Abstract: This document describes techniques and apparatuses for optimizing a cellular network using machine learning. A network-optimization controller determines a performance metric to optimize for a cellular network. The network-optimization controller determines at least one network-configuration parameter that affects the performance metric. The network-optimization controller sends a gradient-request message to multiple base stations that directs multiple wireless transceivers to respectively evaluate gradients of the performance metric relative to the at least one network-configuration parameter. The network-optimization controller receives, from the multiple base stations, gradient-report messages generated by the multiple wireless transceivers, the gradient-report messages respectively including the gradients. The network-optimization controller analyzes the gradients using machine learning to determine at least one optimized network-configuration parameter.

Abstract: Wireless networks may have thousands of configurable parameters, so manual tuning is infeasible. A self-organizing network (SON) can provide automation. However, automated algorithms are not designed to interact with a wireless network, and network experimentation can jeopardize reliability. To address the former, a SON facilitator of a wireless network management node exposes an API that can translate network configuration information for consumption by a SON enhancer, which may implement an AI algorithm for network tuning. The SON facilitator can also transform output from the SON enhancer into directions for controlling a test scenario, including generating a DL SON message describing the test to a UE. To further increase reliability during the test scenario, the UE can be provisioned with two wireless connections. A first connection is unchanged by the test scenario for stability, and a second connection is used for testing.

Abstract: This document describes techniques and devices for determining a machine-learning architecture for network slicing. A user equipment (UE) executes a first application associated with a first requested quality-of-service level. The UE selects a first machine-learning architecture based on the first requested quality-of-service level. The UE transmits, to a network-slice manager of a wireless network, a first machine-learning architecture request message to request permission to use the first machine-learning architecture. The UE receives, from the network-slice manager, a first machine-learning architecture response message that grants permission to use the first machine-learning architecture based on a first network slice. The UE wirelessly communicates data for the first application using the first machine-learning architecture, the first machine-learning architecture being configured to compute an output based on an input using coefficients determined by the user equipment.

Abstract: This document describes techniques and devices for determining a machine-learning architecture. A user equipment (UE) transmits, to a network-slice manager of a wireless network, a first machine-learning architecture request message to request permission to use a first machine-learning architecture.

Abstract: This document describes techniques and apparatuses for a user equipment (UE)-coordination set for a wireless network. In aspects, a base station specifies a set of UEs to form a UE-coordination set for joint transmission and reception of data intended for a target UE within the UE-coordination set. The base station selects one of the UEs within the UE-coordination set to act as a coordinating UE for the UE-coordination set and transmits a request message that directs the coordinating UE to coordinate the joint transmission and reception of the data intended for the target UE. Then, the base station transmits a downlink signal to each UE within the UE-coordination set. Each UE within the UE-coordination set demodulates and samples the downlink signal and then forwards the samples to the coordinating UE, which combines the samples and processes the combined samples to provide decoded data.

Abstract: Techniques and apparatuses are described for hybrid wireless communications processing chains that include deep neural networks (DNNs) and static algorithm modules. In aspects, a first wireless communication device communicates with a second wireless device using a hybrid transmitter processing chain. The first wireless communication device selects a machine-learning configuration (ML configuration) that forms a modulation deep neural network (DNN) that generates a modulated signal using encoded bits as an input. The first wireless communication device forms, based on the modulation ML configuration, the modulation DNN as part of a hybrid transmitter processing chain that includes the modulation DNN and at least one static algorithm module. In response to forming the modulation DNN, the first wireless communication devices processes wireless communications associated with the second wireless communication device using the hybrid transmitter processing chain.

Abstract: This document describes techniques and apparatuses for joint-transmission over an unlicensed frequency band using a user equipment (UE)-coordination set. In aspects, a first UE in a UE-coordination set acts as a coordinating UE. The coordinating UE receives, using a local wireless network connection, uplink data from a second UE in the UE-coordination set. The coordinating UE distributes, using the local wireless network connection, the uplink data to at least a third UE in the UE-coordination set. The coordinating UE receives, from at least one UE in the UE-coordination set, respective results of a clear channel assessment of the unlicensed frequency band. The coordinating UE determines a specified time to begin joint-transmission of the uplink data based on the results and coordinates the joint-transmission by directing the at least one UE to initiate the joint-transmission of the uplink data based on the specified time.

