Inter-spatial cell interference-aware downlink coordination

Abstract

A method of wireless communication by a first network device includes predicting spatial inter-cell downlink interference experienced by a UE, the method also including communicating with a second network device to reduce spatial inter-cell downlink interference in a direction of the UE by protecting resources across a selected resource set.

Description

Claim of Priority

[0001] Cross - Reference to Related Applications

[0001] This application claims the benefit of priority of U.S. Patent Application No. 17 / 675,980, filed on February 18, 2022, entitled "SPATIAL INTER - CELL INTERFERENCE AWARE DOWNLINK COORDINATION", which claims the benefit of U.S. Provisional Patent Application No. 63 / 155,635, filed on March 2, 2021, entitled "SPATIAL INTER - CELL INTERFERENCE AWARE DOWNLINK COORDINATION", the entire disclosures of which are hereby incorporated by reference.

Technical Field

[0002]

[0002] Aspects of the present disclosure generally relate to wireless communication, and more particularly, to techniques and apparatus for the extension of spatial inter - cell interference aware downlink coordination.

Background Art

[0003]

[0003] Wireless communication systems are widely deployed to provide a variety of telecommunications services, including telephone, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies that enable communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies 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, time division synchronous code division multiple access (TD-SCDMA) systems, and Long-Term Evolution (LTE®). LTE / LTE Advanced is a set of extensions to the Universal Mobile Telecommunications System (UMTS) mobile standard published by the Third Generation Partnership Project (3GPP®).

[0004]

[0004] A wireless communication network may include several base stations (BS) that can support communication for several user devices (UEs). User devices (UEs) may communicate with base stations (BS) via downlink and uplink. Downlink (or forward link) refers to the communication link from the BS to the UE, and uplink (or reverse link) refers to the communication link from the UE to the BS. As will be described in more detail, BS may be called node B, gNB, access point (AP), radiohead, transmit / receive point (TRP), new radio (NR) BS, 5G node B, etc.

[0005]

[0005] The above-mentioned multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables different user devices to communicate at urban, national, regional, and even global levels. New Radio (NR), sometimes called 5G, is a set of extensions to the LTE mobile standard published by the Third Generation Partnership Project (3GPP). NR is designed to better support mobile broadband internet access by improving spectral efficiency, lowering costs, improving service, utilizing new spectra, and better integrating with other open standards by using orthogonal frequency division multiplexing (OFDM) with cyclic prefixes (CP) (CP-OFDM) on the downlink (DL) and CP-OFDM and / or SC-FDM (also known as, for example, discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink (UL), as well as by supporting beamforming, multiple input multiple output (MIMO) antenna technology, and carrier aggregation.

[0006]

[0006] An artificial neural network may comprise an interconnected group of artificial neurons (e.g., neuron models). An artificial neural network may be represented as a computational device or as a method to be performed by a computational device. Convolutional neural networks, such as deep convolutional neural networks, are a type of feedforward artificial neural network. A convolutional neural network may include layers of neurons that can be configured in a tiled receptive field. It would be desirable to apply neural network processing to wireless communications to achieve higher efficiency. [Overview of the Initiative]

[0007]

[0007] A method of wireless communication by a first network device includes predicting inter-cell downlink interference that the UE will experience. The method also includes communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0008]

[0008] An apparatus for wireless communication by a first network device is described. The apparatus includes means for predicting inter-cell downlink interference that the UE will experience. The apparatus also includes means for communicating with a second network device in order to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0009]

[0009] The first network device includes a processor and memory coupled to the processor. The first network device also includes instructions stored in the memory. When instructions are executed by the processor, the first network device is capable of operating to predict inter-cell downlink interference that the UE will experience. The first network device is also capable of communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0010]

[0010] A non-temporary computer-readable medium containing program code is executed by the processor of the first network device. The non-temporary computer-readable medium includes program code for predicting inter-cell downlink interference that the UE will experience. The non-temporary computer-readable medium also includes program code for communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0011]

[0011] The embodiments will be described in general substantially with reference to the accompanying drawings and specification, and will include methods, apparatus, systems, computer program products, non-temporary computer-readable media, user equipment, base stations, wireless communication devices, and processing systems, as shown in the accompanying drawings and specification.

[0012]

[0012] The above outlines fairly broadly the features and technical advantages of the examples provided in this disclosure so that embodiments for carrying out the following inventions may be better understood. Additional features and advantages will be described. The concepts and examples disclosed may readily be used as a basis for modifying or designing other structures to accomplish the same objectives of this disclosure. Such equivalent configurations will not depart from the scope of the appended claims. The characteristics of the concepts disclosed, both their organization and method of operation, along with the relevant advantages, will be better understood by considering the following description in relation to the appended figures. Each of the figures is provided for illustrative and explanatory purposes and is not provided as a definition of the limitation of the claims.

[0013]

[0013] A specific description can be obtained by referring to embodiments partially shown in the accompanying drawings, so that the features of this disclosure may be understood in detail. However, it should be noted that the accompanying drawings should not be considered to show only some embodiments of this disclosure and therefore limit the scope of this disclosure, as such descriptions may lead to other equally valid embodiments. The same reference numerals in different drawings may identify the same or similar elements. [Brief explanation of the drawing]

[0014] [Figure 1]

[0014] A block diagram conceptually illustrating an example of a wireless communication network according to various aspects of the present disclosure. [Figure 2]

[0015] A block diagram conceptually illustrating an example of a base station communicating with a user device (UE) in a wireless communication network, according to various aspects of this disclosure. [Figure 3]

[0016] A diagram illustrating exemplary implementations of designing a neural network using a system-on-a-chip (SOC) including a general-purpose processor, according to several aspects of this disclosure. [Figure 4A]

[0017] A diagram illustrating a neural network according to the aspects of this disclosure. [Figure 4B] A diagram illustrating a neural network according to the aspects of this disclosure. [Figure 4C] A diagram illustrating a neural network according to the aspects of this disclosure. [Figure 4D]

[0018] A diagram illustrating an exemplary deep convolutional network (DCN) according to an aspect of this disclosure. [Figure 5]

[0019] A block diagram illustrating an exemplary deep convolutional network (DCN) according to an aspect of this disclosure. [Figure 6A]

[0020] A diagram illustrating a communication network in which spatial interference experienced by user equipment is based on the downlink transmit beam from a neighbor base station to a neighbor user equipment (UE), according to the aspects of this disclosure. [Figure 6B] A diagram illustrating a communication network in which spatial interference experienced by user equipment is based on the downlink transmit beam from a neighbor base station to a neighbor user equipment (UE), according to the aspects of this disclosure. [Figure 7]

[0021] A diagram of a communication network showing the measurement of the signal intensity of the downlink transmit beam from a neighbor base station to enable inter-spatial cell interference-aware downlink coordination according to an aspect of the present disclosure. [Figure 8]

[0022] A block diagram of a network including a neural processing engine configured to enable inter-spatial cell interference-aware downlink coordination according to an aspect of the present disclosure. [Figure 9]

[0023] A timing diagram illustrating, for example, an exemplary process implemented by a network for inter-spatial-cell interference-aware downlink coordination in a serving cell, according to various aspects of this disclosure. [Figure 10]

[0024] A timing diagram showing an exemplary process, such as implemented by a network, for inter - spatial - cell interference - aware downlink coordination in a neighbor cell according to various aspects of the present disclosure. [Figure 11]

[0025] A timing diagram showing an exemplary process, such as implemented by a device, for inter - spatial - cell interference - aware downlink coordination at a central node according to various aspects of the present disclosure. [Figure 12]

[0026] A flowchart showing an exemplary process, such as implemented by a network device, for inter - spatial - cell interference - aware downlink coordination according to various aspects of the present disclosure.

Mode for Carrying Out the Invention

[0015]

[0027] Various aspects of the present disclosure are described more fully hereinafter with reference to the accompanying drawings. However, the present disclosure may be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout the present disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Based on these teachings, it should be understood by those skilled in the art that the scope of the present disclosure covers any aspect of the present disclosure, whether implemented independently of other aspects of the present disclosure or combined with other aspects of the present disclosure. For example, an apparatus may be implemented or a method may be carried out using any number of the described aspects. Further, the scope of the present disclosure is intended to cover such apparatus or methods implemented using other structures, functions, or structures and functions in addition to or other than the various aspects of the present disclosure described. It should be understood that any aspect of the disclosed present disclosure may be implemented by one or more elements of the claims.

[0016]

[0028] Next, several embodiments of telecommunications systems are presented with reference to various devices and techniques. These devices and techniques are described in embodiments for carrying out the following inventions and are shown in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as “elements”). These elements may be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0017]

[0029] While the embodiments may be described using terminology generally associated with 5G and beyond wireless technologies, it should be noted that the embodiments of this disclosure may apply to other generation-based communication systems, including 3G and / or 4G technologies, as well as other generation-based communication systems, including 3G and / or 4G technologies.

[0018]

[0030] Inter-cell interference can degrade the signal for the user (e.g., signal-to-interference plus noise ratio (SINR)). This signal degradation can be particularly significant when the user is at the cell edge. Furthermore, with the introduction of large-scale multi-input multiple-output (MIMO) antennas in next-generation node B (gNB), this inter-cell interference can lead to significant SINR degradation for the user. For example, a narrow downlink transmit beam can be highly directional and highly variable over time, resulting in SINR degradation. Highly directional interference, especially at the cell edge, can reduce data rates and negatively impact the user experience. Moreover, the high variability of interference makes it more difficult to implement link adaptation, such as predicting supported modulation and coding schemes (MCS). This can be challenging for latency-sensitive applications with limited delay budgets.

