阅读说明：本技术 用于动态波束对确定的方法和设备 (Method and apparatus for dynamic beam pair determination ) 是由 朱隽 R·N·查拉 A·图布尔 J·李 于 2018-12-13 设计创作，主要内容包括：在基站与具有毫米波(mmW)能力的UE之间的许多可用波束对之中选择发射(Tx)-接收(Rx)波束对同该基站与该UE之间的传输性能直接相关。公开了一种在能够进行(mmW)通信的传送方用户装备(UE)处的使用人工神经网络来确定新的服务Tx-Rx波束对的方法、设备和计算机可读介质。UE可使用人工神经网络来预测良好Tx-Rx波束对集合,其中该人工神经网络包括输入层、中间层和输出层。然后,UE可基于该良好Tx-Rx波束对集合来确定新的服务Tx-Rx波束对。(Selecting a transmit (Tx) -receive (Rx) beam pair among a number of available beam pairs between a base station and a millimeter wave (mmW) capable UE is directly related to the transmission performance between the base station and the UE. A method, apparatus, and computer-readable medium for determining a new serving Tx-Rx beam pair using an artificial neural network at a transmitting User Equipment (UE) capable of (mmW) communication are disclosed. The UE may predict a good set of Tx-Rx beam pairs using an artificial neural network, wherein the artificial neural network includes an input layer, an intermediate layer, and an output layer. The UE may then determine a new serving Tx-Rx beam pair based on the set of good Tx-Rx beam pairs.)

1. A method of wireless communication by a User Equipment (UE), comprising:

determining a new serving Tx-Rx beam pair among the plurality of Tx-Rx beam pairs based at least in part on the set of predicted good transmit (Tx) -receive (Rx) beam pairs using an artificial neural network; and

switching to the new serving Tx-Rx beam pair.

2. The method of claim 1, further comprising at least one of:

receiving a set of Tx beams from a serving base station, wherein each Tx beam is paired with each Rx beam available at the UE to form the plurality of Tx-Rx beam pairs; or

Prior to determining the new serving Tx-Rx beam pair, training the artificial neural network with a historical first set of input data, wherein the artificial neural network comprises an input layer, an intermediate layer, and an output layer; or

Combinations thereof.

3. The method of claim 2, wherein the input layer of the artificial neural network is configured to: receiving as first input data at least a set of UE rotation angles, a set of UE angular velocities, a set of UE movement directions, a set of UE movement velocities, an angle of departure (AoD), an angle of arrival (AoA), historical beam pair strengths, corresponding indices for each of the plurality of Tx-Rx beam pairs, or a combination thereof.

4. The method of claim 3, wherein the input layer is further configured to: the method may include receiving the first input data from one or more sensors of the UE, and processing the first input data by screening, classifying, generalizing, or a combination thereof the first input data.

5. The method of claim 4, wherein the middle layer of the artificial neural network is configured to: the processed first input data is received as second input data.

6. The method of claim 5, wherein the middle layer of the artificial neural network is further configured to: making a UE rotation prediction, a UE movement prediction, and a determination as to whether a Tx-Rx beam pair has a line of sight (LoS) or a non-LoS (NLoS) between the Tx-Rx beam pair, or a combination thereof, based at least in part on the second input data.

7. The method of claim 6, wherein the intermediate layer of the artificial neural network is further configured to: when the intermediate layer of the artificial neural network determines that there is NLoS between the Tx-Rx beam pair, determining reflector information, the reflector information comprising a predicted movement speed, size, and position of a reflector.

8. The method of claim 7, wherein the output layer of the artificial neural network is configured to: receiving, as third input data, the UE rotation prediction, the UE movement prediction, a determination as to whether the Tx-Rx beam pair has line of sight (LoS) or non-LoS (NLoS), the reflector information, or a combination thereof.

9. The method of claim 8, wherein the output layer is further configured to: predicting the set of good Tx-Rx beam pairs and when the set of good Tx-Rx beam pairs will take effect based at least in part on the third input data, and wherein the set of good Tx-Rx beam pairs meets a predetermined beam strength threshold or is better than the remaining beam pairs of the plurality of Tx-Rx beam pairs.

10. The method of claim 9, wherein the output layer is further configured to: predicting, based on the third input data, a set of bad Tx-Rx beam pairs and when the predicted set of bad Tx-Rx beam pairs will take effect, and wherein the set of bad Tx-Rx beam pairs crosses a predetermined beam strength threshold or is worse than the remaining beam pairs of the plurality of Tx-Rx beam pairs.

11. The method of claim 10, wherein determining the new serving Tx-Rx beam pair further comprises:

blacklisting the set of predicted bad beam pairs to reduce a size of the set of good Tx-Rx beam pairs; and

determining the new serving Tx-Rx beam pair based on a smaller set of good Tx-Rx beam pairs.

12. The method of claim 1, in which the artificial neural network is one of a feedforward artificial neural network, a feedback artificial neural network, or a combination thereof.

