# US 2026/0163615 A1 · Interference suppression methods for multi-antenna 5g aeromacs to fixed satellite service (fss) systems

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

- Number: US 2026/0163615 A1
- Document ID: US20260163615A1
- Status: Published application
- Kind: A1
- Application number: 19/280,094
- Filed: 2025-07-24
- Published: 2026-06-11
- Earliest claimed: 2024-12-06
- Assignees: Beihang University
- Applicants: Beihang University
- Inventors: Jingjing ZHAO; Kaiquan CAI; Jing SU; Yanbo ZHU; Quan ZHOU
- Web page: https://patentgrep.com/patent/US20260163615A1

## CPC

- H04B 7/043: {using best eigenmode, e.g. beam forming or beam steering}
- H04B 7/0617: {for beam forming}
- H04B 7/0686: {Hybrid systems, i.e. switching and simultaneous transmission}
- H04B 7/0854: {using error minimizing algorithms, e.g. minimum mean squared error [MMSE], "cross-correlation" or matrix inversion}
- H04B 17/3913: {Predictive models, e.g. based on neural network models}
- Y02D 30/70: in wireless communication networks
- H04B: TRANSMISSION
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

An interference suppression method for a multi-antenna 5G AeroMACS to an FSS system is provided, which belongs to the field of wireless communication technology. Embodiments of the present disclosure take a G2A channel matrix as an input, adaptively map the G2A channel matrix to a hybrid beamforming weight matrix and take the hybrid beamforming weight matrix as an output. At the same time, a data-driven GAN-GRU-based G2A channel matrix prediction manner is designed, and an interference suppression manner based on AO HBF is proposed to achieve accurate hybrid beamforming.

## Claims

### Claim 1

An interference suppression method for a multi-antenna 5G aeronautical mobile airport communications system (AeroMACS) to a fixed satellite service (FSS) system, comprising:
constructing a minimum mean square error problem at a receiver under a maximum interference power constraint;
constructing a generative adversarial networks-gated recurrent unit (GAN-GRU)-based ground to air (G2A) channel matrix prediction model and obtaining a predicted G2A channel matrix by using the GAN-GRU-based G2A channel matrix prediction model;
constructing an alternating optimization hybrid beamforming (AO HBF)-based interference suppression model based on the predicted G2A channel matrix; and
obtaining an anti-interference hybrid beamforming by using the AO HBF-based interference suppression model and reducing interference to the FSS system using the anti-interference hybrid beamforming.

### Claim 2 (depends on 1)

The interference suppression method of claim 1, wherein the constructing a minimum mean square error problem at a receiver under a maximum interference power constraint includes:
constructing a received signal model at an aircraft (AC) terminal of a subcarrier in a data transmission stage, wherein the received signal model includes a G2A GS-AC channel matrix of the subcarrier, a baseband precoding matrix of the subcarrier at a ground station (GS) terminal, a radio frequency (RF) precoding matrix at the GS terminal, a baseband combining matrix of the subcarrier at the AC terminal, and an RF combining matrix at the AC terminal; and
constructing a mean squared error (MSE) model based on the received signal model at the AC terminal of the subcarrier in the data transmission stage.

### Claim 3 (depends on 2)

The interference suppression method of claim 2, wherein the GAN-GRU-based G2A channel matrix prediction model includes a GAN-based G2A channel data enhancement module and a GRU-based channel prediction module.

### Claim 4 (depends on 3)

The interference suppression method of claim 3, wherein the GAN-based G2A channel data enhancement module includes a GAN input layer, a generative model, a discriminative model, a training model, and an evaluation model.

### Claim 5 (depends on 4)

The interference suppression method of claim 4, wherein the GRU-based channel prediction module includes a GRU input layer, a GRU unit, and an output layer.

### Claim 6 (depends on 2)

The interference suppression method of claim 2, comprising:
training the GAN-GRU-based G2A channel matrix prediction model by minimizing a loss function GAN-GRU of the GAN-GRU-based G2A channel matrix prediction model, an expression of the loss function being:
ℒ
G
⁢
A
⁢
N
-
GRU
=
{
∑
t
=
1
L
⁢

H
^
B
⁢
A
t
-
H
B
⁢
A
t

2
∑
t
=
1
L
⁢

H
B
⁢
A
t

2
}
⁢
wherein
⁢
H
^
B
⁢
A
t
denotes a predicted G2A channel matrix for a t-th frame of the GAN-GRU-based G2A channel matrix prediction model,
H
B
⁢
A
t
denotes a simulated G2A channel matrix for the t-th frame, denotes a mean value symbol, and L denotes a total count of frames.

### Claim 7 (depends on 1)

The interference suppression method of claim 1, wherein the AO HBF-based interference suppression model includes an RF precoder, a baseband precoder, an RF combiner, and a baseband combiner.
