IP Library › Granted Patent US 12,218,734
Granted Patent B2
US 12,218,734 · App. 18/093,602 · Granted Feb 4, 2025

Coordination-free mmWave beam management with deep waveform learning

Inventors: Michele Polese (Boston, MA); Francesco Restuccia (Boston, MA); Tommaso Melodia (Newton, MA)
Assignee: Northeastern University
H04B7/086H04B7/0695H04B7/088
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,218,734
App. No.
18/093,602
Granted
Feb 4, 2025
Kind
B2
Abstract

A system and method for beam management in a wireless network are provided. A learning module having a trained classification module processes received I/Q input samples to determine transmitted beam information of incoming RF transmissions. The learning module includes a beam inference engine to determine waveforms waveform characteristics of incoming RF transmissions beams, and an angle of arrival engine operative to determine an angle of arrival of the incoming RF transmissions beams on an antenna array. An incoming RF transmission beam and angle of arrival are selected based on the determined waveforms for beam management operations.

Claims (40)

1. A system for beam management in a wireless network, comprising:

a radio frequency (RF) receiver comprising an antenna array configured to passively receive incoming RF transmissions without coordination between the RF receiver and a source transmitter of the RF transmissions, wherein the incoming RF transmissions do not include a pilot sequence or a synchronization sequence; and

a processing system comprising:

receiver circuitry in communication with the radio frequency receiver to produce in-phase/quadrature (I/Q) input samples from the incoming RF transmissions, and

a learning module comprising a trained classification module operative to receive the I/Q input samples from the receiver circuitry and process the I/Q input samples to determine transmitted beam information of incoming RF transmissions, the learning module further comprising:

a beam inference engine to determine waveform characteristics of the incoming RF transmissions, and

an angle of arrival engine operative to determine angles of arrival of the incoming RF transmissions on the antenna array,

wherein the processing system is further operative to select an incoming RF transmission and angle of arrival based on the determined waveform characteristics for beam management operations; and

an RF transmitter located at a same node with the RF receiver and in communication with the processing system and operative to transmit RF signals at an angle corresponding to the selected angle of arrival without coordination between the system for beam management and the source transmitter of the RF transmissions.

2. The system of claim 1 , wherein the processing system includes a codebook that comprises a set of codewords corresponding to an identification of the incoming RF transmissions and is operative to select one of the incoming RF transmissions from an identified codeword.

3. The system of claim 1 , wherein the processing system is further operative to associate a quality metric to each of the incoming RF transmissions, the quality metric comprising a received power value, a reference signal received power value, a received signal strength indicator, a reference signal received quality value, a signal-to-noise ratio, or a signal-to-noise-and-interference ratio.

4. The system of claim 3 , wherein the processing system is further operative to rank the incoming RF transmissions by the quality metric associated with each of the incoming RF transmissions.

5. The system of claim 1 , wherein the processing system is operative to match a selected incoming RF transmission at a selected angle of arrival to a synchronization signal block transmitting from a direction corresponding to the selected angle of arrival and corresponding time and frequency resources.

6. The system of claim 1 , wherein the processing system includes a protocol stack including a physical layer and a medium access control layer, and the learning module is in communication with one or both of the physical layer and the medium access control layer to:

receive an activation command to trigger the learning module to process the I/Q samples,

transmit the determined transmitted beam information to the protocol stack, or

both receive an activation command to trigger the learning module to process the I/Q samples and transmit the determined transmitted beam information to the protocol stack.

7. The system of claim 1 , wherein the trained classification module is trained to recognize transitions between occurrences of the I/Q input samples in an I/Q complex plane.

8. The system of claim 1 , wherein the trained classification module comprises a deep learning neural network comprising a convolutional neural network, a multi-layer perceptron, a feedforward network, a recurrent neural network, a long-short term memory neural network, or a support vector machine.

9. The system of claim 1 , wherein the learning module comprises learning circuitry including one or more logic devices.

10. The system of claim 1 , wherein the processing system is operative to carry out the beam management operations including providing initial access to a remote transmitter located at a different node than the RF receiver, tracking of transmissions from one or more remote transmitters, and discovery of neighboring transmitters and receivers.