13. An apparatus for wireless communication at a User Equipment (UE), comprising:

means for determining a new serving Tx-Rx beam pair among a plurality of Tx-Rx beam pairs based at least in part on the set of predicted good transmit (Tx) -receive (Rx) beam pairs using an artificial neural network; and

means for switching to the new serving Tx-Rx beam pair.

14. The apparatus of claim 13, further comprising at least one of:

means for receiving a set of Tx beams from a serving base station, wherein each Tx beam is paired with each Rx beam available at the UE to form the plurality of Tx-Rx beam pairs; or

Means for training the artificial neural network with a historical first set of input data prior to determining the new serving Tx-Rx beam pair, wherein the artificial neural network comprises an input layer, an intermediate layer, and an output layer; or

Combinations thereof.

15. The device of claim 14, wherein the input layer of the artificial neural network is configured to: receiving as first input data at least a set of UE rotation angles, a set of UE angular velocities, a set of UE movement directions, a set of UE movement velocities, an angle of departure (AoD), an angle of arrival (AoA), historical beam pair strengths, corresponding indices for each of the plurality of Tx-Rx beam pairs, or a combination thereof.

16. The device of claim 14, wherein the input layer is further configured to: the method may include receiving the first input data from one or more sensors of the UE, and processing the first input data by screening, classifying, generalizing, or a combination thereof the first input data.

17. The device of claim 16, wherein the middle layer of the artificial neural network is configured to: the processed first input data is received as second input data.

18. The device of claim 17, wherein the middle layer of the artificial neural network is further configured to: making a UE rotation prediction, a UE movement prediction, and a determination as to whether a Tx-Rx beam pair has a line of sight (LoS) or a non-LoS (NLoS) between the Tx-Rx beam pair, or a combination thereof, based at least in part on the second input data.

19. The device of claim 18, wherein the middle layer of the artificial neural network is further configured to: when the intermediate layer of the artificial neural network determines that there is NLoS between the Tx-Rx beam pair, determining reflector information, the reflector information comprising a predicted movement speed, size, and position of a reflector.

20. The device of claim 19, wherein the output layer of the artificial neural network is configured to: receiving, as third input data, the UE rotation prediction, the UE movement prediction, a determination as to whether the Tx-Rx beam pair has line of sight (LoS) or non-LoS (NLoS), the reflector information, or a combination thereof.

21. The device of claim 20, wherein the output layer is further configured to: predicting the set of good Tx-Rx beam pairs and when the set of good Tx-Rx beam pairs will take effect based at least in part on the third input data, and wherein the set of good Tx-Rx beam pairs meets a predetermined beam strength threshold or is better than the remaining beam pairs of the plurality of Tx-Rx beam pairs.

22. The device of claim 21, wherein the output layer is further configured to: predicting, based on the third input data, a set of bad Tx-Rx beam pairs and when the predicted set of bad Tx-Rx beam pairs will take effect, and wherein the set of bad Tx-Rx beam pairs crosses a predetermined beam strength threshold or is worse than the remaining beam pairs of the plurality of Tx-Rx beam pairs.

23. The apparatus of claim 22, wherein the means for determining the new serving Tx-Rx beam pair further comprises:

blacklisting the set of predicted bad beam pairs to reduce a size of the set of good Tx-Rx beam pairs; and

determining the new serving Tx-Rx beam pair based on a smaller set of good Tx-Rx beam pairs.

24. An apparatus for wireless communication, comprising:

a transceiver;

a memory; and

at least one processor coupled to at least one of the memories and configured to:

determining a new serving Tx-Rx beam pair among the plurality of Tx-Rx beam pairs based at least in part on the set of predicted good transmit (Tx) -receive (Rx) beam pairs using an artificial neural network; and

switching to the new serving Tx-Rx beam pair.

25. The device of claim 24, wherein the at least one processor is further configured to perform at least one of:

means for receiving a set of Tx beams from a serving base station, wherein each Tx beam is paired with each Rx beam available at the User Equipment (UE) to form the plurality of Tx-Rx beam pairs, wherein the apparatus comprises the UE; or

Means for training the artificial neural network with a historical first set of input data prior to determining the new serving Tx-Rx beam pair, wherein the artificial neural network comprises an input layer, an intermediate layer, and an output layer; or

Combinations thereof.

26. The device of claim 25, wherein the input layer of the artificial neural network is configured to:

receiving as first input data at least a set of UE rotation angles, a set of UE angular velocities, a set of UE movement directions, a set of UE movement velocities, an angle of departure (AoD), an angle of arrival (AoA), historical beam pair strengths, corresponding indices for each of the plurality of Tx-Rx beam pairs, or a combination thereof.

27. The device of claim 26, wherein the input layer is further configured to: the method may include receiving the first input data from one or more sensors of the UE, and processing the first input data by screening, classifying, generalizing, or a combination thereof the first input data.

