change in the at least one signal condition metric is based on tracking the at least one signal condition metric by the AI module.
16. 16 . A non-transitory computer storage media storing computer-usable instructions that, when used by one or more processors, cause the processor to: determine at least one signal condition metric for a plurality of signals used for communication between a base station and a plurality of devices; train a machine learning model to determine whether each device of the plurality of devices is a mobile device or a fixed wireless device using training data, the training data comprising the at least one signal condition metric for the plurality of signals; use an output of the machine learning model to predict a type of connection to the network for each device of the plurality of devices; and assign MU-MIMO pairings to at least a portion of the plurality of devices based on the type of connection.
17. 17 . The non-transitory computer storage media of claim 16 , wherein a first device of the plurality of devices is determined to be a fixed wireless device.
18. 18 . The non-transitory computer storage media of claim 17 , wherein the fixed wireless device uses fixed customer premises equipment.
19. 19 . The non-transitory computer storage media of claim 16 , wherein a first device of the plurality of devices is determined to be a mobile device.
20. 20 . The non-transitory computer storage media of claim 16 , wherein the machine learning module determines a type of the plurality of devices based on a fluctuation of the at least one signal condition metric for each device of the plurality of devices.

Description

BACKGROUND Multiple user, multiple input, multiple output (MU-MIMO) allows a router to communicate with multiple devices simultaneously. This decreases the amount of time each device has to wait for a signal, thus speeding up the network. When multiple users begin accessing the router at the same time, congestion may arise as the router handles the request from the first device, while other devices wait. These wait times add up as more devices and their users request resources from the network. MU-MIMO allows multiple users to access router functions without congestion and provides increased speeds, up to 10 gigabit, in some use cases. Time division duplex (TDD) systems may user MU-MIMO pairing to reuse frequency and time resources between users in the same cell. Currently, the base station schedules mobile and fixed wireless users with the same or similar MU-MIMO parameters. The current scheduling does not separate mobile users from fixed wireless users, despite differences between use in mobile users and fixed wireless users, resulting in less than optimal use of network resources and capacity. SUMMARY A high-level overview of various aspects of the present technology is provided in this section to introduce a selection of concepts that are further described below in the detailed description section of this disclosure. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in isolation to determine the scope of the claimed subject matter. According to aspects herein, methods and systems for implementing MU-MIMO scheduling in a network are provided. The method begins with determining at least one signal condition metric for a plurality of signals used for communication between a base station and a plurality of devices. Next, a machine learning model is trained to determine whether a device is a mobile device or a fixed wireless device using training data. The training data comprises at least one signal condition metric for the plurality of signals. Users may connect to the network by a mobile connection or through a fixed connection. The fixed connection may use customer premises equipment or may be a fixed wireless connection. An output of the machine learning model is then used to predict a type of connection to the network for each device of the plurality of devices. Then, based on the type of connection, MU-MIMO pairings are assigned to at least a portion of the plurality of devices. This pairings may allow for scheduling the fixed users more aggressively and mobile users less aggressively, providing better resource utilization of resources. BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS Implementations of the present disclosure are described in detail below with reference to the attached drawing figures, wherein: FIG. 1 depicts a diagram of an exemplary network environment in which implementations of the present disclosure may be employed, in accordance with aspects herein; FIG. 2 depicts a cellular network suitable for use in implementations of the present disclosure, in accordance with aspects herein; FIG. 3 depicts a cellular network incorporating MU-MIMO, in which implementations of the present disclosure may be employed, in accordance with aspects herein; FIG. 4 depicts operation of an AI/ML MU-MIMO scheduler in accordance with aspects herein; FIG. 5 depicts a flow diagram of an exemplary method for MU-MIMO scheduling in a network, in accordance with aspects herein; and FIG. 6 depicts an exemplary computing device suitable for use in implementations of the present disclosure, in accordance with aspects herein. DETAILED DESCRIPTION The subject matter of embodiments of the invention is described with specificity herein to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. Rather, the inventors have contemplated that the claimed subject matter might be embodied in other ways, to include different steps or combinations of steps similar to the ones described in this document, in conjunction with other present or future technologies. Moreover, although the terms “step” and/or “block” may be used herein to connote different elements of methods employed, the terms should not be interpreted as implying any particular order among or between various steps herein disclosed unless and except when the order of individual steps is explicitly described. Throughout this disclosure, several acronyms and shorthand notations are employed to aid the understanding of certain concepts pertaining to the associated system and services. These acronyms and shorthand notations are intended to help provide an easy methodology of communicating the ideas expressed herein and are not meant to limit the scope of embodiments described in the present disclosure. The following is a list of these acronyms: 3G Third-Generation Wireless Technology4G Fourth-Generation Cellular Communica