Abstract: This document describes aspects of multiple active-coordination-set (ACS) aggregation for mobility management. A master base station coordinates aggregation of control-plane and user-plane communications, generated by a first active-coordination-set for a first joint communication between the first ACS and a user equipment, where the first ACS includes the master base station and at least a second base station. The master base station receives, from a second master base station of a second ACS, control-plane information or user-plane data associated with a second joint communication between the second ACS and the UE, the second ACS including the second master base station and at least a third base station. The master base station aggregates the control-plane and user-plane communications with at least a portion of the control-plane information or the user-plane data to coordinate data throughput to the user equipment.

Abstract: A wireless system employs neural networks to provide for CSI estimate feedback between a transmitting device and a receiving device. A managing component selects neural network architecture configurations for implementation at the transmitting and receiving devices based on capability information. The receiving device determines CSI estimate(s) from CSI pilot signaling from the transmitting device. The CSI estimate(s) are processed by the neural network(s) at the receiving device to generate a CSF output, which can represent, for example, one or more predicted future CSI estimates and which is wirelessly transmitted to the transmitting device. The one or more neural networks at the transmitting device then process the received CSF output along to generate one or more recovered predicted future CSI estimates, which are then used to control one or more MIMO processes at the transmitting device.

Abstract: Techniques and apparatuses are described for enabling dual connectivity with secondary cell-user equipment. In some aspects, a base station (121) serving as a primary cell forms a base station-user equipment dual connectivity (BUDC) group (410) by configuring a user equipment (UE, 111) as a secondary cell-user equipment (SC-UE, 420) to provide a secondary cell. The base station (121) or SC-UE (420) can then add other UEs (112, 113, 114) to the BUDC group (410) thereby enabling dual connectivity for the UEs through the primary cell or secondary cell provided by the SC-UE (420). In some cases, the SC-UE (420) schedules resources of an air interface (302) by which the other UEs to communicate with the SC-UE (420). By so doing, the SC-UE (420) can communicate data with the other UEs (112, 113, 114) of the BUDC group (410) without communicating through a base station (121, 122), which decreases latency of communications between the UEs (111-114) of the BUDC group (410).

Abstract: Techniques and apparatuses are described for enabling base station-user equipment messaging regarding deep neural networks. A network entity (base station 121, core network server 320) determines a neural network formation configuration (architecture and/or parameter configurations 1208) for a deep neural network (deep neural network(s) 604, 608, 612, 616) for processing communications transmitted over the wireless communication system. The network entity (base station 121, core network server 302) communicates the neural network formation configuration to a user equipment (UE 110). The user equipment (UE 110) configures a first neural network (deep neural network(s) 608, 612) based on the neural network formation configuration. In implementations, the user equipment (UE 110) recovers information communicated over the wireless network using the first neural network (deep neural network(s) 608, 612).

Abstract: This document describes techniques and apparatuses for optimizing a cellular network using machine learning. In particular, a network-optimization controller uses machine learning to determine an optimized network-configuration parameter that affects a performance metric of the cellular network. To make this determination, the network-optimization controller requests and analyzes gradients determined by one or more user equipments, one or more base stations, or combinations thereof. By using machine learning, the network-optimization controller identifies different optimized network-configuration parameters associated with different local optima or global optima of an optimization function, and selects a particular optimized network-configuration parameter that is appropriate for a given environment. In this manner, the network-optimization controller dynamically optimizes the cellular network to account for both short-term and long-term environmental changes.

Abstract: Techniques and apparatuses are described for deep neural network (DNN) processing for a user equipment-coordination set (UECS). A network entity selects (910) an end-to-end (E2E) machine-learning (ML) configuration that forms an E2E DNN for processing UECS communications. The network entity directs (915) each device of multiple devices participating in an UECS to form, using at least a portion of the E2E ML configuration, a respective sub-DNN of the E2E DNN that transfers the UECS communications through the E2E communication, where the multiple devices include at least one base station, a coordinating user equipment (UE), and at least one additional UE. The network entity receives (940) feedback associated with the UECS communications and identifies (945) an adjustment to the E2E ML configuration. The network entity then directs at least some of the multiple devices participating in an UECS to update the respective sub-DNN of the E2E DNN based on the adjustment.