[0019]

[0031] In some aspects of this disclosure, a neural network is trained to infer the impact of a neighbor base station's (e.g., gNB) potential transmit beam on a potential victim user device (UE). In these aspects of this disclosure, the neural network is trained over time using UE Channel State Information (CSI) Reference Signal (CSI-RS) measurement reports, beam information, and UE location. In other aspects of this disclosure, a database stores information about the impact of a neighbor base station's (e.g., gNB) potential transmit beam on a potential victim UE. In these aspects of this disclosure, the database stores UE Channel State Information (CSI) Reference Signal (CSI-RS) measurement reports, beam information, and UE location to enable database lookups to determine the potential impact from the neighbor base station on a potential victim UE.

[0020]

[0032] Once a neural network is trained to infer the effect of a neighbor base station's transmit beam on a victim UE, a network device (e.g., a gNB) will coordinate with the neighbor base station. In these aspects of the disclosure, network device coordination may prevent the neighbor base station from communicating its downlink transmit beam during the time / frequency resources used to service the victim UE. For example, a first user device (UE1) may experience significant interference from a neighbor base station's (gNB2) downlink transmit beam k. In this example, the inter-cell spatial interference is mitigated when the neighbor base station gNB2 avoids transmitting energy in the direction of the downlink transmit beam k over the resources serving the first user device.

[0021]

[0033] According to aspects of this disclosure, a serving cell predicts downlink interference that a UE being served will receive from different potential downlink transmit beams of neighboring cells. For example, a serving cell may identify a subset of UEs being served in which the adverse effects potentially caused by inter-cell downlink interference exceed a given UE interference threshold. This identification of a potential victim subset of UEs may also include additional criteria, such as the type of traffic the UEs are receiving. For example, UEs receiving delay-sensitive traffic and / or high-reliability traffic may be selected as part of a potential victim subset of UEs.

[0022]

[0034] In these embodiments of the Disclosure, a serving cell sends a request message to a potentially interfering neighbor cell for each of the potential victim subsets of the UE. The request message may include a prohibited list of beam indices that the potentially interfering neighbor cell is requested to avoid. Furthermore, the request message may indicate a requested time / frequency resource (e.g., a time slot / resource block (RB)) for which protection is requested. In some implementations, a predefined set of time / frequency resources is configured for every cell, and therefore the signaling may simply refer to an index of the proposed set of resources. Alternatively, the time / frequency resources are left to be determined by the neighbor cell.

[0023]

[0035] In some aspects of this disclosure, learning of inter-spatial cell downlink interference and prediction of a victim subset of UEs are performed in an interference cell, sometimes referred to as an aggressor neighbor cell. In these aspects of this disclosure, a serving cell identifies potentially vulnerable UEs based on their location, traffic type, or other selection criteria. Once identified, the serving cell sends a request message to one or more aggressor neighbor cells. The request message may indicate (1) the location of one or more vulnerable UEs, (2) the UE interference tolerance threshold, and / or (3) a subset of the demand for resources to be protected. In other aspects of this disclosure, an indication of the traffic load of the victim UEs is provided to represent the desired amount of resources to be protected.

[0024]

[0036] Request messages sent by serving cells may omit resource demands, and this is optional. When a request message omits resource demands, the resources to be protected are determined by the neighboring cell. Furthermore, there may be a predefined set of configured time / frequency resources for each cell. In this configuration, the signaling of request messages may simply refer to an index of the proposed set of resources that satisfy the UE resource demands.

[0025]

[0037] In other implementations, learning and prediction are performed at a centralized coordinating node, such as a network controller. For example, a serving cell identifies potentially vulnerable UEs based on their location, traffic type, or other selection criteria. Once identified, the serving cell transmits information about the identified vulnerable UEs to the centralized coordinating node. This information may include (1) the location of (one or more) vulnerable UEs, (2) the interference threshold for vulnerable UEs, and (3) all or a subset of the traffic load (e.g., updated traffic demand). Some implementations, including central node coordination, can be beneficial when multiple aggressor neighbor cells are potentially causing interference to a victim UE.

[0026]

[0038] Figure 1 shows a network 100 in which embodiments of this disclosure may be implemented. Network 100 may be a 5G network or an NR network, or several other wireless networks, such as an LTE network. Wireless network 100 may include several BS110s (shown as BS110a, BS110b, BS110c, and BS110d) and other network entities. A BS is an entity that communicates with user equipment (UE) and may also be called a base station, NR BS, node B, gNB, 5G node B (NB), access point, transmit / receive point (TRP), etc. Each BS may provide communication coverage to a specific geographic area. In 3GPP, the term “cell” may refer to the coverage area of ​​a BS and / or the BS subsystem that services this coverage area, depending on the context in which the term is used.

[0027]

[0039] A BS can provide communication coverage to macrocells, picocells, femtocells, and / or other types of cells. A macrocell may cover a relatively large geographical area (e.g., a radius of several kilometers) and may enable unrestricted access by UEs subscribing to the service. A picocell may cover a relatively small geographical area and may enable unrestricted access by UEs subscribing to the service. A femtocell may cover a relatively small geographical area (e.g., a home) and may enable limited access by UEs associated with the femtocell (e.g., UEs in a Limited Subscriber Group (CSG)). A BS for a macrocell is sometimes called a macroBS. A BS for a picocell is sometimes called a picoBS. A BS for a femtocell is sometimes called a femtoBS or homeBS. In the example shown in Figure 1, BS110a may be a macroBS for macrocell 102a, BS110b may be a picoBS for picocell 102b, and BS110c may be a femtoBS for femtocell 102c. A BS may support one or more (for example, three) cells. The terms “eNB”, “base station”, “NR BS”, “gNB”, “TRP”, “AP”, “Node B”, “5G NB”, and “cell” may be used interchangeably.

[0028]

[0040] In some embodiments, cells may not necessarily be fixed, and the geographical area of ​​a cell may move according to the location of the mobile BS. In some embodiments, BSs may be interconnected with each other and / or with one or more other BSs or network nodes (not shown) in the wireless network 100 through various types of backhaul interfaces, such as direct physical connections and virtual networks, using any suitable transport network.

[0029]

[0041] The wireless network 100 may also include relay stations. A relay station is an entity that can receive data transmissions from upstream stations (e.g., BS or UE) and send those data transmissions to downstream stations (e.g., UE or BS). A relay station may also be a UE that can relay transmissions for other UEs. In the example shown in Figure 1, relay station 110d may communicate with macro BS110a and UE120d to facilitate communication between BS110a and UE120d. Relay stations are sometimes also called relay BS, relay base stations, or relays.

[0030]

[0042] The wireless network 100 may be a heterogeneous network including different types of BS, such as macro BS, pico BS, femto BS, and relay BS. These different types of BS may have different transmission power levels, different coverage areas, and different effects on interference in the wireless network 100. For example, macro BS may have high transmission power levels (e.g., 5-40 watts), while pico BS, femto BS, and relay BS may have lower transmission power levels (e.g., 0.1-2 watts).

[0031]

[0043] The network controller 130 can be coupled to a set of BSs and can coordinate and control these BSs. The network controller 130 can communicate with the BSs via backhaul. The BSs can also communicate with each other directly or indirectly, for example, via wireless or wireline backhaul.

[0032]

[0044] UE120 (e.g., 120a, 120b, 120c) may be distributed throughout the wireless network 100, and each UE may be stationary or mobile. UEs may also be called access terminals, terminals, mobile stations, subscriber units, stations, etc. UEs may be cellular phones (e.g., smartphones), personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, laptop computers, cordless phones, wireless local loop (WLL) stations, tablets, cameras, gaming devices, netbooks, smartbooks, ultrabooks, medical devices or medical equipment, biosensors / biometric devices, wearable devices (smartwatches, smart clothing, smart glasses, smart wristbands, smart jewelry (e.g., smart rings, smart bracelets)), entertainment devices (e.g., music or video devices, or satellite radios), vehicle components or vehicle sensors, smart meters / smart sensors, industrial manufacturing equipment, global positioning system devices, or any other suitable devices configured to communicate via wireless or wired media.

[0033]

[0045] Base station 110 may include a neural processing engine 150. For brevity, only one base station 110a is shown as including the neural processing engine 150, but neighbor base stations may also include the neural processing engine 150. The neural processing engine 150 can predict inter-cell downlink interference that the UE will experience. The neural processing engine 150 may also communicate with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0034]

[0046] The network controller 130 may include a neural processing engine 160. The neural processing engine 160 can predict inter-cell downlink interference that the UE will experience. The neural processing engine 160 may also communicate with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0035]

[0047] Some UEs may be considered machine-type communications (MTC) UEs or advanced or enhanced machine-type communications (eMTC) UEs. MTC UEs and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, and location tags that can communicate with base stations, other devices (e.g., remote devices), or any other entities. Wireless nodes may provide connectivity to or for a network (e.g., a wide area network such as the Internet or a cellular network) via, for example, a wired or wireless communication link. Some UEs may be considered Internet of Things (IoT) devices and / or implemented as NB-IoT (Narrowband Internet of Things) devices. Some UEs may be considered customer premises equipment (CPE). UE120 may be contained within a housing that houses the components of UE120, such as processor components and memory components.

[0036]

[0048] Generally, any number of wireless networks can be deployed within a given geographical area. Each wireless network may support a specific RAT and may operate on one or more frequencies. RATs are sometimes called wireless technologies or air interfaces. Frequencies are sometimes called carriers or frequency channels. Each frequency may support a single RAT within a given geographical area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks may be deployed.

[0037]

[0049] In some embodiments, two or more UE120s (for example, shown as UE120a and UE120e) may communicate directly using one or more sidelink channels (for example, without using base station 110 as an intermediary for communication with each other). For example, UE120s may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-anything (V2X) protocols (which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, etc.), mesh networks, etc. In this case, UE120s may perform scheduling operations, resource selection operations, and / or other operations described elsewhere as being performed by base station 110. For example, base station 110 may configure UE120s via downlink control information (DCI), radio resource control (RRC) signaling, media access control-control elements (MAC-CE), or system information (for example, system information blocks (SIB)).

[0038]

[0050] As stated above, Figure 1 is provided as an example only. Other examples may differ from those described in relation to Figure 1.

