[go: up one dir, main page]

WO2019190368A1 - Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication - Google Patents

Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication Download PDF

Info

Publication number
WO2019190368A1
WO2019190368A1 PCT/SE2018/050334 SE2018050334W WO2019190368A1 WO 2019190368 A1 WO2019190368 A1 WO 2019190368A1 SE 2018050334 W SE2018050334 W SE 2018050334W WO 2019190368 A1 WO2019190368 A1 WO 2019190368A1
Authority
WO
WIPO (PCT)
Prior art keywords
wireless node
wireless
node
data
transmission
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/SE2018/050334
Other languages
English (en)
Inventor
Johan OTTERSTEN
Hugo Tullberg
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Telefonaktiebolaget LM Ericsson AB
Original Assignee
Telefonaktiebolaget LM Ericsson AB
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget LM Ericsson AB filed Critical Telefonaktiebolaget LM Ericsson AB
Priority to PCT/SE2018/050334 priority Critical patent/WO2019190368A1/fr
Publication of WO2019190368A1 publication Critical patent/WO2019190368A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0617—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal for beam forming
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0686—Hybrid systems, i.e. switching and simultaneous transmission
    • H04B7/0695—Hybrid systems, i.e. switching and simultaneous transmission using beam selection
    • H04B7/06952—Selecting one or more beams from a plurality of beams, e.g. beam training, management or sweeping
    • H04B7/0696—Determining beam pairs
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
    • H04B7/0868—Hybrid systems, i.e. switching and combining
    • H04B7/088—Hybrid systems, i.e. switching and combining using beam selection