11. The system of claim 1 , wherein the processing system is operative to receive the incoming transmissions having a frequency of at least 450 MHz.

12. A method for beam management in a wireless network, comprising:

passively detecting, at beam management system having a radio frequency (RF) receiver including an antenna array, incoming RF transmissions without coordination between the RF receiver and a source transmitter of the RF transmissions, wherein the incoming RF transmissions do not include a pilot sequence or a synchronization sequence;

producing, by receiver circuitry of a processing system in communication with the RF receiver, in-phase/quadrature (I/Q) input samples from the incoming RF transmissions;

inputting to a learning module of the processing system, in-phase/quadrature (I/Q) input samples from the incoming RF transmissions;

determining, by a trained classification module of the learning module, transmitted beam information of the incoming RF transmissions including:

determining waveform characteristics of the incoming RF transmissions by processing the I/Q input samples in a beam inference engine of the learning module;

determining angles of arrival of the incoming RF transmissions on the antenna array by processing the I/Q input samples in an angle of arrival engine of the learning module;

selecting an incoming transmission beam based on the angle of arrival and the waveforms for beam management operations; and

transmitting, by an RF transmitter located at a same node with the radio frequency receiver, RF signals at an angle corresponding to the selected angle of arrival without coordination between the beam management system and the source transmitter of the RF transmissions.

13. The method of claim 12 , further comprising performing one or more of the beam management operations, including providing initial access to a transmitter, tracking of transmissions from one or more transmitters, and discovery of neighboring transmitters and receivers.

14. The method of claim 12 , further comprising, from an RF transmitter located at a same node with the RF receiver, transmitting RF signals at an angle corresponding to the selected angle of arrival.

15. The method of claim 12 , further comprising selecting one of the incoming RF transmissions from an identified codeword in a codebook that comprises a set of codewords corresponding to an identification of the incoming RF transmissions.

16. The method of claim 12 , further comprising associating a quality metric to each of the incoming RF transmissions, the quality metric comprising a received power value, a reference signal received power value, a received signal strength indicator, a reference signal received quality value, a signal-to-noise ratio, or a signal-to-noise-and interference ratio.

17. The method of claim 16 , further comprising ranking the incoming RF transmissions by the quality metric associated with each of the incoming RF transmissions.

18. The method of claim 12 , further comprising at least one of:

providing initial access to a remote transmitter located at a different node than the radio frequency receiver;

