JP2024508437A - Spatial intercell interference aware downlink coordination - Google Patents

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 includes communicating with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across the selected resource set. [Selection diagram] Figure 9

Description

priority claim

Cross-reference of related applications
[0001] This application relates to U.S. Provisional Patent Application No. 63/155, filed March 2, 2021, entitled "SPATIAL INTER-CELL INTERFERENCE AWARE DOWNLINK COORDINATION," the entire disclosure of which is expressly incorporated by reference. 635, U.S. Patent Application No. 17/675,980, filed February 18, 2022, entitled "SPATIAL INTER-CELL INTERFERENCE AWARE DOWNLINK COORDINATION."

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

[0003] Wireless communication systems are widely deployed to provide a variety of telecommunications services such as telephone, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access techniques that can support communication with multiple users by sharing available system resources (eg, bandwidth, transmit power, etc.). Examples of such multiple access technologies are 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 Includes 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 enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the 3rd Generation Partnership Project (3GPP).

[0004] A wireless communication network may include a number of base stations (BS) that can support communication for a number of user equipment (UE). User equipment (UE) may communicate with a base station (BS) via the downlink and uplink. The downlink (or forward link) refers to the communication link from the BS to the UE, and the uplink (or reverse link) refers to the communication link from the UE to the BS. As explained in more detail, a BS may be referred to as a Node B, gNB, access point (AP), radio head, transmit/receive point (TRP), new radio (NR) BS, 5G Node B, etc.

[0005] The multiple access techniques described above have been adopted in various telecommunications standards to provide a common protocol that allows different user equipment to communicate on a city, national, regional, or even global scale. . New Radio (NR), sometimes referred to as 5G, is a set of extensions to the LTE mobile standard promulgated by the 3rd Generation Partnership Project (3GPP). NR improves spectral efficiency, lowers costs, improves service, utilizes new spectrum, and orthogonal frequency division multiplexing with cyclic prefix (CP) on the downlink (DL). (OFDM) (CP-OFDM) to implement CP-OFDM and/or SC-FDM (also known as, e.g., Discrete Fourier Transform Spread OFDM (DFT-s-OFDM)) on the uplink (UL). to better support mobile broadband Internet access by supporting beamforming, multiple-input multiple-output (MIMO) antenna technology, and carrier aggregation. Designed.

[0006] An artificial neural network may comprise an interconnected group of artificial neurons (eg, a neuron model). An artificial neural network can be represented as a computing device or a method to be performed by a computing device. Convolutional neural networks, such as deep convolutional neural networks, are a type of feedforward artificial neural network. Convolutional neural networks may include layers of neurons that may be organized in tiled receptive fields. It would be desirable to apply neural network processing to wireless communications to achieve higher efficiency.

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

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

[0009] The first network device includes a processor and memory coupled to the processor. The first network device also includes instructions stored in memory. When the instructions are executed by the processor, the first network device is operable to predict spatial inter-cell downlink interference experienced by the UE. The first network device is also operable to communicate with the second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across the selected resource set. be.

[0010] A non-transitory computer readable medium having program code recorded thereon is executed by a processor of a first network device. The non-transitory computer-readable medium includes program code for predicting spatial inter-cell downlink interference experienced by a UE. The non-transitory computer-readable medium carries program code for communicating with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across a selected set of resources. Also included.

[0011] The aspects are generally described herein with reference to the accompanying drawings and specification, and as illustrated by the accompanying drawings and specification, methods, apparatus, systems, computer program products, non-transitory computer Includes readable media, user equipment, base stations, wireless communication devices, and processing systems.

[0012] The foregoing has outlined rather broadly the features and technical advantages of examples according to this disclosure in order that the detailed description that follows may be better understood. Additional features and advantages are described. The concepts and embodiments disclosed may be readily utilized as a basis for modifying or designing other structures to carry out the same objectives of this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The nature of the disclosed concepts, both their organization and method of operation, together with associated advantages, will be better understood upon consideration of the following description in conjunction with the accompanying figures. Each of the figures is provided for purposes of illustration and explanation, and not as a definition of a limitation on the scope of the claims.

[0013] In order that the features of the present disclosure may be understood in detail, a specific description may be obtained by reference to the embodiments, some of which are illustrated in the accompanying drawings. However, since the description may lead to other equally valid aspects, the accompanying drawings illustrate only some aspects of the disclosure and therefore should not be considered as limiting the scope of the disclosure. Please note. The same reference numbers in different drawings may identify the same or similar elements.

