# US 2023/0412220 A1 · Method and system for unsupervised user clustering and power allocation in non-orthogonal multiple access (noma)-aided massive multiple input-multiple output (mimo) networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0412220 A1
- Document ID: US20230412220A1
- Status: Published application
- Kind: A1
- Application number: 18/252,096
- Filed: 2021-12-01
- Published: 2023-12-21
- Earliest claimed: 2020-12-01
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Sharareh KIANI; Shahram SHAHBAZPANAHI; Majid BAVAND; Gary BOUDREAU; Min DONG
- Web page: https://patentgrep.com/patent/US20230412220A1

## CPC

- H04B 7/0617: {for beam forming}
- G06N 20/00: Machine learning
- H04B 7/0626: {Channel coefficients, e.g. channel state information [CSI]}
- H04L 5/0023: {Time-frequency-space}
- H04L 5/0037: {Inter-user or inter-terminal allocation}
- H04L 5/0057: {Physical resource allocation for CQI}
- H04L 5/006: {Quality of the received signal, e.g. BER, SNR, water filling}
- H04W 52/143: {Downlink power control}
- H04W 52/346: {distributing total power among users or channels}
- H04W 52/42: in systems with time, space, frequency or polarisation diversity
- H04B: TRANSMISSION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Embodiments of a method and network node for managing wireless devices (WDs) in a network are disclosed. In some embodiments, the method comprises grouping the plurality of WDs into clusters based at least in part on correlations between channels of the WDs. The method also includes determining beam forming weights for each cluster, the grouping into clusters and the determining of beam forming weights being performed to minimize a total transmit power to the plurality of WDs.

## Claims

### Claim 1

A method in a network node configured to communicate wirelessly with a plurality of wireless devices, WDs, the method comprising:
grouping the plurality of WDs into clusters based at least in part on correlations between channels of the WDs; and
determining beam forming weights for each cluster, the grouping into clusters and the determining of beam forming weights being performed to minimize a total transmit power to the plurality of WDs.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining a power allocated to each WD of the plurality of WDs that minimizes the total transmit power.

### Claim 3 (depends on 1)

The method of claim 1, wherein the grouping of the plurality of WDs into clusters is performed by an unsupervised machine learning process.

### Claim 4 (depends on 3)

The method of claim 3, wherein the unsupervised machine learning process is configured to maximize a total number of users in each group cluster based at least in part on the correlations.

### Claim 5 (depends on 3)

The method of claim 3, wherein the unsupervised machine learning process includes a mean-shift algorithm.

### Claim 6 (depends on 1)

The method of claim 1, wherein the correlations between the channels are derived from channel state information, CSI, that is one of reported by the plurality of WDs and estimated by the network node.

### Claim 7 (depends on 1)

The method of claim 1, wherein beam forming weights for a cluster are determined based at least in part on a centroid of a function of channel state information, CSI, for the WDs in the cluster.

### Claim 8 (depends on 1)

The method of claim 1, wherein beam forming weights for a cluster are determined based at least in part on a zero-forcing process.

### Claim 9 (depends on 1)

The method of claim 1, further comprising allocating power to WDs within a cluster by application of a non-orthogonal multiple access, NOMA, sequential interference cancellation, SIC, process.

### Claim 10 (depends on 9)

The method of claim 9, wherein the grouping of the plurality of WDs into clusters and the allocating of power to the WDs within a cluster are performed subject to constraints on signal to interference plus noise ratios, SINRs, measured at each WD of the plurality of WDs.

### Claim 11 (depends on 1)

The method of claim 1, wherein the grouping into clusters and the determining of beam forming weights for each cluster is performed in a distributed massive multiple input multiple output, MIMO, non-orthogonal multiple access, NOMA, architecture.

### Claim 12 (depends on 1)

The method of claim 1, wherein the grouping into clusters and the determining of beam forming weights for each cluster is performed in a collocated massive multiple input multiple output, MIMO, non-orthogonal multiple access, NOMA, architecture.

### Claim 13

A network node configured to communicate wirelessly with a plurality of wireless devices, WDs, the network node comprising processing circuitry configured to:
group the plurality of WDs into clusters based at least in part on correlations between channels of the WDs; and
determine beam forming weights for each cluster, the grouping into clusters and the determining of beam forming weights being performed to minimize a total transmit power to the plurality of WDs.

### Claim 14 (depends on 13)

The network node of claim 13, wherein the processing circuitry is further configured to determine a power allocated to each WD of the plurality of WDs that minimizes the total transmit power.

### Claim 15 (depends on 13)

The network node of claim 13, wherein the grouping of the plurality of WDs into clusters is performed by an unsupervised machine learning process.

### Claim 16 (depends on 13)

The network node of claim 13, wherein the unsupervised machine learning process is configured to minimize the total transmit power to the plurality of WDs.

### Claim 17 (depends on 15)

The network node of claim 15, wherein the unsupervised machine learning process includes a mean-shift algorithm.

### Claim 18 (depends on 13)

The network node of claim 13, wherein the correlations between the channels are derived from channel state information, CSI, reported by the plurality of WDs.

### Claim 19 (depends on 13)

The network node of claim 13, wherein beam forming weights for a cluster are determined based at least in part on a centroid of the cluster.

### Claim 20 (depends on 13)

The network node of claim 13, wherein beam forming weights for a cluster are determined based at least in part on a zero-forcing process.

### Claim 21 (depends on 13)

The network node of claim 13, wherein the processing circuitry is further configured to allocate power to WDs within a cluster by application of a non-orthogonal multiple access, NOMA, sequential interference cancellation, SIC, process.

### Claim 22 (depends on 13)

The network node of claim 13, wherein the grouping of the plurality of WDs into clusters and the allocating of power to the WDs within a cluster are performed subject to constraints on signal to interference plus noise ratios, SINRs, measured at each WD of the plurality of WDs.

### Claim 23 (depends on 13)

The network node of claim 13, wherein the grouping into clusters and the determining of beam forming weights for each cluster is performed in a distributed massive multiple input multiple output, MIMO, non-orthogonal multiple access, NOMA, architecture.

### Claim 24 (depends on 13)

The network node of claim 13, wherein the grouping into clusters and the determining of beam forming weights for each cluster is performed in a collocated massive multiple input multiple output, MIMO, non-orthogonal multiple access, NOMA, architecture.