[0039]

[0051] Figure 2 shows a block diagram of design 200 of base station 110, which may be one of the base stations in Figure 1, and UE 120, which may be one of the UEs in Figure 1. Base station 110 may be equipped with T antennas 234a to 234t, and UE 120 may be equipped with R antennas 252a to 252r, where generally T ≥ 1 and R ≥ 1.

[0040]

[0052] At base station 110, the transmit processor 220 may receive data from data source 212 for one or more UEs, select one or more modulation and coding schemes (MCS) for each UE at least in part based on the channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) the data for each UE at least in part based on the (one or more) MCS selected for that UE, and provide data symbols for all UEs. Reducing the MCS reduces throughput but increases the reliability of the transmission. The transmit processor 220 may also process system information and control information (e.g., CQI requests, authorizations, upper-layer signaling, etc.) (e.g., semi-static resource partitioning information (SRPI), etc.) and provide overhead symbols and control symbols. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS)) and synchronization signals (e.g., primary synchronization signals (PSS) and secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may, where applicable, perform spatial processing (e.g., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, and may provide T output symbol streams to T modulators (MODs) 232a-232t. Each modulator 232 may process its respective output symbol stream (e.g., for orthogonal frequency division multiplexing (OFDM), etc.) to acquire an output sample stream. Each modulator 232 may further process the output sample stream (e.g., convert to analog, amplify, filter, and upconvert) to acquire a downlink signal. The T downlink signals from modulators 232a-232t may be transmitted via T antennas 234a-234t, respectively. According to various embodiments described in more detail below, a synchronization signal may be generated using location coding to convey additional information.

[0041]

[0053] In UE120, antennas 252a to 252r may receive downlink signals from base station 110 and / or other base stations and provide the received signals to demodulators (DEMOD) 254a to 254r, respectively. Each demodulator 254 may adjust the received signal (e.g., filter, amplify, downconvert, and digitize) to acquire an input sample. Each demodulator 254 may further process the input sample (e.g., for OFDM, etc.) to acquire a received symbol. A MIMO detector 256 may acquire received symbols from all R demodulators 254a to 254r and, where applicable, perform MIMO detection on the received symbols and provide the detected symbols. A receiving processor 258 may process the detected symbols (e.g., demodulate and decode) and provide the decoded data for UE120 to the data sink 260 and the decoded control and system information to the controller / processor 280. The channel processor may determine the reference signal received power (RSRP), the received signal strength indicator (RSSI), the reference signal received quality (RSRQ), the channel quality indicator (CQI), and so on. In some embodiments, one or more components of the UE120 may be contained within the housing.

[0042]

[0054] On the uplink, at UE120, the transmit processor 264 may receive and process data from data source 262 and control information (for reporting, e.g., RSRP, RSSI, RSRQ, CQI, etc.) from controller / processor 280. The transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may, if applicable, be precoded by the TX MIMO processor 266, further processed by modulators 254a-254r (for, e.g., DFT-s-OFDM, CP-OFDM, etc.), and transmitted to base station 110. At base station 110, uplink signals from UE120 and other UEs may be received by antenna 234, processed by demodulator 254, detected by MIMO detector 236 if applicable, and further processed by receive processor 238 to obtain the decoded data and control information sent by UE120. The receiving processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The base station 110 includes a communication unit 244 and may communicate with the network controller 130 via the communication unit 244. The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292.

[0043]

[0055] The controller / processor 240 of base station 110 and / or the controller / processor 280 of UE 120 in Figure 2 may implement one or more machine learning-related techniques for predicting location-based downlink interference assistance information for UE 120, as will be described in more detail elsewhere. For example, the controller / processor 280 of UE 120 in Figure 2 may implement or direct the operation of, for example, the process in Figure 8 and / or other processes as described. Furthermore, the controller / processor 240 of base station 110 in Figure 2 may implement or direct the operation of, for example, the processes in Figures 9 to 12 and / or other processes as described. Memories 242 and 282 may store data and program code for base station 110 and UE 120, respectively. The scheduler 246 may schedule the UE for data transmission on the downlink and / or uplink.

[0044]

[0056] In some embodiments, the base station 110 and the network controller 130 may include means for predicting, means for selecting, means for transmitting, means for receiving, means for updating, and / or means for communicating. Such means may include one or more components of the network controller 130 or base station 110 as described with respect to Figure 2.

[0045]

[0057] As stated above, Figure 2 is provided as an example only. Other examples may differ from those described in relation to Figure 2.

[0046]

[0058] In some cases, different types of devices supporting different types of applications and / or services may coexist within a cell. Examples of different types of devices include UE handsets, customer premises equipment (CPE), vehicles, and Internet of Things (IoT) devices. Examples of different types of applications include ultra-high reliability low-latency communications (URLLC) applications, massive machine-type communications (mMTC) applications, enhanced mobile broadband (eMBB) applications, and vehicle-to-anything (V2X) applications. Furthermore, in some cases, a single device may support different applications or services simultaneously.

[0047]

[0059] Figure 3 shows an exemplary implementation of a system-on-a-chip (SOC) 300, which may include a central processing unit (CPU) 302 or a multi-core CPU configured to generate gradients for neural network training, according to several aspects of the present disclosure. The SOC 300 may be contained within a base station 110 or UE 120. Variables (e.g., neural signals and synaptic weights), system parameters related to computation devices (e.g., a weighted neural network), delays, frequency bin information, and task information may be stored in a memory block associated with a neural processing unit (NPU) 308, a memory block associated with a CPU 302, a memory block associated with a graphics processing unit (GPU) 304, a memory block associated with a digital signal processor (DSP) 306, a memory block 318, or distributed across multiple blocks. Instructions executed in the CPU 302 may be loaded from program memory associated with the CPU 302 or from memory block 318.

[0048]

[0060] The SOC300 may also include additional processing blocks adapted to specific functions, such as a GPU304 and a DSP306, a connectivity block 310 which may include fifth-generation (5G) connectivity, fourth-generation Long-Term Evolution (4G LTE) connectivity, Wi-Fi® connectivity, USB connectivity, Bluetooth® connectivity, etc., and a multimedia processor 312 which may be capable of detecting and recognizing gestures, for example. In one implementation, the NPU is implemented in the CPU, DSP, and / or GPU. The SOC300 may also include a navigation module 320 which may include a sensor processor 314, an image signal processor (ISP) 316, and / or a global positioning system.

[0049]

[0061] The SOC300 may be based on the ARM instruction set. In one aspect of this disclosure, the instructions loaded into the general-purpose processor 302 may include program code for predicting inter-cell downlink interference that the UE will experience, and program code for communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0050]

[0062] Deep learning architectures can perform object recognition tasks by learning to represent inputs at progressively higher levels of abstraction in each layer, thereby accumulating useful feature representations of the input data. In this way, deep learning addresses a major bottleneck in traditional machine learning. Before the advent of deep learning, machine learning methods for object recognition problems sometimes relied heavily on human-designed features, often in combination with shallow classifiers. A shallow classifier might be, for example, a two-class linear classifier where a weighted sum of feature vector components is compared to a threshold to predict which class an input belongs to. Human-designed features might be templates or kernels adapted to a specific problem domain by engineers with domain expertise. In contrast, deep learning architectures learn to represent features similar to those that human engineers could design, but they can do so through training. Furthermore, deep networks can learn to represent and recognize new types of features that humans may not have considered.

[0051]

[0063] Deep learning architectures can learn feature hierarchies. For example, given visual data, the first layer may learn to recognize relatively simple features in the input stream, such as edges. In another example, given auditory data, the first layer may learn to recognize spectral power at a specific frequency. A second layer, taking the output of the first layer as input, may learn to recognize combinations of features, such as simple shapes in the case of visual data, or combinations of sounds in the case of auditory data. For example, higher layers may learn to represent complex shapes in visual data, or words in auditory data. Even higher layers may learn to recognize common visual objects or speech phrases.

[0052]

[0064] Deep learning architectures can work particularly well when applied to problems with natural hierarchical structures. For example, classifying motorized vehicles can benefit from initial learning to recognize wheels, windshields, and other features. These features can then be combined in different ways in higher layers to recognize cars, trucks, and airplanes.

[0053]

[0065] Neural networks can be designed using various connectivity patterns. In a feedforward network, information is passed from lower layers to higher layers, and each neuron in a given layer communicates with neurons in higher layers. As described above, hierarchical representations can be accumulated in successive layers of a feedforward network. Neural networks can also have recurrent or (also called top-down) feedback connections. In recurrent connections, the output from a neuron in a given layer can communicate with another neuron in the same layer. Recurrent architectures can be useful for recognizing patterns across two or more chunks of input data delivered sequentially to the neural network. The connection from a neuron in a given layer to a neuron in a lower layer is called a feedback (or top-down) connection. Networks with many feedback connections can be useful when the recognition of a higher-level concept can help discriminate certain lower-level features of the input.

[0054]

[0066] The connections between layers of a neural network can be fully connected or locally connected. Figure 4A shows an example of a fully connected neural network 402. In the fully connected neural network 402, neurons in the first layer can communicate their outputs to any neuron in the second layer, such that each neuron in the second layer receives input from any neuron in the first layer. Figure 4B shows an example of a locally connected neural network 404. In the locally connected neural network 404, neurons in the first layer can be connected to a limited number of neurons in the second layer. More generally, the locally connected layers of the locally connected neural network 404 can be configured such that each neuron in the layer has the same or similar connectivity pattern, but with different connectivity strengths (e.g., 410, 412, 414, and 416). The connectivity pattern of local connections can create spatially distinct receptive fields in the upper layers, as higher-layer neurons in a given region can receive inputs that have been tuned through training to the properties of a limited portion of the total input to the network.

[0055]

[0067] An example of a locally connected neural network is a convolutional neural network. Figure 4C shows an example of a convolutional neural network 406. The convolutional neural network 406 can be configured such that the connection strengths related to the input for each neuron in the second layer are shared (e.g., 408). Convolutional neural networks may be suitable for problems where the spatial location of the input is meaningful.