Definitions

  • Embodiments of the present disclosure relate to beam management in communication networks, and particularly to the selection of transmission and reception beams in wireless communication networks.
  • Beamforming techniques are expected to be employed in both the transmitter (e.g., for downlink communications, a network node such as a base station or other transmission point) and the receiver (e.g., for downlink, a wireless terminal device or user equipment (UE)).
  • a transmission beam is generated by the transmitter when multiple antenna elements are controlled to transmit signals having varied phase and/or amplitude so as to constructively interfere with each other in at least one direction (or angle) and destructively interfere with each other in other directions (or angles).
  • the transmission is stronger in the direction of constructive interference and a beam is generated.
  • a receiver can similarly apply phase and/or amplitude variations to signals received at different antenna elements, so as to constructively interfere with each other in at least one direction (or angle) and destructively interfere with each other in other directions (or angles).
  • signals are received more strongly in the direction of constructive interference and less strongly in other directions (i.e. the receiver is more sensitive to signals received in the direction of constructive interference).
  • the directionality of the receiver is known in the art and hereinafter referred to as a reception beam.
  • the combination of a transmission beam for transmitting signals and a reception beam for receiving those signals is referred to as a beam pair.
  • beam management The process of selecting a beam pair for interactions between a transmitter and a receiver is known as beam management.
  • beam management is divided into three stages, referred to as P1 , P2 and P3.
  • the network node transmits synchronization signal (SS) blocks in the form of wide beams to establish initial beams for transmission and reception.
  • SS synchronization signal
  • the transmitter and the receiver each perform a sweep, in which they search through all available wide beams to find the best pair. That is, the network node transmits SS blocks in each of a plurality of differently directed wide transmission beams, and the UE attempts to detect SS blocks in each of a plurality of differently directed reception beams. The UE detects a suitable SS block via one of the reception beams, and transmits a signal back to the network node (e.g.
  • the network node receives the signal from the UE via a suitably oriented reception beam, and can thus select a correspondingly oriented wide transmission beam.
  • the signal transmitted from the UE to the network node may contain an identifier of the beam via which the SS block was detected, again enabling the network node to select a wide transmission beam for transmissions to the UE.
  • the P2 stage consists of refining the initial beam at the transmitter (network node), while the P3 stage consists of refining the initial beam at the receiver (UE).
  • the transmitter transmits signals (e.g., channel state information reference signals (CSI- RS)) via a plurality of narrow beams arranged within the solid angle of the wide beam selected in P1.
  • the receiver performs measurements on those signals and reports to the transmitter, which may then select a suitable narrow beam based on the measurements.
  • a similar process is then carried out in P3, in which the transmitter transmits a fixed signal using the narrow beam selected in P2, and configured resources for the receiver, while the receiver performs measurements using a plurality of narrow reception beams.
  • a suitable narrow reception beam is then selected by the receiver on the basis of those measurements. This establishes a link made up of two narrow beams, which increases the gain and provides better communication.
  • P2 and P3 can be done either separately or jointly.
  • a separate P2/P3 sweep is described above, and involves refining the beam at the transmitter first (keeping the reception beam fixed) before refining the reception beam (keeping the transmission beam fixed).
  • a joint sweep involves both transmitter and receiver switching their beams simultaneously. In order to synchronize this beam switch, the transmitter and receiver exchange information in a process known as beam indication. This is only required in the joint P2/P3 sweep; in the separate sweep example, the transmitter and receiver can adjust their beams without beam indication.
  • Embodiments of the present disclosure seek to address these and other problems.
  • One aspect of the disclosure provides a method in a node of a communication network, for performing beam management between a first wireless node of the communication network and a second wireless node of the communication network.
  • the method comprises: obtaining input data, the input data comprising: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by the second wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the method further comprises, based on the input data, using a prediction model, developed using a machine-learning algorithm, to determine a beam pair for the first and second wireless nodes to utilize in establishing a beam pair link, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam; and initiating establishment of the beam pair link between the first and second wireless nodes using the determined beam pair.
  • a prediction model developed using a machine-learning algorithm
  • the prediction model is developed based on training data comprising: measurement data from one or more measurements performed by a third wireless node on at least one further signal transmitted by the second wireless node, wherein the at least one further signal is received by the third wireless node on one or more first reception beams and the at least one further signal is transmitted by the second wireless node on at least a first transmission beam; beamforming data indicating beamforming capabilities of the second and third wireless nodes; and an indication of a beam pair selected to establish a beam pair link between the second and third wireless nodes.
  • the method further comprises obtaining feedback data indicative of success of establishment of the beam pair link using the determined beam pair; and using the machine-learning algorithm to update the prediction model based on the feedback data.
  • the feedback data may comprise one or more of: an acknowledgement message transmitted between the first and second wireless nodes; and measurement data from one or more further measurements performed by the first wireless node on at least one signal transmitted by the second wireless node using the second transmission beam.
  • the at least one signal transmitted by the second wireless node using the second transmission beam may comprise a channel state information reference signal.
  • the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first wireless node comprises a user equipment
  • the second wireless node comprises a radio transmission point
  • the method is performed in one of the first wireless node, the second wireless node, and a server which is remote from the first and second wireless nodes.
  • the at least one signal transmitted on at least the first transmission beam comprises a synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the fourth wireless node.
  • the input data further comprises a cell identity associated with the second wireless node.
  • Another aspect of the disclosure provides a method of enabling beam management between wireless nodes of a communication network.
  • the method comprises: obtaining input data, the input data comprising: measurement data from one or more measurements performed by a first wireless node of the communication network on at least one signal transmitted by a second wireless node of the communication network, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the method further comprises obtaining target data, comprising an indication of a beam pair selected to establish a beam pair link between the first and second wireless nodes, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam; and utilizing a machine-learning algorithm to train a prediction model based on the input data and the target data, for use in determining a beam pair for establishment of a beam pair link between the second wireless node and a third wireless node.
  • At least the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first and third wireless nodes comprise user equipments, and the second wireless node comprises a radio transmission point.
  • the at least one signal transmitted on at least the first transmission beam comprises synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data characterising beamforming capabilities of the fourth wireless node.
  • the input data further comprises a cell identity associated with the second wireless node.
  • Another aspect of the disclosure provides a node of a communication network, for performing beam management between a first wireless node of the communication network and a second wireless node of the communication network.
  • the node is configured to carry out any of the methods recited above.
  • a further aspect of the disclosure provides a node of a communication network, for performing beam management between a first wireless node of the communication network and a second wireless node of the communication network.
  • the node comprises processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the node to: obtain input data, the input data comprising: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by the second wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes; based on the input data, use a prediction model, developed using a machine-learning algorithm, to determine a beam pair for the first and second wireless nodes to utilize in establishing a beam pair link, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and
  • the prediction model is developed based on training data comprising: measurement data from one or more measurements performed by a third wireless node on at least one further signal transmitted by the second wireless node, wherein the at least one further signal is received by the third wireless node on one or more first reception beams and the at least one further signal is transmitted by the second wireless node on at least a first transmission beam; beamforming data indicating beamforming capabilities of the second and third wireless nodes; and an indication of a beam pair selected to establish a beam pair link between the second and third wireless nodes.
  • the non-transitory machine-readable medium further stores instructions which, when executed by the processing circuitry, cause the node to: obtain feedback data indicative of success of establishment of the beam pair link using the determined beam pair; and use the machine-learning algorithm to update the prediction model based on the feedback data.
  • the feedback data may comprise one or more of: an acknowledgement message transmitted between the first and second wireless nodes; and measurement data from one or more further measurements performed by the first wireless node on at least one signal transmitted by the second wireless node using the second transmission beam.
  • the at least one signal transmitted by the second wireless node using the second transmission beam may comprise a channel state information reference signal.
  • the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first wireless node comprises a user equipment
  • the second wireless node comprises a radio transmission point
  • the node is one of the first wireless node, the second wireless node, and a server which is remote from the first and second wireless nodes.
  • the at least one signal transmitted on at least the first transmission beam comprises a synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the fourth wireless node.
  • the input data further comprises a cell identity associated with the second wireless node.
  • a further aspect of the disclosure provides a processing device.
  • the processing device comprises processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the processing device to: obtain input data, the input data comprising: measurement data from one or more measurements performed by a first wireless node of a communication network on at least one signal transmitted by a second wireless node of the communication network, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes; obtain target data, comprising an indication of a beam pair selected to establish a beam pair link between the first and second wireless nodes, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam; and utilize a machine-learning algorithm to train a prediction model based on the
  • At least the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first and third wireless nodes comprise user equipments, and the second wireless node comprises a radio transmission point.
  • the at least one signal transmitted on at least the first transmission beam comprises synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data characterising beamforming capabilities of the fourth wireless node.
  • the input data further comprises a cell identity associated with the second wireless node.
  • embodiments of the disclosure simplify the process of selecting a beam pair link for wireless communications between a transmitter and a receiver.
  • the P2 and P3 processes identified in the background section above may be omitted altogether.
  • the beam pair selection process is made quicker, and signalling overhead is reduced.
  • a base station configured to communicate with a user equipment (UE), the base station comprising a radio interface and processing circuitry configured to:
  • the input data comprising: measurement data from one or more measurements performed by the UE on at least one signal transmitted by the base station, wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • a communication system including a host computer comprising:
  • processing circuitry configured to provide user data
  • a communication interface configured to forward the user data to a cellular network for transmission to a user equipment (UE),
  • UE user equipment
  • the cellular network comprises a base station having a radio interface and processing circuitry, the base station’s processing circuitry configured to:
  • input data comprising:
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the processing circuitry of the host computer is configured to execute a host application, thereby providing the user data
  • the UE comprises processing circuitry configured to execute a client application associated with the host application.
  • a method implemented in a base station comprising:
  • the input data comprising:
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the host computer initiating a transmission carrying the user data to the UE via a cellular network comprising the base station, wherein the base station is configured to: obtain input data, the input data comprising: measurement data from one or more measurements performed by the UE on at least one signal transmitted by the base station, wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • a user equipment configured to communicate with a base station, the UE comprising a radio interface and processing circuitry configured to:
  • input data comprising:
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine- learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • a communication system including a host computer comprising:
  • processing circuitry configured to provide user data
  • a communication interface configured to forward user data to a cellular network for transmission to a user equipment (UE),
  • UE user equipment
  • the UE comprises a radio interface and processing circuitry, the UE’s processing circuitry configured to:
  • input data comprising:
  • beamforming data indicating beamforming capabilities of the UE and the base station
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the cellular network further includes a base station configured to communicate with the UE.
  • the processing circuitry of the host computer is configured to execute a host application, thereby providing the user data; and the UE’s processing circuitry is configured to execute a client application associated with the host application.
  • a method implemented in a user equipment comprising:
  • the input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam; and initiating establishment of the beam pair link between the UE and the base station using the determined beam pair.
  • the host computer initiating a transmission carrying the user data to the UE via a cellular network comprising the base station, wherein the UE:
  • the input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam; and initiates establishment of the beam pair link between the UE and the base station using the determined beam pair.
  • a user equipment configured to communicate with a base station, the UE comprising a radio interface and processing circuitry configured to:
  • input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • a communication system including a host computer comprising:
  • a communication interface configured to receive user data originating from a transmission from a user equipment (UE) to a base station
  • the UE comprises a radio interface and processing circuitry, the UE’s processing circuitry configured to:
  • input data comprising:
  • the measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station; based on the input data, use a prediction model, developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam; and
  • the processing circuitry of the host computer is configured to execute a host application