[0014] FIG. 1 is a block diagram conceptually illustrating an example wireless communication network, in accordance with various aspects of the present disclosure. [0015] FIG. 1 is a block diagram conceptually illustrating an example of a base station communicating with user equipment (UE) in a wireless communication network, in accordance with various aspects of the present disclosure. [0016] FIG. 3 illustrates an example implementation of designing a neural network using a system-on-chip (SOC) that includes a general-purpose processor, in accordance with certain aspects of the present disclosure. [0017] FIG. 2 is a diagram illustrating a neural network, according to aspects of the present disclosure. FIG. 2 is a diagram illustrating a neural network, according to aspects of the present disclosure. FIG. 2 is a diagram illustrating a neural network, according to aspects of the present disclosure. [0018] FIG. 2 illustrates an example deep convolutional network (DCN) in accordance with aspects of this disclosure. [0019] FIG. 2 is a block diagram illustrating an example deep convolutional network (DCN) in accordance with aspects of this disclosure. [0020] FIG. 2 illustrates a communication network in which the spatial interference experienced by user equipment is based on downlink transmission beams from neighbor base stations to neighbor user equipment (UE), in accordance with aspects of the present disclosure. FIG. 2 illustrates a communication network in which the spatial interference experienced by user equipment is based on downlink transmission beams from neighbor base stations to neighbor user equipment (UE), in accordance with aspects of the present disclosure. [0021] FIG. 2 is an illustration of a communication network illustrating signal strength measurements of downlink transmit beams from neighbor base stations to enable spatial inter-cell interference-aware downlink coordination in accordance with aspects of the present disclosure. [0022] FIG. 2 is a block diagram of a network that includes a neural processing engine configured to enable spatial inter-cell interference-aware downlink coordination in accordance with aspects of the present disclosure. [0023] FIG. 3 is a timing diagram illustrating an example process, e.g., implemented by a network, for spatial inter-cell interference-aware downlink coordination in a serving cell, in accordance with various aspects of this disclosure. [0024] FIG. 3 is a timing diagram illustrating an example process, e.g., implemented by a network, for spatial inter-cell interference-aware downlink coordination in neighboring cells, in accordance with various aspects of this disclosure. [0025] FIG. 3 is a timing diagram illustrating an example process, e.g., performed by a device, for spatial inter-cell interference-aware downlink coordination at a central node, in accordance with various aspects of this disclosure. [0026] FIG. 3 is a flowchart illustrating an example process performed, eg, by a network device, for spatial inter-cell interference-aware downlink coordination in accordance with various aspects of this disclosure.

[0027] Various aspects of the disclosure are described more fully below with reference to the accompanying drawings. This disclosure may, however, be embodied in many different forms and should not be construed as limited to any specific structure or functionality presented throughout this 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, the scope of this disclosure covers any aspect of this disclosure, whether implemented independently or in combination with other aspects of this disclosure. Those skilled in the art will appreciate that this is true. For example, an apparatus may be implemented or a method practiced using any number of the described aspects. Moreover, the scope of the disclosure extends to such devices or methods that are implemented using other structures, features, or structures and features in addition to or in addition to the various aspects of the disclosure described. shall be covered. It is to be understood that any aspect of the disclosed disclosure may be implemented by one or more elements of a claim.

[0028] Several aspects of telecommunications systems are then presented with reference to various devices and techniques. These devices and techniques are described in the detailed description below and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). is shown. These elements may be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the particular application and design constraints imposed on the overall system.

[0029] Although aspects of the present disclosure may be described using terminology commonly associated with 5G and later wireless technologies, aspects of the present disclosure may be described using terminology commonly associated with 5G and later wireless technologies, such as 3G and/or 4G technologies, as well as other technologies, including 3G and/or 4G technologies. Note that it can be applied in generation-based communication systems.

[0030] Inter-cell interference can result in signal (eg, signal-to-interference-plus-noise ratio (SINR)) degradation for users. Signal degradation to the user can be particularly significant when the user is at the cell edge. Furthermore, with the introduction of massive multiple-input multiple-output (MIMO) antennas in next-generation Node Bs (gNBs), this inter-cell interference can lead to significant SINR degradation for users. For example, narrow downlink transmit beams are highly directional and highly variable over time, which can result in SINR degradation. In particular, highly directional interference at the cell edge can reduce data rates and negatively impact user experience. Furthermore, the high variability of interference makes it more difficult to implement link adaptation, such as predicting supportable modulation and coding schemes (MCS). This can be difficult for latency sensitive applications with limited delay budgets.

[0031] In some aspects of this disclosure, a neural network is trained to infer the impact of a potential transmit beam of a neighbor base station (eg, gNB) on a potential victim user equipment (UE). In these aspects of the present disclosure, a 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 the disclosure, a database stores information regarding the impact of potential transmit beams of neighbor base stations (eg, gNBs) on potential victim UEs. In these aspects of the present disclosure, the database includes UE channel state information (CSI) reference signals (CSI) to enable database lookups to determine potential effects from neighbor base stations on potential victim UEs. - RS) Stores measurement reports, beam information and UE location.

[0032] Once the neural network is trained to infer the influence of the neighbor base station's transmit beam on the victim UE, the network device (eg, gNB) coordinates with the neighbor base station. In these aspects of the present disclosure, network device coordination may prohibit communication of downlink transmit beams by neighbor base stations during the time/frequency resources used to serve the victim UE. For example, a first user equipment (UE1) may experience significant interference from a downlink transmit beam k of a neighbor base station (gNB2). In this example, spatial inter-cell interference is mitigated when neighbor base station gNB2 avoids transmitting energy in the direction of downlink transmission beam k on the resources serving the first user equipment.