[0056]

[0068] One type of convolutional neural network is the deep convolutional network (DCN). Figure 4D shows a detailed example of DCN400 designed to recognize visual features from an image 426 input from an image capture device 430, such as an in-vehicle camera. In this example, DCN400 can be trained to identify traffic signs and the numbers provided on them. Of course, DCN400 can be trained for other tasks, such as identifying lane markings or traffic signals.

[0057]

[0069] DCN400 can be trained using supervised learning. During training, DCN400 may be presented with images, such as image 426 of a speed limit sign, and then a forward pass may be calculated to produce output 422. DCN400 may include a feature extraction section and a classification section. Upon receiving image 426, a convolutional layer 432 may apply a convolutional kernel (not shown) to image 426 to generate a first set of feature maps 418. As an example, the convolutional kernel for convolutional layer 432 may be a 5x5 kernel that generates a 28x28 feature map. In this example, four different feature maps are generated in the first set of feature maps 418, so four different convolutional kernels were applied to image 426 in convolutional layer 432. Convolutional kernels are sometimes called filters or convolutional filters.

[0058]

[0070] A first set of feature maps 418 may be subsampled by a max pooling layer (not shown) to generate a second set of feature maps 420. The max pooling layer reduces the size of the first set of feature maps 418; that is, the size of the second set of feature maps 420, such as 14×14, is smaller than the size of the first set of feature maps 418, such as 28×28. The reduced size provides similar information to subsequent layers while reducing memory consumption. The second set of feature maps 420 may be further convolved through one or more subsequent convolutional layers (not shown) to generate one or more subsequent sets of feature maps (not shown).

[0059]

[0071] In the example in Figure 4D, a second set of feature maps 420 is convolved to generate a first feature vector 424. Furthermore, the first feature vector 424 is further convolved to generate a second feature vector 428. Each feature in the second feature vector 428 may contain a number corresponding to a possible feature of image 426, such as "label", "60", and "100". A softmax function (not shown) can be used to convert the numbers in the second feature vector 428 into probabilities. Thus, the output 422 of DCN400 is the probability that image 426 contains one or more features.

[0060]

[0072] In this example, the probabilities in output 422 for "label" and "60" are higher than the probabilities for other outputs in output 422, such as "30", "40", "50", "70", "80", "90", and "100". Before training, the outputs 422 generated by DCN400 may be inaccurate. Therefore, an error can be calculated between output 422 and the target output. The target output is the ground truth of image 426 (e.g., "label" and "60"). The weights of DCN400 can then be adjusted so that the output 422 of DCN400 is more closely matched to the target output.

[0061]

[0073] To adjust the weights, the learning algorithm may compute a gradient vector for the weights. The gradient may indicate the amount by which the error increases or decreases when the weights are adjusted. In the top layer, the gradient may directly correspond to the weight values ​​connecting the activated neurons in the second-to-last layer to the neurons in the output layer. In lower layers, the gradient may depend on the weight values ​​and the error gradient computed in the upper layers. The weights can then be adjusted to reduce the error. This method of adjusting weights is sometimes called "backpropagation" because it involves a "backward path" through the neural network.

[0062]

[0074] In practice, the error gradient of the weights can be calculated over a small number of examples so that the calculated gradient approximates the true error gradient. This approximation method is sometimes called stochastic gradient descent. Stochastic gradient descent can be repeated until the achievable error rate for the entire system no longer decreases, or until the error rate reaches a target level. After training, the DCN may be presented with a new image (e.g., the speed limit sign in image 426), and the forward pass through the network may yield output 422, which can be considered the DCN's inference or prediction.

[0063]

[0075] A deep belief network (DBN) is a probabilistic model with multiple layers of hidden nodes. DBNs can be used to extract hierarchical representations of training datasets. DBNs can be obtained by stacking layers of restricted Boltzmann machines (RBMs). RBMs are a type of artificial neural network that can learn probability distributions across a set of inputs. Because RBMs can learn probability distributions in the absence of information about the class to which each input should be categorized, RBMs are often used in unsupervised learning. Using hybrid unsupervised and supervised paradigms, the lower RBM of a DBN can be trained in an unsupervised manner and can act as a feature extractor, while the upper RBM can be trained in a supervised manner (on a joint distribution of inputs from previous layers and target classes) and can act as a classifier.

[0064]

[0076] A deep convolutional network (DCN) is a network of convolutional networks consisting of additional pooling and normalization layers. DCNs have achieved state-of-the-art performance for many tasks. DCNs can be trained using supervised learning, where both the input and output targets are known for many samples and the network weights are modified using gradient descent methods.

[0065]

[0077] A DCN can be a feedforward network. Furthermore, as described above, the connections from neurons in the first layer of a DCN to groups of neurons in the next higher layer are shared across the neurons in the first layer. The feedforward and covalent connections of a DCN can be leveraged for high-speed processing. The computational burden of a DCN can be much less than that of a similarly sized neural network with recurrent or feedback connections, for example.

[0066]

[0078] The processing of each layer of a convolutional network can be considered as a spatially invariant template or basis projection. If the input is initially decomposed into multiple channels, such as the red, green, and blue channels of a color image, the convolutional network trained on that input can be considered three-dimensional, with two spatial dimensions along the image axes and a third dimension capturing the color information. The output of the convolutional connections can be considered to form a feature map in subsequent layers, where each element of the feature map (e.g., 220) may receive input from various neurons in the previous layer (e.g., feature map 218) and from each of the multiple channels. Values ​​in the feature map can be further processed using nonlinearity, such as rectification or max(0,x). Values ​​from adjacent neurons can be further pooled, which corresponds to downsampling and may provide further local invariance and dimensionality reduction. Normalization, corresponding to whitening, can also be applied by lateral suppression between neurons in the feature map.

[0067]

[0079] The performance of deep learning architectures can improve as more labeled data points become available or as computational power increases. Modern deep neural networks are routinely trained using computing resources thousands of times greater than what was available to the average researcher just 15 years ago. New architectures and training paradigms can further enhance the performance of deep learning. Rectified linear units can mitigate the training problem known as vanishing gradient. New training techniques can reduce overfitting, thus enabling larger models to achieve better generalization. Encapsulation techniques can extract data within a given receptive field, further improving overall performance.

[0068]

[0080] Figure 5 is a block diagram of a deep convolutional network 550. The deep convolutional network 550 may include several different types of layers based on connectivity and weight sharing. As shown in Figure 5, the deep convolutional network 550 includes convolutional blocks 554A and 554B. Each of the convolutional blocks 554A and 554B may consist of a convolutional layer (CONV) 356, a normalization layer (LNorm) 558, and a maximum pooling layer (MAX POOL) 560.

[0069]

[0081] The convolutional layer 556 may include one or more convolutional filters that can be applied to the input data to generate a feature map. Although only two of the convolutional blocks 554A and 554B are shown, this disclosure is not limited in that way, and instead, any number of convolutional blocks 554A and 554B may be included in the deep convolutional network 550 according to design preferences. A normalization layer 558 may normalize the output of the convolutional filters. For example, the normalization layer 558 may perform whitening or lateral suppression. A max pooling layer 560 may perform downsampling aggregation across space for local invariance and dimensionality reduction.

[0070]

[0082] For example, the parallel filter bank of the deep convolutional network may be loaded onto the CPU 302 or GPU 304 of the SOC 300 to achieve high performance and low power consumption. In an alternative embodiment, the parallel filter bank may be loaded onto the DSP 306 or ISP 316 of the SOC 300. Furthermore, the deep convolutional network 550 may have access to other processing blocks that may reside on the SOC 300, such as the sensor processor 314 and the navigation module 320, which are dedicated to sensors and navigation, respectively.

[0071]

[0083] The deep convolutional network 550 may also include one or more fully connected layers 562 (FC1 and FC2). The deep convolutional network 550 may further include logistic regression (LR) layers 564. Between each layer 556, 558, 560, 562, 564 of the deep convolutional network 550 are weights (not shown) to be updated. The output of each layer (e.g., 556, 558, 560, 562, 564) may serve as input to subsequent layers of the deep convolutional network 550 (e.g., 556, 558, 560, 562, 564) to learn a hierarchical feature representation from the input data 552 (e.g., images, audio, video, sensor data, and / or other input data) supplied in the first of the convolutional blocks 554A. The output of the deep convolutional network 550 is a classification score 566 for the input data 552. A classification score of 566 can be a set of probabilities, where each probability is the probability that the input data contains a feature from the set of features.

[0072]

[0084] As described above, Figures 3 to 5 are provided as examples. Other examples may differ from those described with respect to Figures 3 to 5.

[0073]

[0085] As described above, inter-cell interference can result in signal degradation for the user (e.g., signal-to-interference plus noise ratio (SINR)). This signal degradation for the user can be particularly significant when the user is at the cell edge. Furthermore, with the introduction of large-scale multi-input multiple-output (MIMO) antennas in next-generation base stations (e.g., gNBs), this inter-cell interference can be highly directional and highly variable over time. Unfortunately, highly directional interference at the cell edge can reduce data rates and negatively impact the user experience. Moreover, the high variability of interference makes it more difficult to implement link adaptation, such as predicting the supported modulation and coding scheme (MCS). This is challenging for latency-sensitive applications with limited latency budgets. This limited latency budget may be insufficient to recover packets through the Hybrid Auto Retransmission Request (HARQ) procedure when the selected modulation and coding scheme (MCS) is incorrect.

[0074]

[0086] Figures 6A and 6B illustrate a communication network in which spatial interference experienced by user equipment (UEs) is based on a downlink transmit beam from a neighbor base station to a neighbor UE, according to aspects of the present disclosure. As shown in Figure 6A, in the first interference scenario 600, the first UE 120-1 communicates with the first base station 110-1 through the downlink transmit beam i. Similarly, the second UE 120-2 communicates with the neighbor base station 110-2 through the downlink transmit beam j. In this example, spatial intercellular interference from the downlink transmit beam j to the downlink transmit beam i results in minimal signal degradation (e.g., SINR = 20 dB) in the first UE 120-1.