  • the UE’s processing circuitry is configured to execute a client application associated with the host application, thereby providing the user data.
  • the processing circuitry of the host computer is configured to execute a host application, thereby providing request data
  • the UE’s processing circuitry is configured to execute a client application associated with the host application, thereby providing the user data in response to the request data.
  • the input data comprising:
  • the measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station; based on the input data, using a prediction model, developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam; and
  • the host computer receiving user data transmitted to the base station from the UE, wherein the UE:
  • the input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the user data to be transmitted is provided by the client application in response to the input data.
  • a base station configured to communicate with a user equipment (UE), the base station comprising a radio interface and processing circuitry configured to:
  • input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • a communication system including a host computer comprising a communication interface configured to receive user data originating from a transmission from a user equipment (UE) to a base station, wherein the base station comprises a radio interface and processing circuitry, the base station’s processing circuitry configured to:
  • the input data comprising: measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station, wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the processing circuitry of the host computer is configured to execute a host application
  • the UE is configured to execute a client application associated with the host application, thereby providing the user data to be received by the host computer.
  • a method implemented in a base station comprising:
  • the input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • the host computer receiving, from the base station, user data originating from a transmission which the base station has received from the UE, wherein the UE: obtains input data, the input data comprising:
  • measurement data from one or more measurements performed by the UE on at least one signal transmitted by a base station wherein the at least one signal is received by the UE on one or more first reception beams and the at least one signal is transmitted by the base station on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the UE and the base station;
  • a prediction model developed using a machine learning algorithm, to determine a beam pair for the UE and the base station to utilize in establishing a beam pair link, the beam pair comprising a respective second transmission beam and a respective second reception beam for the base station and the UE, wherein the second transmission beam is narrower than the first transmission beam;
  • Figure 1 is a schematic diagram of a wireless communications system according to embodiments of the disclosure
  • Figure 2a is a schematic diagram of a prediction model training process according to embodiments of the disclosure.
  • Figure 2b is a schematic diagram of a prediction model refinement process according to embodiments of the disclosure.
  • Figure 3 is a flowchart of a method of enabling beam management according to embodiments of the disclosure.
  • Figure 4 is a flowchart of a method of beam management according to embodiments of the disclosure.
  • FIG. 5 to 7 illustrate nodes according to embodiments of the disclosure
  • Figure 8 schematically illustrates a telecommunication network connected via an intermediate network to a host computer
  • Figure 9 is a generalized block diagram of a host computer communicating via a base station with a user equipment over a partially wireless connection.
  • Figures 10 to 13 are flowcharts illustrating methods implemented in a communication system including a host computer, a base station and a user equipment.
  • FIG 1 shows a wireless communications system 110 according to embodiments of the present disclosure.
  • the system 1 10 may implement any suitable wireless communications protocol or technology, such as Global System for Mobile communication (GSM), Wide Code-Division Multiple Access (WCDMA), Long Term Evolution (LTE), New Radio (NR), WiFi, WiMAX, or Bluetooth wireless technologies.
  • GSM Global System for Mobile communication
  • WCDMA Wide Code-Division Multiple Access
  • LTE Long Term Evolution
  • NR New Radio
  • WiFi WiMAX
  • Bluetooth wireless technologies such as Bluetooth wireless technology.
  • the system 1 10 comprises a cellular telecommunications network, such as the type developed by the 3 rd Generation Partnership Project (3GPP).
  • 3GPP 3 rd Generation Partnership Project
  • the network nodes 112 may be base stations, NodeBs, eNodeBs, gNodeBs, access points or any other transmission-reception point (TRP).
  • TRP transmission-reception point
  • the network nodes 112 may each serve one or more cells.
  • the system 110 also comprises a wireless device 114 (also referred to as a user equipment (UE), mobile device, mobile terminal, terminal device, etc), which is able to communicate wireless with the network nodes 112.
  • a wireless device 114 also referred to as a user equipment (UE), mobile device, mobile terminal, terminal device, etc
  • Both the network nodes 112 and the wireless device 114 have antennas and transmit/receive circuitry which permit them to use beamforming techniques to transmit and/or receive wireless signals.
  • each device may comprise an antenna array, consisting of a plurality of antenna elements arranged.
  • a transmission beam may be generated using such an antenna array by varying the amplitude and/or phase of signals provided to the multiple antenna elements so as to constructively interfere with each other in at least one direction (or angle) and destructively interfere with each other in other directions (or angles).
  • a reception beam may be generated using such an antenna array by varying the amplitude and/or phase of signals detected by the multiple antenna elements so as to constructively interfere with each other in at least one
  • the width of the beams generated by the network nodes 112 and/or the wireless device 114 may be varied.
  • the network nodes 112 may be capable of generating relatively wide transmission beams 116a, 116b, 116c (collectively, 116), and relatively narrow transmission beams 120.
  • the narrow beams typically extend further from the device than the wide beams, although it should be noted that Figure 1 is not drawn to scale.
  • Figure 1 also shows wide transmission beams 118a, 118b, 118c from network node 112b, and reception beams 124 of the wireless device 114.
  • the width of the beams may be determined by any suitable metric.
  • the width of the beams may be determined by an angular extent of the beam as measured in a particular plane (e.g. a horizontal plane), e.g., an included angle of the beam as subtended at the transmission or reception point.
  • a wide beam will have a greater angular extent than a narrow beam, as subtended at the transmission or reception point.
  • the width of a beam may be determined with respect to the solid angle of the beam, rather than the angular extent of the beam. In such embodiments, a wide beam will have a greater solid angle than a narrow beam as subtended at the transmission or reception point.
  • a solid angle is the two-dimensional angle in three-dimensional space that an object subtends at a point (as measured in steradians).
  • a conical transmission or reception beam for example may subtend a particular solid angle at the transmission or reception point.
  • FIG. 1 further shows, in an optional embodiment, a server 122 which is communicably coupled to both the network node 1 12a and the wireless device 1 14.
  • the server 122 may be embodied in a core network of the system 1 10, or in any other node of the system 110. The function of the server 122 will be discussed in greater detail below.
  • the network nodes 1 12 and the wireless device 114 communicate with each other using beamforming techniques. That is, the network nodes 112 transmit wireless signals to the wireless device 114 using a directional transmission beam, and the wireless device 1 14 receives those wireless signals using a directional reception beam.
  • the combination of the transmission beam and the reception beam is known as a“beam pair”, and the link established between those transmission and reception beams known as a“beam pair link”.
  • a beam pair must be chosen for the establishment of the beam pair link in a process known as beam management. Such a process may be required in various scenarios, such as during initial connection of the wireless device 114 to the network, following loss of connection to the network, or as part of a routine optimization process (i.e., to ensure an appropriate beam pair is utilized for ongoing communication).
  • a predictive model is used to significantly shorten the beam management process and reduce signalling overhead. Following initial acquisition of input data based on wide transmission beams (e.g., as for the P1 process), the predictive model is used to determine a (narrow) beam pair for communication between the network node 112 and the wireless device 114. Thus, the significant signalling of processes P2 and P3, related to measurement and reporting in order to select the narrow transmission and reception beams, is avoided.
  • the predictive model may be developed using one or more machine-learning algorithms. Thus, in such embodiments, the predictive model is first trained.
  • Figure 2a is a schematic diagram of a prediction model training process according to embodiments of the disclosure.
  • Figure 3 is a corresponding flowchart of a training method according to embodiments of the disclosure. The training may be carried out in any suitable processing equipment.
  • Training data 200 is obtained, and passed to a machine learning algorithm 206.
  • the machine-learning algorithm 206 then generates a predictive model 208 based on the training data 200.
  • Several different machine learning techniques may be used for the machine-learning algorithm 206, including decision trees, random forests, neural networks, recurrent neural networks/long-short term memory etc. The present disclosure is not limited in that respect.
  • the training data 200 comprises input data 202 (i.e. , that data which the prediction model 208 is to act upon once trained) and target data 204 (i.e., that data which the prediction model 208 is to be trained to predict, based on the input data).
  • the training data 200 may be obtained by following a P1/P2/P3 procedure substantially as described above.
  • the network nodes 112 utilize wide transmission beams to transmit one or more wireless signals, such as reference signals (e.g., synchronization signals).
  • the network nodes 112 may perform a“sweep” of such transmissions over a plurality of differently oriented wide transmission beams, e.g., in a time-multiplexed fashion.
  • the term“sweep” does not imply that the beams are swept in a clockwise or anticlockwise order; the beams may be swept in any order.
  • the network node 112a transmits one or more wireless signals over wide transmission beams 1 16a, 116b and 1 16c. Although three wide transmission beams are shown, any number of wide transmission beams may be utilized for this purpose. Similarly, network node 112b transmits one or more wireless signals over wide transmission beams 1 18.
  • the wireless device 114 attempts to detect the wireless signals transmitted over the wide transmission beams 116, 118, and particularly performs measurements on the transmitted signals(e.g., synchronization signal blocks) using each of a plurality of reception beams 124, to determine respective metrics for each of the reception beams 124. For example, in one embodiment the wireless device 114 measures the reference signal received power (RSRP) of the wireless signals using each of its reception beams 124.
  • RSRP reference signal received power
  • the wireless device 1 14 obtains data comprising the respective metrics for each of its reception beams 124, as measured for each of one or more wide transmission beams 1 16, 1 18. It will be noted that the measurements may relate to transmissions from one or more network nodes 1 12. For example, if the wireless device 1 14 performs measurements using five reception beams, and detects transmissions from wide beams 1 16b, 116c as well as from a wide beam 118 (from network node 1 12b), the wireless device 1 14 may obtain up to five metrics for each wide beam (up to 15 metrics in total).
  • input data 200 is therefore obtained, in step 300, which comprises some or all of this measurement data, as well as data which is indicative of the beamforming capabilities of the wireless device 114 and the network nodes 112 (“beamforming data”).
  • the measurement data may comprise all of the measurements performed by the wireless device 1 14, or only a subset of the measurements. In the latter case, for example, the measurement data may be limited by including only the metrics for the n best reception beams per transmission beam or the n best reception beams overall (where n is an integer), for example.
  • the measurement data may contain measurements performed on transmissions by one or multiple wide transmission beams. In the latter case, the measurement data may additionally comprise identifiers for the transmission beams in question.
  • the measurement data may contain measurements performed on transmissions by one or multiple network nodes. In the latter case, the measurement data may additionally comprise identifiers for the network nodes in question (e.g. cell IDs, etc).
  • the beamforming data may comprise any data which is indicative of the beamforming capabilities of the wireless device 1 14 and the network nodes 112.
  • the UE type may be indicative of the number of beams supported by the wireless device 1 14.
  • the beamforming data may comprise respective codebooks of the wireless device 1 14 and the network nodes 112.
  • target data 204 is obtained.
  • the target data 204 (i.e. the appropriate beam pair, given the input data 202) may be acquired by following conventional processes, e.g., by following processes P2 and P3 as described above.
  • the wireless device 1 14 selects its own transmission beam for transmission of a signal (e.g. a random access preamble) back to the network node.
  • the wireless device 1 14 may determine the best metric value (e.g., the highest RSRP, strongest signal, etc) and its corresponding wide transmission beam 1 16b and reception beam 124.
  • the wireless device 114 uses its own transmission beam (not illustrated in Figure 1), oriented in a similar direction to the determined reception beam 124, the wireless device 114 transmits a signal (e.g., a random access preamble) back to the network node 112a.
  • the P2 stage consists of refining the initial beam at the transmitter (network node), while the P3 stage consists of refining the initial beam at the receiver (UE).
  • the transmitter transmits signals (e.g., channel state information reference signals (CSI- RS)) via a plurality of narrow beams (e.g., beams 120-n) arranged within the solid angle of the wide beam selected in P1 (e.g., beam 1 16b).
  • the receiver performs measurements on those signals and reports to the transmitter, which may then select a suitable narrow beam based on the measurements.
  • a similar process is then carried out in P3, in which the transmitter transmits a fixed signal using the narrow beam selected in P2, and configured resources for the receiver, while the receiver performs measurements using a plurality of narrow reception beams.
  • a suitable narrow reception beam is then selected by the receiver on the basis of those measurements.
  • Each beam may be identified through an index, or other identifying value.
  • P2 and P3 processes can be performed either separately or jointly.
  • a separate P2/P3 sweep is described above, and involves refining the beam at the transmitter first (keeping the reception beam fixed) before refining the reception beam (keeping the transmission beam fixed).
  • a joint sweep involves both transmitter and receiver switching their beams simultaneously.
  • the transmitter and receiver exchange information in a process known as beam indication. This is only required in the joint P2/P3 sweep; in the separate sweep example, the transmitter and receiver can adjust their beams without beam indication.
  • the selected beam pair then forms the target data 204 for the given input data 202.
  • the machine-learning algorithm 206 utilizes both the target data 204 and the input data 202 to train the prediction model 208 to predict the target data, based on the input data as input. This step is repeated multiple times, iteratively, using different input and target data (i.e. data acquired under different conditions), until the prediction model 208 performs adequately.
  • the machine-learning algorithm 206 may seek to minimize a loss function such as the mean squared error, the cross-entropy cost, the exponential cost or the Kullback-Leibler divergence.
  • the training data 200 comprises input data 202 and target data 204 relating to beam pair selection for a particular network node only (e.g., the network node 1 12a).
  • the training data may relate to beam pair selection for that particular network node and any wireless device (potentially multiple different wireless devices).
  • the training process may be performed in any suitable processing equipment, including the network node itself or in processing equipment remote from the network node.
  • the training data 200 may be obtained through communication with the network node 112 and/or the wireless devices 1 14 which form beam pair links with the network node 112.