28. The device of claim 27, wherein the middle layer of the artificial neural network is further configured to: making a UE rotation prediction, a UE movement prediction, and a determination as to whether a Tx-Rx beam pair has a line of sight (LoS) or a non-LoS (NLoS) between the Tx-Rx beam pair, or a combination thereof, based at least in part on the processed input data.

29. The device of claim 28, wherein the middle layer of the artificial neural network is further configured to: when the intermediate layer of the artificial neural network determines that there is NLoS between the Tx-Rx beam pair, determining reflector information, the reflector information comprising a predicted movement speed, size, and position of a reflector.

30. The device of claim 29, wherein the output layer is configured to:

predict the set of good Tx-Rx beam pairs and when the set of good Tx-Rx beam pairs will take effect based at least in part on the UE rotation prediction, the UE movement prediction, the determination of whether a Tx-Rx beam pair has line of sight (LoS) or non-LoS (NLoS) between the Tx-Rx beam pair, reflector information, or a combination thereof; and

predict a set of bad Tx-Rx beam pairs and when the predicted set of bad Tx-Rx beam pairs will take effect based at least in part on the UE rotation prediction, the UE movement prediction, the determination of whether a Tx-Rx beam pair has a line of sight (LoS) or a non-LoS (NLoS) between the Tx-Rx beam pair, reflector information, or a combination thereof.

Technical Field

The present disclosure relates generally to wireless communication systems, and more particularly, to methods and apparatus for dynamic beam pair selection.

Background

Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple-access techniques capable of supporting communication with multiple users by sharing the available system resources. Examples of such multiple-access techniques include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

These multiple access techniques have been adopted in various telecommunications standards to provide a common protocol that enables different wireless devices to communicate on a city, country, region, and even global level. An example telecommunication standard is the 5G New Radio (NR). The 5G NR is part of a continuous mobile broadband evolution promulgated by the third generation partnership project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the internet of things (IoT)), and other requirements. Some aspects of the 5GNR may be based on the 4G Long Term Evolution (LTE) standard. There is a need for further improvements in the 5G NR technology. These improvements are also applicable to other multiple access techniques and telecommunications standards employing these techniques.

NR may support various wireless communication services, such as enhanced mobile broadband (eMBB) targeting wide bandwidths (e.g., over 80MHz), millimeter wave (mmW) targeting high carrier frequencies (e.g., 60GHz), massive MTC (MTC) targeting non-backward compatible MTC technologies, and/or mission critical targeting ultra-reliable low latency communication (URLLC). These services may include latency and reliability requirements. These services may also have different Transmission Time Intervals (TTIs) to meet corresponding quality of service (QoS) requirements. In addition, these services may coexist in the same subframe.

The wireless communication system may also include or support a network, also referred to as a vehicle networking (V2X), vehicle-to-vehicle (V2V) network, and/or cellular V2X (C-V2X) network, used for vehicle-based communication. Vehicle-based communication networks may provide always-on telematics, where UEs (e.g., vehicular UEs (V-UEs)) communicate directly with the network (V2N), with pedestrian UEs (V2P), with infrastructure equipment (V2I), and with other V-UEs (e.g., via the network). Vehicle-based communication networks may support a safe, always-on driving experience by providing intelligent connectivity in which traffic signals/timing, real-time traffic and route planning, safety alerts to pedestrians/riders, collision avoidance information, and the like are exchanged.

However, such networks that support vehicle-based communications may also be associated with various requirements (e.g., communication requirements, security and privacy requirements, etc.). Other example requirements may include, but are not limited to, reduced latency requirements, higher reliability requirements, and the like. For example, vehicle-based communication may include communicating sensor data that may support an autonomous automobile. Sensor data may be used between vehicles to improve the safety of an autonomous vehicle.

SUMMARY

The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

Selecting a transmit (Tx) -receive (Rx) beam pair among a number of available beam pairs between a base station and a mmW capable UE is directly related to the transmission performance between the base station and the UE. A currently popular approach to selecting active Tx-Rx beam pairs is to measure each beam pair from a plurality of available beam pairs in a round-robin fashion and determine a new serving beam pair based on the measurement results. In this cyclic manner, each beam pair has equal opportunity to be measured in the synchronization cycle. In fact, the probability of each beam pair being selected as a serving beam pair is different due to factors such as line of sight (LoS) and proximity between beam pairs. This round-robin approach does not distinguish between these beam pairs and thus may result in a longer latency in selecting a serving beam pair.

Thus, for methods, apparatus, and computer-readable media at a User Equipment (UE) in a mmW communication environment, there is a need to randomly assign an opportunity to each wave velocity pair taking into account factors such as LoS, proximity, etc., to quickly converge on one good service beam pair using an artificial neural network. The UE may predict a good set of Tx-Rx beam pairs using an artificial neural network. The artificial neural network may include an input layer, an intermediate layer, and an output layer. The UE may then determine a new serving Tx-Rx beam pair based on the set of good Tx-Rx beam pairs.

To the accomplishment of the foregoing and related ends, the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed and the present description is intended to include all such aspects and their equivalents.