[0075]

[0087] Figure 6B shows a second interference scenario 650 in which the first UE120-1 communicates with the first base station 110-1 through the downlink transmit beam i. In contrast, the second UE120-2 communicates with the neighbor base station 110-2 through the downlink transmit beam k, which interferes with the downlink transmit beam i. In this example, spatial intercellular interference from the downlink transmit beam k to the downlink transmit beam i results in significant signal degradation in the first UE120-1 (e.g., SINR = 5 dB), which degrades the user experience in the first UE120-1.

[0076]

[0088] Figure 7 is a diagram of a communication network 700 showing signal intensity measurement of a downlink transmit beam from a neighbor base station to enable inter-spatial cell interference-aware downlink coordination according to an aspect of the present disclosure. According to an aspect of the present disclosure, a neural network is trained to infer the effect of a potential transmit beam from a neighbor base station (e.g., gNB) on a potential victim UE. In this example, a victim user device (UE1) 120-1 communicates with a serving base station (gNB1) 110-1 on a downlink transmit beam i. Unfortunately, the victim UE1120-1 is subjected to significant interference from the downlink transmit beam k of a neighbor base station (gNB2) 110-2, which is used to communicate with a second user device (UE2) 120-2.

[0077]

[0089] In this example, inter-cell spatial interference with the victim UE1120-1 is mitigated by coordination with the neighbor base station gNB2110-2. For example, the neighbor base station gNB2110-2 may transmit on the downlink beam j to avoid transmitting energy in the direction of the downlink transmit beam k over the resources servicing the victim UE1120-1. An aspect of this disclosure involves coordinating with the neighbor base station gNB2110-2 to transmit on the downlink beam j over the resources used to serve the victim UE1120-1 in order to avoid interference with the victim UE1110-1.

[0078]

[0090] According to aspects of this disclosure, a neural network in serving base station gNB1110-1 is trained to infer the impact of neighbor base station gNB2110-2's downlink transmit beam on victim UE1120-1. In these aspects of this disclosure, serving base station gNB1110-1 cooperates with neighbor base station gNB2110-2 to prohibit communication of the downlink transmit beam k by neighbor base station gNB2110-2 on the time / frequency resources used to service victim UE1120-1. In some configurations, inter-cell interference prediction is performed using machine learning with a neural processing engine (NPE), for example, as shown in Figure 8.

[0079]

[0091] Figure 8 is a block diagram of a network including a neural processing engine configured for neural network-based prediction of spatial inter-cell interference-based distributions to enable spatial inter-cell interference-aware downlink coordination, according to an aspect of the present disclosure. In aspects of the present disclosure, a database stores information about the potential transmit beam influence of a neighbor base station (e.g., gNB) on a potential victim UE. In these aspects of the present disclosure, the database stores UE channel state information (CSI) reference signal (CSI-RS) measurement reports, beam information, and UE location, enabling database lookups to determine the potential influence from a neighbor base station on a potential victim UE.

[0080]

[0092] Figure 8 shows a network 800 including a UE 120 having a location block 830 and a base station 110 having a neural processing engine 810 for implementing a neural network. In this example, location block 830 provides the neural processing engine 810 with the UE location 802(X). A neighbor cell transmit precoder 804(T) (e.g., channel state information (CSI) beam index) is also input from the neighbor cell to the neural processing engine 810. Based on the UE location 802 and the neighbor cell transmit precoder 804, the neural processing engine 810 predicts an interference-based distribution 820(F) for the current location of the UE 120. For example, an interference (e.g., interference overthermal) distribution may be predicted, or a signal-to-interference plus noise ratio (SINR) distribution may be predicted.

[0081]

[0093] In aspects of this disclosure, the training of the neural network of the neural processing engine 810 may be based on UE channel state information (CSI) reference signal (CSI-RS) measurement reports, as well as neighbor cell transmit precoder 804 and UE location 802. The UE CSI-RS measurement report provides neighbor cell signal strength for each beam of the neighbor base station. For example, the signal strength measurement report may be based on the CSI report, which may include, for example, SINR information or reference signal received power (RSRP) information. In some aspects of this disclosure, the UE CSI-RS measurement report may provide SINR information where the signal strength corresponds to the serving cell and the interference corresponds to each beam of the neighbor base station.

[0082]

[0094] In some aspects of this disclosure, the base station 110 periodically sends a precoded CSI-RS signal to the serviced UE 120. The serviced UE 120 may use the received CSI-RS signal to estimate channel conditions. The serviced UE 120 may also use the received CSI-RS signal to identify a single beam or combination of beams that produces the strongest received signal quality (e.g., the strongest beam) to assist in data channel precoding. Furthermore, CSI-RS signals from other cells may be measured. For example, the UE may use CSI-RS signals from other cells to estimate interference caused by other cells. The UE may use the measured CSI-RS signals to perform radio resource management. For example, the UE may use the measured CSI-RS signals from other cells to identify whether a neighbor cell is stronger than the current serving cell, which may trigger a handover. In practice, CSI-RS measurements performed by the UE are reported to the serving cell 110 by the UE 120.

[0083]

[0095] As shown in Figure 8, the neural network of the neural processing engine 810 predicts an interference-based distribution 820 for a given UE location 802 based on the neighbor cell transmit precoder 804 and the UE location 802. The neighbor cell transmit precoder 804 may be a precoder index in a known codebook or a precoder weight. In aspects of this disclosure, the UE location 802 may be represented in the form of a combination of (x,y,z) coordinates of the UE 120 from a positioning source. The positioning source may be, for example, a Global Navigation Satellite System (GNSS), a 5G NR location server, etc. Alternatively, the UE location 802 may be determined based on a set of metrics representing the location of the UE 120 within a serving cell. For example, a set of metrics representing the location of UE120 within a serving cell may include a serving cell reference signal received power (RSRP) signal, a serving cell precoder indicating the strongest transmit beam direction (e.g., a precoding matrix indicator (PMI)), a serving cell channel quality indicator (CQI), and / or a path loss estimate for the channel between the serving cell and UE120. Furthermore, the UE location 802 may be determined based on other UE sensor information. In some embodiments, the UE location 802 may be a geolocation.

[0084]

[0096] In aspects of this disclosure, neural network training may be performed at various nodes. For example, neural network training may be performed at a serving cell. In this example, interference measurement reports, along with information about UE location 802, are sent by UE 120 to the serving cell base station 110. Location estimation of UE 120 may be performed at the serving cell base station 110 or communicated to the serving cell base station 110 by a separate location server. Alternatively, UE location indicator metrics are reported by UE 120 to the serving cell to determine UE location 802.

[0085]

[0097] In some aspects of this disclosure, neural network training is performed in one or more neighbor cells, such as neighbor base station gNB2110-2 shown in Figure 7. In these aspects of this disclosure, the serving cell base station gNB1110-1 sends UE location 802 and interference measurement report to neighbor base station gNB2110-2 in order to train the neural network at neighbor base station gNB2110-2. In other aspects of this disclosure, neural network training is performed in a centralized node. In these aspects of this disclosure, the serving cell base station gNB1110-1 sends UE location 802, serving cell identification information (ID), neighbor cell ID, and interference measurement report to the centralized node in order to train the neural network at the centralized node.

[0086]

[0098] Once a neural network is trained to infer the effect of a neighbor base station's transmit beam on a victim UE, a network device (e.g., a gNB) will coordinate with the neighbor base station. In these embodiments of the disclosure, network device coordination can prevent the neighbor base station from communicating its downlink transmit beam on the time / frequency resources used to service the victim UE. For example, as shown in Figure 7, UE 1120-1 is subjected to significant interference from the downlink transmit beam k of neighbor base station (gNB2) 110-2. In this example, the inter-cell spatial interference is mitigated when neighbor base station gNB2 110-2 avoids transmitting energy in the direction of the downlink transmit beam k on the resources used to service UE 1120-1.

[0087]

[0099] According to aspects of this disclosure, undesirable neighbor cell beams are identified based on several criteria that follow a predicted interference-based distribution. For example, the criterion may be an average or percentile exceeding a predetermined threshold. Furthermore, this spatial interference characterization may be used to coordinate scheduling between nearby cells, such as neighbor base station gNB2110-2, to prevent high-interference events, for example, as shown in Figures 9 to 11.

[0088]

[0100] Figure 9 is a timing diagram illustrating an exemplary process for inter-spatial-cell interference-aware downlink coordination in serving cell 900, according to various aspects of the present disclosure, performed, for example, by UE120 (120-1, ..., 120-N), base station 110-1 of serving cell 900, and base stations 110-2, ..., 110-N of neighbor cell 950 (950-1, ..., 950-N).

[0089]

[0101] According to aspects of this disclosure, the base station 110-1 of serving cell 900 predicts potential downlink interference that UEs 120 (120-1, ..., 120-N) in serving cell 900 will experience from different potential downlink transmit beams of neighbor cell 950 (950-1, ..., 950-N). For example, the base station 110-1 of serving cell 900 identifies a subset of UEs 120 being served for which the potential adverse effects caused by inter-cell downlink interference from neighbor cell 950 exceed a predetermined UE interference threshold. That is, neighbor cell 950 may include potentially interfering neighbor cells. This identification of a potential victim subset of UEs may also include additional criteria, such as the type of traffic the UEs are receiving. For example, UEs receiving delay-sensitive traffic and / or high-reliability traffic may be selected as part of a potential victim subset of UEs.