Abstract: Techniques and apparatuses are described for enabling a base station to enable peer-to-peer communication among multiple user equipment (UE) over a mmWave link. The techniques described herein overcome challenges that the multiple UEs might otherwise face in trying to establish peer-to-peer links on their own. By relying on the base station to grant air interface resources for the UE to perform peer-to-peer communications with the UE, the UE can communicate directly with the other UE, independent of links that the UE or the other UE maintains with the base station. Furthermore, reliance on the base station may help the UE and the other UE mitigate interference from other nearby mmWave links that are separate from the peer-to-peer wave link. In addition, by relying on the base station to specify the beam sweeping pattern, beam acquisition by the UE and the other UE may be improved.

Abstract: Methods, devices, systems, and means for intra-UECS communication by a coordinating user equipment, UE, in a user equipment-coordination set, UECS, are described herein. The coordinating UE allocates first air interface resources to a second UE and second air interface resources to a third UE for intra-UECS communication. The coordinating UE receives, using the allocated first air interface resources, an Internet Protocol, IP, data packet from the second UE in the UECS. The coordinating UE determines that a destination address included in the IP data packet is an address of the third UE and transmits, using the allocated second air interface resources, the IP data packet to the third UE.

Abstract: This document describes techniques and devices for determining a machine-learning architecture for network slicing. A user equipment (UE) and a network-slice manager communicate with each other to determine a machine-learning (ML) architecture, which the UE then employs to wirelessly communicate data for an application. In particular, the UE selects a machine-learning architecture that provides a quality-of-service level requested by an application. The network-slice manager accepts or rejects the request based on one or more available end-to-end machine-learning architectures associated with a network slice that supports the quality-of-service level requested by the application. By working together, the UE and the network-slice manager can determine an appropriate machine-learning architecture that satisfies a quality-of-service level associated with the application and forms a portion of an end-to-end machine-learning architecture that meets the quality-of-service requested by the application.

Abstract: Techniques and apparatuses are described that implement cooperative bistatic radar sensing using deep neural networks. In particular, a base station (120) operates as a transmitter of the bistatic radar, and the user equipment (110) operates as a receiver of the bistatic radar. During radar sensing, the base station (120) and the user equipment (110) use their respective deep neural networks (460 and 420) for signal generation and signal processing. The deep neural networks (460 and 420) also enable the base station (120) and the user equipment (110) to utilize the same hardware for both radar sensing and wireless communication. With cooperative bistatic radar sensing, the base station (120) and the user equipment (110) can compile explicit information about objects within an operating environment and use this information to improve wireless communication performance.

Abstract: Techniques and apparatuses are described that implement control signaling for monostatic radar sensing. In particular, a base station uses control signaling to configure a user equipment for monostatic radar sensing and control when monostatic radar sensing is performed by the user equipment. With control signaling, the base station can enable monostatic radar sensing to occur using similar frequency resources used for wireless communication, which enables efficient use of a frequency spectrum. The base station can also use control signaling to reduce interference observed by other user equipment as the user equipment performs monostatic radar sensing. By performing monostatic radar sensing, the user equipment compiles explicit information about objects within an operating environment and shares this information with the base station. The base station uses this information to improve wireless communication performance.

Abstract: Techniques described herein describe aspects of signal adjustments in user equipment-coordination set, UECS, joint transmissions. A base station analyzes a first joint transmission from multiple user equipments, UEs, participating in a UECS, where the multiple UEs include a coordinating UE of the UECS and at least one non-coordinating UE participating in the UECS. The base station determines that the first joint transmission fails to meet a performance metric and directs the multiple UEs participating in the UECS to add signal adjustments to a second joint transmission.

Abstract: Techniques and apparatuses are described for deep neural network (DNN) processing for a user equipment-coordination set (UECS). A network entity selects (910) an end-to-end (E2E) machine-learning (ML) configuration that forms an E2E DNN for processing UECS communications. The network entity directs (915) each device of multiple devices participating in an UECS to form, using at least a portion of the E2E ML configuration, a respective sub-DNN of the E2E DNN that transfers the UECS communications through the E2E communication, where the multiple devices include at least one base station, a coordinating user equipment (UE), and at least one additional UE. The network entity receives (940) feedback associated with the UECS communications and identifies (945) an adjustment to the E2E ML configuration. The network entity then directs at least some of the multiple devices participating in an UECS to update the respective sub-DNN of the E2E DNN based on the adjustment.