  • the UE type may be explicitly signalled by the wireless device 1 14 to the network nodes 112, or may be inferred by the network nodes, for example, based on the measurement pattern of the wireless device 114 (where different UE types have different measurement patterns).
  • Further beamforming capabilities (such as the codebook of the wireless device, for example) may be explicitly signalled between the wireless device 1 14 and the network nodes 1 12.
  • Figures 2a and 3 illustrate a method of training a prediction model to be used in selecting a beam pair for communications between first and second wireless nodes (e.g. between a network node and a wireless device).
  • Figure 2b is a schematic diagram of a process of utilizing that trained prediction according to embodiments of the disclosure, to select a beam for communications between first and second wireless nodes (e.g. between a network node and a wireless device), and also optionally refining the prediction model during use.
  • Figure 4 is a flowchart of a corresponding method. The method may be performed in any node, such as the wireless device (e.g., wireless device 1 14), the network node (e.g., network node 112a) or a remote server (e.g., server 122).
  • Figure 2b is described with relation to Figure 4 below.
  • input data 210 is obtained in step 400.
  • the input data may be substantially similar to input data 200 obtained for the training process, as described above.
  • the dimensionality of the input data may remain the same.
  • the network nodes 1 12 utilize wide transmission beams to transmit one or more wireless signals, such as reference signals (e.g., synchronization signals).
  • the network nodes 112 may perform a“sweep” of such transmissions over a plurality of differently oriented wide transmission beams, e.g., in a time-multiplexed fashion. It will be noted that the term “sweep” does not imply that the beams are swept in a clockwise or anticlockwise order; the beams may be swept in any order.
  • the wireless device 114 attempts to detect the wireless signals transmitted over the wide transmission beams 116, 118, and particularly performs measurements on the transmitted signals(e.g., synchronization signal blocks) using each of a plurality of reception beams 124, to determine respective metrics for each of the reception beams 124. For example, in one embodiment the wireless device 1 14 measures the reference signal received power (RSRP) of the wireless signals using each of its reception beams 124.
  • RSRP reference signal received power
  • the wireless device 1 14 obtains data comprising the respective metrics for each of its reception beams 124, as measured for each of one or more wide transmission beams 1 16, 1 18. It will be noted that the measurements may relate to transmissions from one or more network nodes 112. For example, if the wireless device 1 14 performs measurements using five reception beams, and detects transmissions from wide beams 1 16b, 116c as well as from a wide beam 118 (from network node 1 12b), the wireless device 1 14 may obtain up to five metrics for each wide beam (up to 15 metrics in total).
  • the input data comprises measurement data and beamforming data.
  • the measurement data may comprise all of the measurements performed by the wireless device 1 14, or only a subset of the measurements. In the latter case, for example, the measurement data may be limited by including only the metrics for the n best reception beams per transmission beam or the n best reception beams overall (where n is an integer), for example.
  • the measurement data may contain measurements performed on transmissions by one or multiple wide transmission beams. In the latter case, the measurement data may additionally comprise identifiers for the transmission beams in question.
  • the measurement data may contain measurements performed on transmissions by one or multiple network nodes. In the latter case, the measurement data may additionally comprise identifiers for the network nodes in question (e.g. cell IDs, etc).
  • the beamforming data may comprise any data which is indicative of the beamforming capabilities of the wireless device 1 14 and the network node 1 12.
  • the UE type may be indicative of the number of beams supported by the wireless device 1 14.
  • the beamforming data may comprise respective codebooks of the wireless device 1 14 and the network node 1 12.
  • the method may be performed in the wireless device, the network node, or a remote server. If performed in the wireless device, the wireless device therefore obtains knowledge as to the beamforming capabilities of the network node. Such beamforming data may be provided in signalling from the network node to the wireless device (e.g. as part of system information broadcast). If the method is performed in the network node, the network node therefore obtains knowledge as to the beamforming capabilities of the wireless device, as well as the measurement data obtained by the wireless device. In this case, the wireless device may signal the measurement data and/or its beamforming capabilities to the network node (e.g. together with the random access preamble message, or subsequent to transmission of the random access preamble message).
  • the wireless device may signal the measurement data and/or its beamforming capabilities to the network node (e.g. together with the random access preamble message, or subsequent to transmission of the random access preamble message).
  • the beamforming capabilities of the wireless device may be inferred by the network node.
  • the UE type may be inferred by the network node based on the measurement pattern of the wireless device (where different UE types have different measurement patterns). If the method is performed in the remote server, similar considerations may apply as for the network node discussed above, with the network node transmitting the input data (i.e. the measurement data and beamforming data for the wireless device, as well as its own beamforming data) to the remote server for processing.
  • the input data 210 is provided to a prediction model 212 in order to determine an appropriate beam pair 214 for use by the network node and the wireless device.
  • the prediction model for example based on the training process described above with respect to Figures 2a and 3, outputs a beam pair 214 comprising a transmission beam (e.g., for the network node) and a reception beam (e.g., for the wireless device).
  • At least the transmission beam is relatively narrow compared to the wide transmission beam used to generate the input data 210.
  • both the selected transmission and reception beams are relatively narrow compared to the transmission and reception beams used to generate the input data 210.
  • step 404 the establishment of a beam pair link between the network node and the wireless device is initiated, using the beam pair 214 output by the prediction model 212.
  • the network node may transmit a wireless signal to the wireless device, using its determined transmission beam, and comprising an indication of the proposed reception beam for use by the wireless device (e.g., a beam index or other identifier).
  • the server may transmit an instruction to the network node comprising an indication of the determined beam pair.
  • the network node may then follow a similar process and transmit to the wireless device using its determined transmission beam, and comprising an indication of the proposed reception beam for use by the wireless device.
  • the wireless device may transmit a wireless signal to the network node comprising an indication of the proposed transmission beam for use by the network node (e.g., a beam index or other identifier).
  • Beam indication signalling may be utilized to ensure that the network node 112 and the wireless device 114 switch to the determined beams simultaneously.
  • the prediction model 212 significantly reduces the latency and the signalling overhead associated with selecting a narrow beam pair for use in communications between first and second wireless nodes (e.g. a network node and a wireless device).
  • first and second wireless nodes e.g. a network node and a wireless device.
  • the method ends at this point, with establishment of the beam pair link between the first and second wireless nodes.
  • the method continues so as to refine the predictive model based on feedback data.
  • step 406 the node obtains feedback data 216 which is indicative of the success (or failure) of the establishment of the beam pair link using the beam pair determined in step 402.
  • successful establishment of the beam pair link may be determined by the transmission between the network node 1 12a and the wireless device 1 14 of a positive acknowledgement message, such as an ACK message used in hybrid automatic request (HARQ), to indicate the successful transmission of data between the network node 112a and the wireless device 1 14 using the beam pair link.
  • a positive acknowledgement message such as an ACK message used in hybrid automatic request (HARQ)
  • HARQ hybrid automatic request
  • Such an acknowledgement message may be used as positive feedback to indicate the successful establishment of the beam pair link.
  • transmission of a negative acknowledgement message between the network node 1 12a and the wireless device such as a NACK message used in HARQ, may be indicative that establishment of the beam pair link was unsuccessful, or at least subject to poor radio performance. In this case, the negative acknowledgement message may be used as negative feedback.
  • successful establishment of the beam pair link may be determined based on measurement data obtained by the network node 112a and/or the wireless device 1 14.
  • the network node 1 12a may periodically transmit reference signals (e.g. CSI-RS) using some or all of the narrow transmission beams 120 (e.g., in a beam sweep), while the wireless device 114 may perform measurements on some or all of those reference signals using its reception beams to obtain a metric ( e.g. CSI-RS).
  • the wireless device 1 14 reports some or all of the measured values to the network.
  • the wireless device 1 14 may report the measured values for only the x narrow transmission beams having the highest measured values (where x is an integer). In this way, the network node 112a and the wireless device 1 14 may ensure that the connection between the two wireless nodes is not lost, for example, as a result of changing radio conditions or movement of the wireless device 114 relative to the network node 112a.
  • positive feedback indicative of a successful beam pair link establishment may be obtained if the beam pair determined in step 402 is associated with the highest metric value reported by the wireless device 1 14. In further embodiments, positive feedback may be obtained if the beam pair determined in step 402 is associated with one of the highest metric values reported by the wireless device 114 (e.g., the x highest values). In such embodiments, an established beam pair link may be considered a success even if it is not associated with the highest value.
  • the beam pair determined in step 402 is not associated with the highest metric value reported by the wireless device 114, or not associated with the x highest values, or not reported by the wireless device 114 at all, negative feedback may be obtained.
  • the wireless device 114 If the method is performed by the wireless device 114, such feedback information is inherently available to the wireless device, in the form of acknowledgement messages transmitted or received by it, or measurements performed by it. If the method is performed by the network node 112a, the acknowledgement messages transmitted or received by the node will again be inherently available, while the measurements are transmitted to the network node in reports by the wireless device 1 14. If the method is performed by the server 122, the wireless device 114 and/or the network node 112a may transmit the relevant feedback data to the server 122.
  • the feedback data 216 is provided to a machine-learning algorithm 218 which, in step 408, updates the prediction model 212 based on the feedback data 216.
  • a machine-learning algorithm 218 which, in step 408, updates the prediction model 212 based on the feedback data 216.
  • various methods may be used to update the prediction model based on the feedback data 216. For example, reinforcement learning techniques based on data from current and past time instances may be used to update the model or, alternatively, simpler techniques may utilize only data from the current time instance to update the model 212.
  • the machine-learning algorithm 218 used for refinement of the prediction model 212 may be different to the machine-learning algorithm 206 used for training the prediction model 208.
  • embodiments of the disclosure additionally comprise a method for updating a prediction model while that model has been deployed for use in a network.
  • the model can be updated to take account of a changing environment (e.g. the erection of buildings in the vicinity of the network node, changing natural environment, etc).
  • a changing environment e.g. the erection of buildings in the vicinity of the network node, changing natural environment, etc.
  • the description above has focussed primarily on the use of wide and narrow transmission beams by a network node, and the use of reception beams by a wireless device. However, those skilled in the art will appreciate that the reverse of this scenario is also possible.
  • the wireless device may transmit signals over a plurality of wide transmission beams, such as a request for synchronization to the network.
  • a network node may then perform measurements on the transmitted signals, and use those measurements as the inputs to a prediction model to determine a beam pair.
  • a prediction model to determine a beam pair for first and second wireless nodes.
  • FIG 5 is a schematic illustration of a node or processing device 500 according to embodiments of the disclosure.
  • the node or processing device 500 may be configured to perform the methods of Figures 3 and/or 4.
  • the node or processing device 500 may be implemented within a wireless device (such as the wireless device 1 14 described above), a network node (such as the network node 112a described above) or in any other processing device or server (such as the server 122 described above).
  • the node or processing device 500 comprises processing circuitry 502 and a non- transitory machine-readable medium 504 (such as memory).
  • the node or processing device 500 also comprises one or more interfaces 506 for communication with other nodes or devices.
  • the node or processing device 500 is provided for performing beam management between a first wireless node of a communication network and a second wireless node of the communication network.
  • the memory 504 stores instructions which, when executed by the processing circuitry 502, cause the node or processing device 500 to: obtain input data.
  • the input data comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by the second wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the node or processing device 500 is further caused to, based on the input data, use a prediction model, developed using a machine-learning algorithm, to determine a beam pair for the first and second wireless nodes to utilize in establishing a beam pair link, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam; and initiate establishment of the beam pair link between the first and second wireless nodes using the determined beam pair.
  • a prediction model developed using a machine-learning algorithm
  • the memory 504 stores instructions which, when executed by the processing circuitry 502, cause the node or processing device 500 to: obtain input data.
  • the input data comprises: measurement data from one or more measurements performed by a first wireless node of a communication network on at least one signal transmitted by a second wireless node of the communication network, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the node or processing device 500 is further caused to obtain target data, comprising an indication of a beam pair selected to establish a beam pair link between the first and second wireless nodes, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam; and utilize a machine-learning algorithm to train a prediction model based on the input data and the target data, for use in determining a beam pair for establishment of a beam pair link between the second wireless node and a third wireless node.
  • FIG. 5 shows the processing circuitry 502, the memory 504 and the interface(s) 506 coupled together in series, those skilled in the art will appreciate that the components of the node or processing device 500 may be coupled together in any suitable manner (e.g. via a bus or other internal connection).
  • FIG. 6 is a schematic illustration of a node or processing device 600 according to further embodiments of the disclosure.
  • the node or processing device 600 may be configured to perform the methods of Figure 3.
  • the node or processing device 600 may be implemented within a wireless device (such as the wireless device 1 14 described above), a network node (such as the network node 112a described above) or in any other processing device or server (such as the server 122 described above).
  • the node or processing device 600 comprises an obtaining module 602, a predicting module 604 and an initiating module 606.
  • the modules may be implemented purely in hardware, purely in software, or in a combination of hardware and software.
  • the node or processing device 600 is provided for performing beam management between a first wireless node of a communication network and a second wireless node of the communication network.
  • the obtaining module 602 is configured to obtain input data.