[0090]

[0102] At time t0, base station 110-1 of serving cell 900 sends a request message to the potentially interfering neighbor cell 950 for each victim subset of UE 120. The request message may include a proposal indicating a requested list of beam indices that the potentially interfering neighbor cell 950 is requested to avoid. Furthermore, the request message may indicate the requested time / frequency resources (e.g., time slots / resource blocks (RBs)) for which protection is requested. For example, the request message may indicate the amount of resources to be protected. Base station 110-1 may determine how much bandwidth a vulnerable UE needs, for example, 1 / 4 of the resources to be allocated. In some implementations, a predefined set of time / frequency resources is configured for each cell, and therefore the signaling of the request message at time t0 may simply refer to an index of the proposed set of resources. Alternatively, the selection of time / frequency resources is left to the neighbor cell 950 as a decision.

[0091]

[0103] At time t1, base stations 110-2~N of Aggressor Neighbor Cell 950 respond with one or more response messages received by base station 110-1 of Serving Cell 900 at time t1. The response message may be an acceptance of the proposal indicated in the request message. For example, the response message may indicate agreement to limit the energy transmitted in the identified beam direction for the time / frequency resource mentioned. Alternatively, the response message may include a potential or alternative proposal for the time / frequency resource to be protected. For example, the response message received at time t1 may include an alternative proposal for a different set of resources if the proposal in the request message from Serving Cell 900 (e.g., a serving proposal) is not accepted.

[0092]

[0104] Serving cell 900 may periodically repeat spatial cell-to-cell downlink interference predictions when the victim UE 120 changes location, channel conditions change, and / or traffic demand changes. For example, UE 120 may move closer to serving base station 110-1, or the UE may enter idle mode. At time t2, serving cell 900 may send an updated request message to neighbor cell 950 based on the updated prediction for the new conditions. Furthermore, at time t3, neighbor cell 950 may similarly respond to the updated request message with an updated response message. When the interference threat regarding victim UE 120 disappears, at time t4, serving cell 900 may send a cancel request message to stop resource protection. For example, serving cell 900 may send a cancel request message at time t4 when victim UE 120 enters idle mode.

[0093]

[0105] Figure 10 is a timing diagram illustrating an exemplary process for inter-spatial cell interference-aware downlink coordination in neighbor cell 950, according to various aspects of the present disclosure, performed, for example, by UE120 (120-1, ..., 120-N), base station 110-1 of serving cell 900, and base station 110-2 of neighbor cell 950.

[0094]

[0106] In aspects of this disclosure, prediction of inter-spatial cell downlink interference is performed in Neighbor Cell 950, sometimes referred to as Aggressor Neighbor Cell 950. In these aspects of this disclosure, Base Station 110-1 of Serving Cell 900 identifies potentially vulnerable UEs based on their location, traffic type, or other selection criteria. Once identified, at time t0, Base Station 110-1 of Serving Cell 900 sends a request message to Aggressor Neighbor Cell 950. The request message may indicate (1) the location of (one or more) vulnerable UEs, (2) UE interference tolerance thresholds, and / or (3) a subset of resource demands.

[0095]

[0107] The request message sent by base station 110-1 of serving cell 900 at time t0 may omit resource demand, which is optional. When the request message omits resource demand, the protected resources are determined by base station 110-2 of aggressor neighbor cell 950. Furthermore, instead of geolocation, the UE's location may be represented by a set of metrics that represent the UE's location. In addition, there may be a predefined set of configured time / frequency resources for each cell. In this configuration, the signaling of the request message sent at time t0 may simply refer to an index of the proposed set of resources that satisfy the UE's resource demand.

[0096]

[0108] In these aspects of the Disclosure, the base station 110-2 of Aggressor Neighbor Cell 950, in response to a request message at time t0, predicts whether interference from the transmitting beam of Aggressor Neighbor Cell 950 will cause a harmful effect on the victim UE that exceeds a UE interference threshold. In response to the predicted harmful effect, at time t1, the base station 110-2 of Aggressor Neighbor Cell 950 sends a response message to the serving cell 900 indicating agreement to limit the transmitted energy in the prohibited beam direction for the victim UE's requested time / frequency resources. Potentially, the response message at time t1 includes a proposal for time / frequency resources for the protected UE, such as a set of resources to be protected, or (if the resource demand is not accepted) an alternative proposal.

[0097]

[0109] In some implementations, the base station 110-1 of the serving cell 900 periodically evaluates the location and vulnerability of the protected UE120 and protected resources when the UE120 changes location, channel conditions change, or traffic demand changes. In response to any of these changed conditions, at time t2, the serving cell 900 may send an updated request message with the new conditions. At time t3, after predicting whether downlink interference would be detrimental to the updated set of vulnerable UE120s, the base station 110-2 of the aggressor neighbor cell 950 responds to the updated request message by sending an updated response message. In this example, once the interference threat to the set of vulnerable UE120s has disappeared, at time t4, the base station 110-1 of the serving cell 900 may send a cancel message to the aggressor neighbor cell 950 to terminate resource protection.

[0098]

[0110] Figure 11 is a timing diagram illustrating an exemplary process for inter-spatial cell interference-aware downlink coordination at the central node 960, according to various aspects of the present disclosure, performed by, for example, UE120 (120-1, ..., 120-N), base station 110-1 of serving cell 900, the central node, and base station 110-2 of aggressor neighbor cell 950.

[0099]

[0111] In some implementations, the prediction may be performed at a central node 960, such as a network controller 130. For example, base stations 110-1 of a serving cell 900 identify potentially vulnerable UEs based on their location, traffic type, or other selection criteria. Once identified, at time t1, base stations 110-1 of the serving cell 900 send a message to the central node 960 regarding the identified vulnerable UEs. This message may indicate (1) the location of (one or more) vulnerable UEs, (2) the interference threshold of the vulnerable UEs, and (3) all or a subset of the traffic load. As described above, the UE location may be represented using (1) the (x,y,z) coordinates of the UE from a positioning source (e.g., geolocation), and / or (2) a combination of a set of metrics representing the location of the UE within the serving cell 900. The positioning source may be, for example, a Global Navigation Satellite System (GNSS) location server, a 5G NR location server, or other location servers. Furthermore, the set of metrics representing the UE location may include the reference signal received power (RSRP) of serving cell 900, the serving cell precoder (e.g., the direction of the strongest transmit beam), the serving cell channel quality indicator (CQI), and / or an estimate of the path loss between serving cell 900 and UE120. Other UE sensor information may also be included in the vulnerable UE message at time t0.

[0100]

[0112] During operation, the central node 960 predicts whether the degradation caused by interference from the downlink transmit beam of Aggressor Neighbor Cell 950 to the victim UE 120 exceeds the UE interference threshold. At time t1, if the interference from the neighbor cell downlink transmit beam exceeds the UE interference threshold, the central node 960 sends a coordination request message to Aggressor Neighbor Cell 950. The request message may include a proposal to protect the UE by limiting the transmitted energy in a specified beam direction for the requested time / frequency resources mentioned in the request message. In response, at time t2, base station 110-2 of Aggressor Neighbor Cell 950 sends a response message to the central node 960. The response message may indicate that base station 110-2 of Aggressor Neighbor Cell 950 accepts the proposal. Otherwise, the response message may propose an alternative plan to protect the UE. At time t3, the central node 960 sends a response message to the serving cell 900, which may indicate a set of protected resources for the protected UE.

[0101]

[0113] In some implementations, the central node 960 periodically evaluates the location and vulnerability of (one or more) protected UEs and protected resources. The periodic evaluation may determine whether changes have been detected in the UE's location, the UE's channel conditions, and / or traffic demand to the UE. In response to detected changes, at time t4, the central node 960 may send an updated request message to the Aggressor Neighbor Cell 950 based on the changed conditions. In response, at time t5, the base station 110-2 of the Aggressor Neighbor Cell 950 may respond to the updated request message with an updated response message indicating the updated protected resources. At time t6, the central node 960 sends a response message to the serving cell 900, which may notify base station 110-1 of the updated set of protected resources.

[0102]

[0114] When the interference threat disappears, at time t7, serving cell 900 sends a cancel message to central node 960, which may trigger a termination message at time t8 to terminate resource protection. Several implementations, including a central node, may be beneficial when multiple aggressor neighbor cells are potentially causing interference to the victim UE.

[0103]

[0115] Figure 12 is a flowchart illustrating exemplary processes 1200 for neural network-based spatial inter-cell interference learning, for example, performed by a network device, according to various aspects of the present disclosure. Exemplary process 1200 is an example of a network extension for neural network-based spatial inter-cell interference-aware downlink coordination.

[0104]

[0116] As shown in Figure 12, in some embodiments, process 1200 includes predicting spatial downlink interference that the UE will experience (block 1202). For example, a base station (e.g., using controller / processor 240 and / or memory 242) can predict spatial downlink inter-cell downlink interference. The prediction may be made at a serving base station, an aggressor base station, or a central node. In some embodiments, the prediction is based on the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE.

[0105]

[0117] In some embodiments, process 1200 further includes communicating with a second network device (block 1204) to reduce inter-cell spatial downlink interference in the direction of the UE by protecting resources across a selected set of resources. For example, a base station (using, for example, antenna 234, DEMOD / MOD 232, TX MIMO processor 230, transmit processor 220, controller / processor 240, and / or memory 242) can communicate with a second network device to reduce inter-cell spatial downlink interference in the direction of the UE. In some embodiments, the resources to be protected include a beam index to be prohibited, time / frequency resources to be protected, and / or the amount of resources to be protected. Exemplary embodiments

[0118] Embodiment 1: A method for wireless communication by a first network device, comprising predicting inter-cell downlink interference experienced by a UE and communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0106]

[0119] Embodiment 2: The method of Embodiment 1, wherein a first network device comprises a serving cell, and a second network device comprises a potentially interfering neighbor cell, and the method further comprises the first network device selecting a UE in which the predicted inter-cell downlink interference exceeds a predetermined threshold, and sending a request message to the second network device.

[0107]

[0120] Embodiment 3: The method according to Embodiment 1 or 2, wherein the request message indicates a beam causing excessive interference.