tracking transmissions from one or more remote transmitters; and

discovering neighboring transmitters and receivers.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 6, 2023
From: POLESE, MICHELE; RESTUCCIA, FRANCESCO; MELODIA, TOMMASO
To: NORTHEASTERN UNIVERSITY
Reel/Frame 062291/0159 →
Continuity (3)
Continuation 17481378 · Sep 22, 2021
Provisional Application 63081938 · Sep 23, 2020
Related Publication 20230163830A1 · May 25, 2023
References Cited (33)
US 10432290B2 · Luo et al. · 2019 [cited by applicant]
US 11588539B2 · Polese · 2023 [cited by examiner]
US 20200120458A1 · Aldana et al. · 2020 [cited by applicant]
US 20200358514A1 · Landis et al. · 2020 [cited by applicant]
US 20210092703A1 · Min · 2021 [cited by examiner]
US 20210135723A1 · Chiu et al. · 2021 [cited by applicant]
US 20210184744A1 · Pezeshki · 2021 [cited by examiner]
US 20210385040A1 · Pezeshki · 2021 [cited by examiner]
US 20210399775A1 · Lehtimaki · 2021 [cited by examiner]
US 20210409089A1 · Haider et al. · 2021 [cited by applicant]
US 20220038163A1 · Va et al. · 2022 [cited by applicant]
US 20220046385A1 · Sundararajan et al. · 2022 [cited by applicant]
US 20220141684A1 · Li · 2022 [cited by examiner]
US 20220158702A1 · Nallampatti Ekambaram et al. · 2022 [cited by applicant]
Giordani et al., “Toward 6G Networks: Use Cases and Technologies,” IEEE Commun. Mag., vol. 58, pp. 55-61, Mar. 2020. [cited by applicant]
Giordani et al., “A Tutorial on Beam Management for 3GPP NR at mmWave Frequencies,” IEEE Commun. Surveys Tuts., vol. 21, pp. 173-196, First Quarter 2019. [cited by applicant]
Asadi et al., “FML: Fast Machine Learning for 5G mmWave Vehicular Communications,” in Proc. of IEEE Conf. on Computer Communications (INFOCOM), pp. 1961-1969; 2018. [cited by applicant]
Haider et al., “LiSteer: mmWave Beam Acquisition and Steering by Tracking Indicator LEDs on Wireless APs,” in Proc. of the 24th Annual Intl. Conf. on Mobile Computing and Networking, pp. 273-288, 2018. [cited by applicant]
O'Shea et al., “An Introduction to Deep Learning for the Physical Layer,” IEEE Trans. Cogn. Commun. Netw., vol. 3, No. 4, pp. 563-575, 2017. [cited by applicant]
O'Shea et al., “Over-the-Air Deep Learning Based Radio Signal Classification,” IEEE J. Sel. Topics Signal Process., vol. 12, pp. 168-179, Feb. 2018. [cited by applicant]
Jian et al., “Deep Learning for RF Fingerprinting: A Massive Experimental Study,” IEEE Internet Things Mag., vol. 3, No. 1, pp. 50-57, 2020. [cited by applicant]
Zhou et al., “Deep Learning-based Beam Management and Interference Coordination in dense mmWave networks,” IEEE Trans. Veh. Technol., vol. 68, No. 1, pp. 592-603, 2018. [cited by applicant]
Alkhateeb et al., “Deep Learning Coordinated Beamforming for Highly-mobile Millimeter Wave Systems,” IEEE Access, vol. 6, pp. 37328-37348, 2018. [cited by applicant]
Alkhateeb, A., “DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications,” in Proc. of Information Theory and Applications Workshop (ITA), pp. 1-8; Feb. 2019. [cited by applicant]
Wang et al., “MmWave Beam Prediction with Situational Awareness: A Machine Learning Approach,” in IEEE 19th Intl. Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 5 pages; IEEE, 2018. [cited by applicant]
Mao et al., “Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey,” IEEE Commun. Surveys Tuts., pp. 2595-2621; Fourth quarter 2018. [cited by applicant]
Sim et al., “An Online Context-Aware Machine Learning Algorithm for 5G mmWave Vehicular Communications,” IEEE/ACM Trans. Netw., vol. 26, No. 6, pp. 2487-2500, 2018. [cited by applicant]
Polese et al., “DeepBeam: Deep Waveform Learning for Coordination-Free Beam Management in mmWave Networks,” arXiv:2012.14350v2 [cs.NI], 10 pages, Jun. 7, 2021. [cited by applicant]
Restuccia et al., “PolymoRF: Polymorphic Wireless Receivers Through Physical-Layer Deep Learning,” Proc. of ACM Mobi-Hoc, pp. 271-280, 2020. [cited by applicant]
Restuccia et al., “Big Data Goes Small: Real-Time Spectrum-Driven Embedded Wireless Networking Through Deep Learning in the RF Loop,” Proc. of IEEE Conf. on Computer Communications (INFOCOM), pp. 2152-2160, 2019. [cited by applicant]
Restuccia et al., “DeepWiERL: Bringing Deep Reinforcement Learning to the Internet of Self-Adaptive Things,” Proc. of IEEE Conf. on Computer Communications (INFOCOM), pp. 844-853, 2020. [cited by applicant]
Riyaz et al., “Deep Learning Convolutional Neural Networks for Radio Identification,” IEEE Commun. Mag., vol. 56, No. 9, pp. 146-152, 2018. [cited by applicant]
Jagannath et al., “Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey,” Ad Hoc Networks (Elsevier), vol. 93, p. 101913, 2019. [cited by applicant]