  • the input data comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by the second wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the predicting module 604 is configured to, based on the input data, use a prediction model, developed using a machine-learning algorithm, to determine a beam pair for the first and second wireless nodes to utilize in establishing a beam pair link, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam.
  • the initiating module 606 is configured to initiate establishment of the beam pair link between the first and second wireless nodes using the determined beam pair.
  • the prediction model is developed based on training data comprising: measurement data from one or more measurements performed by a third wireless node on at least one further signal transmitted by the second wireless node, wherein the at least one further signal is received by the third wireless node on one or more first reception beams and the at least one further signal is transmitted by the second wireless node on at least a first transmission beam; beamforming data indicating beamforming capabilities of the second and third wireless nodes; and an indication of a beam pair selected to establish a beam pair link between the second and third wireless nodes.
  • the obtaining module 502 is further configured to: obtain feedback data indicative of success of establishment of the beam pair link using the determined beam pair, and the predicting module 604 is configured to update the prediction model based on the feedback data.
  • the feedback data may comprise one or more of: an acknowledgement message transmitted between the first and second wireless nodes; and measurement data from one or more further measurements performed by the first wireless node on at least one signal transmitted by the second wireless node using the second transmission beam.
  • the at least one signal transmitted by the second wireless node using the second transmission beam may comprise a channel state information reference signal.
  • the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first wireless node comprises a user equipment
  • the second wireless node comprises a radio transmission point
  • the node or processing device 600 is one of the first wireless node, the second wireless node, and a server which is remote from the first and second wireless nodes.
  • the at least one signal transmitted on at least the first transmission beam comprises a synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the fourth wireless node.
  • the input data further comprises a cell identity associated with the second wireless node.
  • Figure 7 is a schematic illustration of a node or processing device 700 according to further embodiments of the disclosure.
  • the node or processing device 700 may be configured to perform the methods of Figure 4.
  • the node or processing device 700 may be implemented within a wireless device (such as the wireless device 114 described above), a network node (such as the network node 112a described above) or in any other processing device or server (such as the server 122 described above).
  • the node or processing device 700 comprises an obtaining module 702 and a training module 704.
  • the modules may be implemented purely in hardware, purely in software, or in a combination of hardware and software.
  • the obtaining module 702 is configured to obtain input data.
  • the input data comprises: measurement data from one or more measurements performed by a first wireless node of a communication network on at least one signal transmitted by a second wireless node of the communication network, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the second wireless node on at least a first transmission beam; and beamforming data indicating beamforming capabilities of the first and second wireless nodes.
  • the obtaining module 702 is further configured to obtain target data, comprising an indication of a beam pair selected to establish a beam pair link between the first and second wireless nodes, the beam pair comprising a respective second reception beam and a respective second transmission beam for the first and second wireless nodes, wherein the second transmission beam is narrower than the first transmission beam.
  • the training module 704 is configured to utilize a machine-learning algorithm to train a prediction model based on the input data and the target data, for use in determining a beam pair for establishment of a beam pair link between the second wireless node and a third wireless node.
  • At least the second transmission beam is determined from a plurality of candidate second transmission beams arranged within a solid angle of the first transmission beam.
  • the first and third wireless nodes comprise user equipments, and the second wireless node comprises a radio transmission point.
  • the at least one signal transmitted on at least the first transmission beam comprises synchronization signal.
  • the input data further comprises: measurement data from one or more measurements performed by the first wireless node on at least one signal transmitted by a fourth wireless node, wherein the at least one signal is received by the first wireless node on one or more first reception beams and the at least one signal is transmitted by the fourth wireless node on at least a first transmission beam; and beamforming data characterising beamforming capabilities of the fourth wireless node
  • the input data further comprises a cell identity associated with the second wireless node.
  • a communication system includes a telecommunication network 810, such as a 3GPP-type cellular network, which comprises an access network 811 , such as a radio access network, and a core network 814.
  • the access network 811 comprises a plurality of base stations 812a, 812b, 812c, such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 813a, 813b, 813c.
  • Each base station 812a, 812b, 812c is connectable to the core network 814 over a wired or wireless connection 815.
  • a first user equipment (UE) 891 located in coverage area 813c is configured to wirelessly connect to, or be paged by, the corresponding base station 812c.
  • a second UE 892 in coverage area 813a is wirelessly connectable to the corresponding base station 812a. While a plurality of UEs 891 , 892 are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding base station 812.
  • the telecommunication network 810 is itself connected to a host computer 830, which may be embodied in the hardware and/or software of a standalone server, a cloud- implemented server, a distributed server or as processing resources in a server farm.
  • the host computer 830 may be under the ownership or control of a service provider, or may be operated by the service provider or on behalf of the service provider.
  • the connections 821 , 822 between the telecommunication network 810 and the host computer 830 may extend directly from the core network 814 to the host computer 830 or may go via an optional intermediate network 820.
  • the intermediate network 820 may be one of, or a combination of more than one of, a public, private or hosted network; the intermediate network 820, if any, may be a backbone network or the Internet; in particular, the intermediate network 820 may comprise two or more sub-networks (not shown).
  • the communication system of Figure 8 as a whole enables connectivity between one of the connected UEs 891 , 892 and the host computer 830.
  • the connectivity may be described as an over-the-top (OTT) connection 850.
  • the host computer 830 and the connected UEs 891 , 892 are configured to communicate data and/or signaling via the OTT connection 850, using the access network 811 , the core network 814, any intermediate network 820 and possible further infrastructure (not shown) as intermediaries.
  • the OTT connection 850 may be transparent in the sense that the participating communication devices through which the OTT connection 850 passes are unaware of routing of uplink and downlink communications. For example, a base station 812 may not or need not be informed about the past routing of an incoming downlink communication with data originating from a host computer 830 to be forwarded (e.g., handed over) to a connected UE 891. Similarly, the base station 812 need not be aware of the future routing of an outgoing uplink communication originating from the UE 891 towards the host computer 830.
  • a host computer 910 comprises hardware 915 including a communication interface 916 configured to set up and maintain a wired or wireless connection with an interface of a different communication device of the communication system 900.
  • the host computer 910 further comprises processing circuitry 918, which may have storage and/or processing capabilities.
  • the processing circuitry 918 may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions.
  • the host computer 910 further comprises software 911 , which is stored in or accessible by the host computer 910 and executable by the processing circuitry 918.
  • the software 911 includes a host application 912.
  • the host application 912 may be operable to provide a service to a remote user, such as a UE 930 connecting via an OTT connection 950 terminating at the UE 930 and the host computer 910. In providing the service to the remote user, the host application 912 may provide user data which is transmitted using the OTT connection 950.
  • the communication system 900 further includes a base station 920 provided in a telecommunication system and comprising hardware 925 enabling it to communicate with the host computer 910 and with the UE 930.
  • the hardware 925 may include a communication interface 926 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of the communication system 900, as well as a radio interface 927 for setting up and maintaining at least a wireless connection 970 with a UE 930 located in a coverage area (not shown in Figure 9) served by the base station 920.
  • the communication interface 926 may be configured to facilitate a connection 960 to the host computer 910.
  • connection 960 may be direct or it may pass through a core network (not shown in Figure 9) of the telecommunication system and/or through one or more intermediate networks outside the telecommunication system.
  • the hardware 925 of the base station 920 further includes processing circuitry 928, which may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions.
  • the base station 920 further has software 921 stored internally or accessible via an external connection.
  • the communication system 900 further includes the UE 930 already referred to.
  • Its hardware 935 may include a radio interface 937 configured to set up and maintain a wireless connection 970 with a base station serving a coverage area in which the UE 930 is currently located.
  • the hardware 935 of the UE 930 further includes processing circuitry 938, which may comprise one or more programmable processors, application- specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions.
  • the UE 930 further comprises software 931 , which is stored in or accessible by the UE 930 and executable by the processing circuitry 938.
  • the software 931 includes a client application 932.
  • the client application 932 may be operable to provide a service to a human or non-human user via the UE 930, with the support of the host computer 910.
  • an executing host application 912 may communicate with the executing client application 932 via the OTT connection 950 terminating at the UE 930 and the host computer 910.
  • the client application 932 may receive request data from the host application 912 and provide user data in response to the request data.
  • the OTT connection 950 may transfer both the request data and the user data.
  • the client application 932 may interact with the user to generate the user data that it provides.
  • the host computer 910, base station 920 and UE 930 illustrated in Figure 9 may be identical to the host computer 830, one of the base stations 812a, 812b, 812c and one of the UEs 891 , 892 of Figure 8, respectively.
  • the inner workings of these entities may be as shown in Figure 9 and independently, the surrounding network topology may be that of Figure 8.
  • the OTT connection 950 has been drawn abstractly to illustrate the communication between the host computer 910 and the use equipment 930 via the base station 920, without explicit reference to any intermediary devices and the precise routing of messages via these devices.
  • Network infrastructure may determine the routing, which it may be configured to hide from the UE 930 or from the service provider operating the host computer 910, or both. While the OTT connection 950 is active, the network infrastructure may further take decisions by which it dynamically changes the routing (e.g., on the basis of load balancing consideration or reconfiguration of the network).
  • the wireless connection 970 between the UE 930 and the base station 920 is established in accordance with the teachings of the embodiments described throughout this disclosure (e.g., as described above with respect to Figure 4).
  • One or more of the various embodiments improve the performance of OTT services provided to the UE 930 using the OTT connection 950, in which the wireless connection 970 forms the last segment. More precisely, the teachings of these embodiments may improve the power consumption (e.g., by reducing signaling overhead) and the latency (e.g., by replacing the signaling and measurement processes (P2 and P3) with a prediction model), and thereby provide benefits such as reduced user waiting time and extended battery lifetime.
  • a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.
  • the measurement procedure and/or the network functionality for reconfiguring the OTT connection 950 may be implemented in the software 911 of the host computer 910 or in the software 931 of the UE 930, or both.
  • sensors (not shown) may be deployed in or in association with communication devices through which the OTT connection 950 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software 91 1 , 931 may compute or estimate the monitored quantities.
  • the reconfiguring of the OTT connection 950 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not affect the base station 920, and it may be unknown or imperceptible to the base station 920. Such procedures and functionalities may be known and practiced in the art.
  • measurements may involve proprietary UE signaling facilitating the host computer’s 910 measurements of throughput, propagation times, latency and the like.
  • the measurements may be implemented in that the software 91 1 , 931 causes messages to be transmitted, in particular empty or‘dummy’ messages, using the OTT connection 950 while it monitors propagation times, errors etc.
  • FIGURE 10 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment.
  • the communication system includes a host computer, a base station and a UE which may be those described with reference to Figures 8 and 9. For simplicity of the present disclosure, only drawing references to Figure 10 will be included in this section.
  • the host computer provides user data.
  • the host computer provides the user data by executing a host application.
  • the host computer initiates a transmission carrying the user data to the UE.
  • the base station transmits to the UE the user data which was carried in the transmission that the host computer initiated, in accordance with the teachings of the embodiments described throughout this disclosure.
  • the UE executes a client application associated with the host application executed by the host computer.
  • FIGURE 11 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment.
  • the communication system includes a host computer, a base station and a UE which may be those described with reference to Figures 8 and 9. For simplicity of the present disclosure, only drawing references to Figure 1 1 will be included in this section.
  • the host computer provides user data.
  • the host computer provides the user data by executing a host application.
  • the host computer initiates a transmission carrying the user data to the UE. The transmission may pass via the base station, in accordance with the teachings of the embodiments described throughout this disclosure.
  • the UE receives the user data carried in the transmission.
  • FIGURE 12 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment.
  • the communication system includes a host computer, a base station and a UE which may be those described with reference to Figures 8 and 9. For simplicity of the present disclosure, only drawing references to Figure 12 will be included in this section.
  • the UE receives input data provided by the host computer.
  • the UE provides user data.
  • the UE provides the user data by executing a client application.
  • the UE executes a client application which provides the user data in reaction to the received input data provided by the host computer.
  • the executed client application may further consider user input received from the user.
  • the UE initiates, in an optional third substep 1230, transmission of the user data to the host computer.
  • the host computer receives the user data transmitted from the UE, in accordance with the teachings of the embodiments described throughout this disclosure.
  • FIGURE 13 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment.
  • the communication system includes a host computer, a base station and a UE which may be those described with reference to Figures 8 and 9. For simplicity of the present disclosure, only drawing references to Figure 13 will be included in this section.
  • the base station receives user data from the UE.
  • the base station initiates transmission of the received user data to the host computer.
  • the host computer receives the user data carried in the transmission initiated by the base station.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