[0108]

[0121] Embodiment 4: The method according to Embodiment 1 or 2, wherein the request message indicates the time / frequency resources to be protected.

[0109]

[0122] Embodiment 5: The method according to Embodiment 1 or 2, wherein the request message indicates the amount of resources to be protected, and the amount is determined based on the traffic demand of the UE.

[0110]

[0123] Embodiment 6: The method according to Embodiment 1 or 2, wherein the request message indicates an index of a selected resource set within a predetermined list of resource sets.

[0111]

[0124] Embodiment 7: The method according to Embodiment 1 or 2, further comprising receiving a response message indicating acceptance of the proposal indicated by the request message.

[0112]

[0125] Embodiment 8: The method according to Embodiment 1 or 2, further comprising receiving a response message indicating an alternative suggestion for a different set of resources.

[0113]

[0126] Embodiment 9: The method according to Embodiment 1 or 2, further comprising updating the request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE.

[0114]

[0127] Embodiment 10: The method of any one embodiment 1 to 9, wherein a first network device comprises a neighbor cell and a second network device comprises a serving cell, and the method further comprises receiving a request message from the second network device indicating the location of a UE, the UE interference tolerance threshold, and / or resource demand for the UE, making predictions based on the request message, and sending a response message to the second network device.

[0115]

[0128] Embodiment 11: The method according to any one of embodiments 1 to 10, further comprising receiving updates from a second network device on UE location, UE interference tolerance threshold, and / or resource demand for UE.

[0116]

[0129] Embodiment 12: The method according to Embodiment 1, wherein a first network device comprises a central node and a second network device comprises a serving cell, and the method further comprises receiving a first request message from the second network device indicating the location of a UE, a UE interference tolerance threshold, and / or resource demand for a UE; making predictions based on the first request message; sending a second request message to an Aggressor Neighbor Cell requesting resource protection; and sending a response message to the second network device indicating the resource to be protected.

[0117]

[0130] Embodiment 13: The method according to Embodiment 12, further comprising updating the forecast based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE.

[0118]

[0131] Embodiment 14: An apparatus for wireless communication by a first network device, comprising means for predicting spatial downlink cell interference experienced by a UE, and means for communicating with a second network device to reduce spatial downlink cell interference in the direction of the UE by protecting resources across a selected set of resources.

[0119]

[0132] Embodiment 15: The apparatus according to Embodiment 14, wherein a first network device comprises a serving cell, a second network device comprises a potentially interfering neighbor cell, and the apparatus further comprises means for the first network device to select a UE in which the predicted spatial downlink cell interference exceeds a predetermined threshold, and means for sending a request message to the second network device.

[0120]

[0133] Embodiment 16: The apparatus according to Embodiment 15, further comprising means for receiving a response message indicating acceptance of a proposal indicated by a request message.

[0121]

[0134] Embodiment 17: The apparatus according to Embodiment 15, further comprising means for receiving response messages indicating alternative suggestions for different sets of resources.

[0122]

[0135] Embodiment 18: The apparatus according to Embodiment 15, further comprising means for updating a request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE.

[0123]

[0136] Embodiment 19: The apparatus according to Embodiment 14, wherein a first network device comprises a neighbor cell, a second network device comprises a serving cell, and the apparatus further comprises means for receiving a request message from the second network device indicating the location of a UE, a UE interference tolerance threshold, and / or resource demand for a UE, means for making predictions based on the request message, and means for sending a response message to the second network device.

[0124]

[0137] Embodiment 20: The apparatus according to Embodiment 19, further comprising means for receiving updates from a second network device on UE locations, UE interference tolerance thresholds, and / or resource demands for UEs.

[0125]

[0138] Embodiment 21: The apparatus according to Embodiment 14, wherein the first network device comprises a central node, the second network device comprises a serving cell, and the apparatus further comprises means for receiving from the second network device a first request message indicating the location of a UE, a UE interference tolerance threshold, and / or resource demand for a UE; means for making predictions based on the first request message; means for sending a second request message to an Aggressor Neighbor Cell requesting resource protection; and means for sending a response message to the second network device indicating the resource to be protected.

[0126]

[0139] Embodiment 22: The apparatus according to Embodiment 21, further comprising means for updating forecasts based on updated UE locations, updated channel conditions for UEs, and / or updated resource demand for UEs.

[0127]

[0140] Embodiment 23: A first network device comprising a processor, a memory coupled to the processor, and instructions stored in the memory, wherein the instructions are operable, when executed by the processor, to cause the first network device to predict inter-cell downlink interference that a UE will experience and to communicate with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0128]

[0141] Embodiment 24: The first network device according to Embodiment 23, wherein the first network device comprises a serving cell, and the second network device comprises a potentially interfering neighbor cell, and the instruction further causes the first network device to select a UE in which the predicted inter-cell downlink interference exceeds a predetermined threshold, and to send a request message to the second network device.

[0129]

[0142] Embodiment 25: The first network device according to Embodiment 23, wherein the first network device comprises a neighbor cell and the second network device comprises a serving cell, and a command further causes the first network device to receive a request message from the second network device indicating the location of a UE, the UE interference tolerance threshold, and / or resource demand for a UE, to make predictions based on the request message, and to send a response message to the second network device.

[0130]

[0143] Embodiment 26: The first network device according to Embodiment 23, wherein the first network device comprises a central node and the second network device comprises a serving cell, and the command further causes the first network device to receive a first request message from the second network device indicating the location of a UE, the UE interference tolerance threshold, and / or resource demand for a UE; to make predictions based on the first request message; to send a second request message to the Aggressor Neighbor Cell requesting resource protection; and to send a response message to the second network device indicating the resource to be protected.

[0131]

[0144] Embodiment 27: The first network device according to Embodiment 26, wherein the instruction causes the first network device to further update its forecasts based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE.

[0132]

[0145] Embodiment 28: A non-temporary computer-readable medium recording program code, wherein the program code is executed by the processor of a first network device and comprises program code for predicting inter-cell downlink interference experienced by a UE, and program code for communicating with a second network device to reduce inter-cell downlink interference in the direction of the UE by protecting resources across a selected set of resources.

[0133]

[0146] Embodiment 29: The non-temporary computer-readable medium according to Embodiment 28, wherein the first network device comprises a neighbor cell, the second network device comprises a serving cell, and the non-temporary computer-readable medium further comprises program code for receiving a request message from the second network device indicating the location of a UE, the UE interference tolerance threshold, and / or resource demand for the UE, program code for making predictions based on the request message, and program code for sending a response message to the second network device.

[0134]

[0147] Embodiment 30: The non-temporary computer-readable medium according to Embodiment 28, wherein the first network device comprises a central node, the second network device comprises a serving cell, and the non-temporary computer-readable medium further comprises: program code for receiving from the second network device a first request message indicating the location of a UE, a UE interference tolerance threshold, and / or resource demand for a UE; program code for making predictions based on the first request message; program code for sending a second request message to an Aggressor Neighbor Cell requesting resource protection; and program code for sending a response message to the second network device indicating the resource to be protected.

[0135]

[0148] The foregoing disclosures are illustrative and explanatory, and are not exhaustive, nor do they limit the embodiments to the exact forms disclosed. Modifications and variations may be made in light of the foregoing disclosures or derived from the practice of the embodiments.

[0136]

[0149] The term “components” as used shall be broadly interpreted as hardware, firmware, and / or combinations of hardware and software. The processor used shall be implemented as hardware, firmware, and / or combinations of hardware and software.

[0137]

[0150] Several aspects of thresholds are described. Meeting the threshold used can mean, depending on the context, that the value is greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, or not equal to the threshold.

[0138]

[0151] It will be apparent that the systems and / or methods described may be implemented in different forms of hardware, firmware, and / or combinations of hardware and software. The specific control hardware or software code used to implement these systems and / or methods is not limiting to their embodiments. Therefore, the operation and behavior of the systems and / or methods are described without reference to specific software code, and it should be understood that software and hardware may be designed to implement the systems and / or methods based at least partially on the description.

[0139]

[0152] Certain combinations of features are expressed in the claims and / or disclosed herein, but these combinations do not limit the disclosure of various embodiments. In fact, many of these features can be combined in ways that are not expressed in the claims and / or disclosed herein in detail. Each dependent claim described below may depend directly on only one claim, but the disclosure of various embodiments includes each dependent claim combined with any other claims in the claims. The phrase “at least one of” the list of items refers to any combination of those items that includes a single member. For example, “at least one of a, b, or c” shall include a, b, c, ab, ac, bc, and abc, as well as any combination having multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc, and ccc, or any other order of a, b, and c).