L'invention concerne des procédés, un appareil, et des programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication. L'invention concerne un procédé exécuté dans un nœud d'un réseau de communication, pour exécuter une gestion de faisceau entre un premier nœud sans fil du réseau de communication et un second nœud sans fil du réseau de communication. Le procédé consiste à obtenir des données d'entrée comprenant : des données de mesurage provenant d'un ou plusieurs mesurages exécutés par le premier nœud sans fil sur au moins un signal émis par le second nœud sans fil, le ou les signaux étant reçus par le premier nœud sans fil sur un ou plusieurs premiers faisceaux de réception et le ou les signaux étant transmis par le second nœud sans fil sur au moins un premier faisceau de transmission; et des données de formation de faisceau indiquant les capacités de formation de faisceau des premier et second nœuds sans fil. Le procédé consiste en outre à : utiliser, sur la base des données d'entrée, un modèle de prédiction développé à l'aide d'un algorithme d'apprentissage automatique afin de déterminer une paire de faisceaux pour les premier et second nœuds sans fil à utiliser lors de l'établissement d'une liaison de paire de faisceaux, la paire de faisceaux comprenant un second faisceau de réception respectif et un second faisceau de transmission respectif pour les premier et second nœuds sans fil, le second faisceau de transmission étant plus étroit que le premier faisceau de transmission; et initier l'établissement de la liaison de paire de faisceaux entre les premier et second nœuds sans fil à l'aide de la paire de faisceaux déterminée.
PCT/SE2018/050334 2018-03-28 2018-03-28 Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication Ceased WO2019190368A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/SE2018/050334 WO2019190368A1 (fr) 2018-03-28 2018-03-28 Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/SE2018/050334 WO2019190368A1 (fr) 2018-03-28 2018-03-28 Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication

Publications (1)

Publication Number Publication Date
WO2019190368A1 true WO2019190368A1 (fr) 2019-10-03

Family

ID=68060661

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SE2018/050334 Ceased WO2019190368A1 (fr) 2018-03-28 2018-03-28 Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication

Country Status (1)

Country Link
WO (1) WO2019190368A1 (fr)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112886996A (zh) * 2019-11-29 2021-06-01 北京三星通信技术研究有限公司 信号接收方法、用户设备、电子设备及计算机存储介质
WO2021211703A1 (fr) * 2020-04-16 2021-10-21 Qualcomm Incorporated Sélection de modèle d'apprentissage automatique dans des communications formées en faisceau
US20210391911A1 (en) * 2018-09-28 2021-12-16 Nokia Technologies Oy Beam alignment
CN114390580A (zh) * 2020-10-20 2022-04-22 维沃移动通信有限公司 波束上报方法、波束信息确定方法及相关设备
CN114938712A (zh) * 2022-04-13 2022-08-23 北京小米移动软件有限公司 波束选择方法和装置
WO2022237832A1 (fr) * 2021-05-12 2022-11-17 维沃移动通信有限公司 Procédé et appareil de traitement d'informations, terminal et dispositif côté réseau
WO2023119136A1 (fr) * 2021-12-20 2023-06-29 Lenovo (Singapore) Pte. Ltd. Gestion de faisceau activée par intelligence artificielle
WO2023123127A1 (fr) * 2021-12-29 2023-07-06 Oppo广东移动通信有限公司 Procédé et appareil d'interaction d'informations de gestion de faisceaux, terminal et support
WO2023197222A1 (fr) * 2022-04-13 2023-10-19 北京小米移动软件有限公司 Procédé et appareil de prédiction de faisceau, dispositif, et support de stockage
WO2023211350A1 (fr) * 2022-04-29 2023-11-02 Telefonaktiebolaget Lm Ericsson (Publ) Informations d'assistance d'équipement utilisateur pour de meilleures prédictions de faisceau de réseau
WO2023212890A1 (fr) * 2022-05-06 2023-11-09 Qualcomm Incorporated Techniques de prédiction de caractéristiques de faisceau à l'aide de processus d'apprentissage fédérés
WO2023216020A1 (fr) * 2022-05-07 2023-11-16 Qualcomm Incorporated Gestion prédictive de ressources à l'aide d'informations d'équipement utilisateur dans un modèle d'apprentissage automatique
WO2024092797A1 (fr) * 2022-11-04 2024-05-10 Google Llc Procédé de signalisation entre un réseau et un équipement utilisateur pour une prédiction de faisceau basée sur un livre de codes de faisceau
WO2024168789A1 (fr) * 2023-02-17 2024-08-22 Qualcomm Incorporated Prédiction de paire de faisceaux au niveau d'une entité de réseau à l'aide d'un rapport de matrice basé sur des coordonnées
WO2025150029A1 (fr) * 2024-04-12 2025-07-17 Lenovo (Singapore) Pte. Ltd. Gestion de faisceau pour rapport de groupe de faisceaux par l'intermédiaire de multi-trp
WO2025152037A1 (fr) * 2024-01-16 2025-07-24 Oppo广东移动通信有限公司 Procédé de communication sans fil, dispositif terminal et dispositif réseau
US12468961B2 (en) 2021-11-30 2025-11-11 T-Mobile Usa, Inc. Algorithm selector for profiling application usage based on network signals