[0140]

[0153] Any element, action, or command used should not be interpreted as important or essential unless explicitly stated so. Furthermore, the articles "a" and "an" used include one or more items and may be used interchangeably with "one or more." Additionally, the terms "set" and "group" used include one or more items (e.g., related items, unrelated items, combinations of related and unrelated items) and may be used interchangeably with "one or more." When only one item is intended, the phrase "only one" or a similar expression is used. Also, terms such as "has," "have," and "having" used should be open-ended. Furthermore, the phrase "based on" means "at least partially based on" unless otherwise specified. The invention described in the original claims of this application is listed below. [C1] A method of wireless communication using a first network device, Predicting the inter-cell downlink interference that the UE will experience, To reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, and to communicate with a second network device, A method that includes [a certain feature]. [C2] The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the method is The first network device selects the UE such that the predicted inter-cell downlink interference exceeds a predetermined threshold, Sending a request message to the second network device, A method of C1 that further includes the following: [C3] The aforementioned request message is a method of C2 indicating a beam that causes excessive interference. [C4] The aforementioned request message is a method of C2 indicating the time / frequency resources to be protected. [C5] The method according to C2, wherein the request message indicates the amount of resources to be protected, and the amount is determined based on the traffic demand of the UE. [C6] The method of C2 wherein the request message indicates the index of the selected resource set within a predetermined list of resource sets. [C7] The method of C2, further comprising receiving a response message indicating acceptance of the proposal indicated by the request message. [C8] The method for C2 further includes receiving a response message that presents alternative suggestions for different sets of resources. [C9] The method of C2, further comprising updating the request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE. [C10] The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the method is Receiving a request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, To make a prediction based on the aforementioned request message, Sending a response message to the second network device, A method of C1 that further includes the following: [C11] The method of C10, further comprising receiving updates from the second network device for the UE location, the UE interference tolerance threshold, and / or the resource demand for the UE. [C12] The first network device comprises a central node, the second network device comprises a serving cell, and the method is Receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, To make a prediction based on the first request message, Send a second request message to the Aggressor Neighbor Cell requesting resource protection, Sending a response message to the second network device indicating the protected resource, A method of C1 that further includes the following: [C13] The method according to C12, further comprising updating the forecast based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE. [C14] A device for wireless communication by a first network device, A means for predicting spatial downlink cell interference experienced by UE, Means for communicating with a second network device in order to reduce inter-spatial downlink cell interference in the direction of the UE by protecting resources across a selected set of resources, A device equipped with the following features. [C15] The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the device comprises The first network device provides means for selecting the UE such that the predicted spatial downlink cell interference exceeds a predetermined threshold, Means for sending a request message to the second network device, The apparatus described in C14, further comprising the above. [C16] The apparatus according to C15, further comprising means for receiving a response message indicating acceptance of the proposal indicated by the request message. [C17] The apparatus described in C15 further comprises means for receiving response messages indicating alternative suggestions for different sets of resources. [C18] The apparatus according to C15, further comprising means for updating the request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE. [C19] The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the device, Means for receiving request messages from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or resource demand for the UE, Means for making predictions based on the aforementioned request message, Means for sending a response message to the second network device, The apparatus described in C14, further comprising the above. [C20] The apparatus according to C19, further comprising means for receiving updates from the second network device for the UE location, the UE interference tolerance threshold, and / or the resource demand for the UE. [C21] The first network device comprises a central node, the second network device comprises a serving cell, and the device comprises Means for receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, Means for making predictions based on the first request message, A means for sending a second request message to the Aggressor Neighbor Cell requesting resource protection, The second network device has means for sending a response message indicating the protected resource, The apparatus described in C14, further comprising the above. [C22] The apparatus according to C21, further comprising means for updating the forecast based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE. [C23] Processor and The memory coupled to the aforementioned processor, Instructions stored in the aforementioned memory, A first network device comprising, where, when the instruction is executed by the processor, the first network device, Predicting the inter-cell downlink interference that the UE will experience, To reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, and to communicate with a second network device, A first network device capable of performing the following actions. [C24] The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the instruction is given to the first network device, Selecting the UE such that the predicted inter-cell downlink interference exceeds a predetermined threshold, Sending a request message to the second network device, The first network device described in C23 further enables this process. [C25] The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the instruction is given to the first network device, Receiving a request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, To make a prediction based on the aforementioned request message, Sending a response message to the second network device, The first network device described in C23 further enables this process. [C26] The first network device comprises a central node, the second network device comprises a serving cell, and the instruction is sent to the first network device, Receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, To make a prediction based on the first request message, Send a second request message to the Aggressor Neighbor Cell requesting resource protection, Sending a response message to the second network device indicating the protected resource, The first network device described in C23 further enables this process. [C27] The instruction causes the first network device, as described in C26, to further update the forecast based on the updated UE location, the updated channel conditions for the UE, and / or the updated resource demand for the UE. [C28] A non-temporary computer-readable medium recording program code, wherein the program code is executed by the processor of a first network device. Program code for predicting inter-cell downlink interference experienced by UE, Program code for communicating with a second network device in order to reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, A non-temporary computer-readable medium comprising [a specific feature]. [C29] The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the non-temporary computer-readable medium is Program code for receiving request messages from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, Program code for making predictions based on the aforementioned request message, Program code for sending a response message to the second network device, A non-temporary computer-readable medium as described in C28, further comprising the features described above. [C30] The first network device comprises a central node, the second network device comprises a serving cell, and the non-temporary computer-readable medium is Program code for receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, Program code for making predictions based on the first request message, Program code for sending a second request message to the Aggressor Neighbor Cell requesting resource protection, The second network device includes program code for sending a response message indicating the protected resource, A non-temporary computer-readable medium as described in C28, further comprising the features described above.

Claims

1. A method of wireless communication using a first network device, Using a neural network trained on UE Channel Information (CSI) Reference Signal (CSI-RS) measurement reports, predict the inter-cell downlink interference experienced by a UE based on the UE's location. To reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, and to communicate with a second network device, A method that includes [a certain feature].

2. The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the method is The first network device selects the UE such that the predicted inter-cell downlink interference exceeds a predetermined threshold, Sending a request message to the second network device, The method according to claim 1, further comprising:

3. The aforementioned request message indicates a beam that causes excessive interference, or The request message indicates the time and / or frequency resources to be protected, or The request message indicates the amount of resources to be protected, and the amount is determined based on the traffic demand of the UE, or The request message indicates the index of the selected resource set within a predetermined list of resource sets, or The system further comprises receiving a response message indicating acceptance of the proposal indicated by the request message, or It further includes receiving response messages that offer alternative suggestions for different sets of resources, or The method according to claim 2, further comprising updating the request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE.

4. The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the method is Receiving a request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, To make a prediction based on the aforementioned request message, Sending a response message to the second network device, Furthermore, The method according to claim 1, further comprising receiving updates from the second network device regarding the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE.

5. The first network device comprises a central node, the second network device comprises a serving cell, and the method is Receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, To make a prediction based on the first request message, Send a second request message to the Aggressor Neighbor Cell requesting resource protection, Sending a response message to the second network device indicating the protected resource, Furthermore, The method according to claim 1, further comprising updating the forecast based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE.

6. A device for wireless communication by a first network device, A means for predicting spatial downlink cell interference experienced by a UE based on the location of the UE, using a neural network trained on UE channel information (CSI) reference signal (CSI-RS) measurement reports, Means for communicating with a second network device in order to reduce inter-spatial downlink cell interference in the direction of the UE by protecting resources across a selected set of resources, A device equipped with the following features.

7. The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the device comprises The first network device provides means for selecting the UE such that the predicted spatial downlink cell interference exceeds a predetermined threshold, Means for sending a request message to the second network device, The apparatus according to claim 6, further comprising:

8. Means for receiving a response message indicating acceptance of the proposal indicated by the request message, or A means for receiving a response message indicating alternative suggestions for different sets of resources, Means for updating the request message in response to an updated forecast based on an updated UE location, updated channel conditions for the UE, and / or updated traffic demand for the UE. The apparatus according to claim 7, further comprising:

9. The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the device comprises Means for receiving a request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, Means for making predictions based on the aforementioned request message, Means for sending a response message to the second network device, Furthermore, The apparatus according to claim 6, further comprising means for receiving updates from the second network device regarding the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE.

10. The first network device comprises a central node, the second network device comprises a serving cell, and the device comprises Means for receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource demand for the UE, Means for making a prediction based on the first request message, Means for sending a second request message to Aggressor Neighbor Cell requesting resource protection, The second network device has means for sending a response message indicating the protected resource, Furthermore, The apparatus according to claim 6, further comprising means for updating the forecast based on updated UE locations, updated channel conditions for the UE, and / or updated resource demand for the UE.

11. Processor and The memory coupled to the aforementioned processor, Instructions stored in the aforementioned memory, A first network device comprising, where, when the instruction is executed by the processor, the first network device, Using a neural network trained on UE Channel Information (CSI) Reference Signal (CSI-RS) measurement reports, predict the inter-cell downlink interference experienced by a UE based on the UE's location. To reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, and to communicate with a second network device, A first network device capable of performing the following actions.

12. The first network device described above is The second network device comprises a serving cell, and the second network device comprises a potentially interfering neighbor cell, and the instruction is given to the first network device, Selecting the UE such that the predicted inter-cell downlink interference exceeds a predetermined threshold, Sending a request message to the second network device, To have them do that further, or The second network device includes a neighbor cell, and the second network device includes a serving cell, and the instruction is given to the first network device, Receiving a request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, To make a prediction based on the aforementioned request message, Sending a response message to the second network device, The first network device according to claim 11, which further enables the following:

13. The first network device comprises a central node, the second network device comprises a serving cell, and the instruction is given to the first network device, Receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, To make a prediction based on the first request message, Send a second request message to the Aggressor Neighbor Cell requesting resource protection, Sending a response message to the second network device indicating the protected resource, Let them do it further, The instruction causes the first network device to further update the forecast based on the updated UE location, the updated channel conditions for the UE, and / or the updated resource demand for the UE, according to claim 11.

14. A non-temporary computer-readable recording medium that stores program code, wherein the program code is executed by the processor of a first network device. A program code for predicting spatial inter-cell downlink interference experienced by a UE, based on the location of the UE, using a neural network trained on UE Channel Information (CSI) Reference Signal (CSI-RS) measurement reports, and Program code for communicating with a second network device in order to reduce inter-spatial cell downlink interference in the direction of the UE by protecting resources across a selected set of resources, A non-temporary computer-readable recording medium comprising the following features.

15. The first network device described above is The neighbor cell is provided, the second network device is provided with a serving cell, and the non-temporary computer-readable recording medium is, Program code for receiving request messages from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, Program code for making predictions based on the aforementioned request message, Program code for sending a response message to the second network device, To further include, or, The system comprises a central node, the second network device comprises a serving cell, and the non-temporary computer-readable recording medium is Program code for receiving a first request message from the second network device indicating the location of the UE, the UE interference tolerance threshold, and / or the resource requirements for the UE, Program code for making predictions based on the first request message, Program code for sending a second request message to the Aggressor Neighbor Cell requesting resource protection, The second network device includes program code for sending a response message indicating the protected resource, A non-temporary computer-readable recording medium according to claim 14, further comprising the above.

Images