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130223251A1 (en) * 2012-02-24 2013-08-29 Samsung Electronics Co., Ltd Beam management for wireless communication

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130223251A1 (en) * 2012-02-24 2013-08-29 Samsung Electronics Co., Ltd Beam management for wireless communication

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
GUO HAO ET AL.: "A comparison of beam refinement algorithms for millimeter wave initial access", 2017 IEEE 28TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR, AND MOBILE RADIO COMMUNICATIONS (PIMRC, 8 October 2017 (2017-10-08), XP033321581 *
KLAUTAU ALDEBARO ET AL.: "5G MIMO Data for Machine Learning: Application to Beam-Selection Using Deep Learning", IEEE 2018 INFORMATION THEORY AND APPLICATIONS WORKSHOP (ITA, 11 February 2018 (2018-02-11), XP055545411 *
SAMSUNG: "Overview on beam management", 3GPP DRAFT; R1-1609080, 10 October 2016 (2016-10-10), Lisbon, Portugal, XP051149131 *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11870530B2 (en) * 2018-09-28 2024-01-09 Nokia Technologies Oy Beam alignment
US20210391911A1 (en) * 2018-09-28 2021-12-16 Nokia Technologies Oy Beam alignment
WO2021107472A1 (fr) 2019-11-29 2021-06-03 Samsung Electronics Co., Ltd. Procédé et équipement utilisateur de réception de signal
EP4018557A4 (fr) * 2019-11-29 2022-10-12 Samsung Electronics Co., Ltd. Procédé et équipement utilisateur de réception de signal
US11563502B2 (en) 2019-11-29 2023-01-24 Samsung Electronics Co., Ltd. Method and user equipment for a signal reception
CN112886996A (zh) * 2019-11-29 2021-06-01 北京三星通信技术研究有限公司 信号接收方法、用户设备、电子设备及计算机存储介质
WO2021211703A1 (fr) * 2020-04-16 2021-10-21 Qualcomm Incorporated Sélection de modèle d'apprentissage automatique dans des communications formées en faisceau
US11424791B2 (en) 2020-04-16 2022-08-23 Qualcomm Incorporated Machine learning model selection in beamformed communications
CN114390580A (zh) * 2020-10-20 2022-04-22 维沃移动通信有限公司 波束上报方法、波束信息确定方法及相关设备
CN114390580B (zh) * 2020-10-20 2024-10-15 维沃移动通信有限公司 波束上报方法、波束信息确定方法及相关设备
WO2022237832A1 (fr) * 2021-05-12 2022-11-17 维沃移动通信有限公司 Procédé et appareil de traitement d'informations, terminal et dispositif côté réseau
US12468961B2 (en) 2021-11-30 2025-11-11 T-Mobile Usa, Inc. Algorithm selector for profiling application usage based on network signals
US11962389B2 (en) 2021-12-20 2024-04-16 Lenovo (Singapore) Pte. Ltd. Artificial intelligence enabled beam management
WO2023119136A1 (fr) * 2021-12-20 2023-06-29 Lenovo (Singapore) Pte. Ltd. Gestion de faisceau activée par intelligence artificielle
US12335018B2 (en) 2021-12-20 2025-06-17 Lenovo (Singapore) Pte. Ltd Artificial intelligence enabled beam management
WO2023123127A1 (fr) * 2021-12-29 2023-07-06 Oppo广东移动通信有限公司 Procédé et appareil d'interaction d'informations de gestion de faisceaux, terminal et support
WO2023197226A1 (fr) * 2022-04-13 2023-10-19 北京小米移动软件有限公司 Procédés de sélection de faisceau d'ondes, et appareils
WO2023197222A1 (fr) * 2022-04-13 2023-10-19 北京小米移动软件有限公司 Procédé et appareil de prédiction de faisceau, dispositif, et support de stockage
CN114938712A (zh) * 2022-04-13 2022-08-23 北京小米移动软件有限公司 波束选择方法和装置
CN114938712B (zh) * 2022-04-13 2024-07-19 北京小米移动软件有限公司 波束选择方法和装置
WO2023211350A1 (fr) * 2022-04-29 2023-11-02 Telefonaktiebolaget Lm Ericsson (Publ) Informations d'assistance d'équipement utilisateur pour de meilleures prédictions de faisceau de réseau
WO2023212890A1 (fr) * 2022-05-06 2023-11-09 Qualcomm Incorporated Techniques de prédiction de caractéristiques de faisceau à l'aide de processus d'apprentissage fédérés
WO2023216020A1 (fr) * 2022-05-07 2023-11-16 Qualcomm Incorporated Gestion prédictive de ressources à l'aide d'informations d'équipement utilisateur dans un modèle d'apprentissage automatique
WO2024092797A1 (fr) * 2022-11-04 2024-05-10 Google Llc Procédé de signalisation entre un réseau et un équipement utilisateur pour une prédiction de faisceau basée sur un livre de codes de faisceau
WO2024168789A1 (fr) * 2023-02-17 2024-08-22 Qualcomm Incorporated Prédiction de paire de faisceaux au niveau d'une entité de réseau à l'aide d'un rapport de matrice basé sur des coordonnées
WO2025152037A1 (fr) * 2024-01-16 2025-07-24 Oppo广东移动通信有限公司 Procédé de communication sans fil, dispositif terminal et dispositif réseau
WO2025150029A1 (fr) * 2024-04-12 2025-07-17 Lenovo (Singapore) Pte. Ltd. Gestion de faisceau pour rapport de groupe de faisceaux par l'intermédiaire de multi-trp

Similar Documents

Publication Publication Date Title
WO2019190368A1 (fr) Procédés, appareil, et programmes informatiques pour activer et exécuter une gestion de faisceau dans un réseau de communication
US11552690B2 (en) Handling beam pairs in a wireless network
RU2732187C1 (ru) Аппаратура, способы, компьютерные программы и компьютерные программные продукты для управления лучом
US12273776B2 (en) Master node, secondary node and user equipment in mobile communication network and communication methods therebetween
US10952236B2 (en) Beam selection systems and methods
US12003309B2 (en) Beam selection priority
EP3103306A1 (fr) Procédés, dispositif sans fil, station de base et station relais candidate pour supporter la communication d2d sur relais
CN113424628B (zh) 蜂窝系统中的多用户协调传输
US10998939B2 (en) Beamformed reception of downlink reference signals
EP3963942B1 (fr) Procédés et appareils de mesure de faisceau
US20210306946A1 (en) Secondary network node selection for dual connectivity
US11202220B2 (en) Method of adapting report mapping based on beamforming
US11399325B2 (en) High-gain beam handover
US11075684B2 (en) Method and apparatus for estimating channel quality
US20200413315A1 (en) Handover control
WO2024151190A1 (fr) Nœud de réseau radio et procédé mis en œuvre dans celui-ci
WO2023211353A1 (fr) Rapport d'informations de prédiction de faisceau de domaine spatial dans le cadre d'un rétablissement sur défaillance de faisceau
US20240057009A1 (en) Inter-network node delay driven harq feedback offset design for inter-network node carrier aggregation
WO2025119442A1 (fr) Découverte d'ondes millimétriques (mmwave) dans une bande de fréquences en dessous de 7 gigahertz
WO2024175951A1 (fr) Adaptation de périodicité de suivi de faisceau
WO2024128964A1 (fr) Sélection de faisceau de détection pour scénarios de véhicule
WO2021180765A1 (fr) Gestion de dispositifs sans fil incompatibles

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18912211

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18912211

Country of ref document: EP

Kind code of ref document: A1