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

[0034] In these aspects of the present disclosure, the serving cell sends a request message to the potentially interfering neighbor cell for each potential victim subset of the UE. The request message may include a forbidden list of beam indices that potentially interfering neighbor cells are requested to avoid. Further, the request message may indicate the requested time/frequency resources (eg, time slots/resource blocks (RBs)) for which protection is requested. In some implementations, a predefined set of time/frequency resources is configured for every cell, so the signaling may simply refer to the index of the proposed set of resources. Alternatively, time/frequency resources are left to neighbor cells to decide.

[0035] In some aspects of this disclosure, learning spatial inter-cell downlink interference and predicting a victim subset of a UE occurs in an interfering cell, sometimes referred to as an aggressor neighbor cell. Implemented. In these aspects of the present disclosure, the 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 the aggressor neighbor cell(s). The request message may indicate (1) the location of the vulnerable UE(s), (2) the UE interference tolerance threshold, and/or (3) a subset of the needs for protected resources. In other aspects of this disclosure, an indication of the victim UE's traffic load is provided to represent the desired amount of protected resources.

[0036] The request message sent by the serving cell may omit resource requirements, which is optional. When the request message omits resource demand, the resources to be protected are determined by the neighbor cells. Additionally, there may be a predefined set of time/frequency resources configured for each cell. In this configuration, the request message signaling may simply refer to an index of the proposed set of resources that satisfies the UE resource demands.

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

[0038] FIG. 1 is a diagram illustrating a network 100 in which aspects of the present disclosure may be implemented. Network 100 may be a 5G network or NR network, or some other wireless network, such as an LTE network. Wireless network 100 may include several BSs 110 (shown as BS 110a, BS 110b, BS 110c, and BS 110d) and other network entities. A BS is an entity that communicates with user equipment (UE) and may also be referred to as 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 for a particular geographic area. In 3GPP, the term "cell" can refer to the coverage area of a BS and/or the BS subsystem serving this coverage area, depending on the context in which the term is used.

[0039] A BS may provide communication coverage to macro cells, pico cells, femto cells, and/or another type of cell. A macro cell may cover a relatively large geographic area (eg, several kilometers radius) and may allow unrestricted access by UEs that subscribe to the service. A picocell may cover a relatively small geographic area and may allow unrestricted access by UEs subscribing to the service. A femtocell may cover a relatively small geographic area (e.g., a home) and may allow limited access by UEs that have an association with the femtocell (e.g., UEs in a closed subscriber group (CSG)). . A BS for a macro cell is sometimes called a macro BS. A BS for pico cells is sometimes called a pico BS. A BS for a femto cell may be called a femto BS or a home BS. In the example shown in FIG. 1, BS 110a may be a macro BS for macro cell 102a, BS 110b may be a pico BS for pico cell 102b, and BS 110c may be a femto BS for femto cell 102c. A BS may support one or more (eg, three) cells. The terms "eNB", "base station", "NR BS", "gNB", "TRP", "AP", "Node B", "5G NB", and "cell" may be used interchangeably. .

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

[0041] Wireless network 100 may also include relay stations. A relay station is an entity that can receive data transmissions from an upstream station (eg, a BS or UE) and forward the data transmissions to a downstream station (eg, a UE or BS). A relay station may also be a UE that can relay transmissions for other UEs. In the example shown in FIG. 1, relay station 110d may communicate with macro BS 110a and UE 120d to facilitate communication between BS 110a and UE 120d. A relay station is sometimes called a relay BS, relay base station, relay, etc.

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

[0043] Network controller 130 may couple to a set of BSs and provide coordination and control of these BSs. Network controller 130 may communicate with the BS via backhaul. BSs may also communicate with each other directly or indirectly via wireless or wireline backhaul, for example.

[0044] UEs 120 (eg, 120a, 120b, 120c) may be distributed throughout wireless network 100, and each UE may be fixed or mobile. A UE may also be referred to as an access terminal, terminal, mobile station, subscriber unit, station, etc. The UE may be a cellular phone (e.g., a smartphone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet, a camera, a gaming device, netbooks, smartbooks, ultrabooks, medical devices or equipment, biosensors/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 radio), vehicle components or sensors, smart meters/sensors, industrial manufacturing equipment, global positioning system devices, or communicating via wireless or wired media. Any other suitable device configured to do so may be used.

[0045] Base station 110 may include a neural processing engine 150. Although only one base station 110a is shown as including neural processing engine 150 for sake of brevity, neighboring base stations may also include neural processing engine 150. Neural processing engine 150 may predict spatial inter-cell downlink interference experienced by the UE. Neural processing engine 150 may also communicate with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across the selected resource set.

[0046] Network controller 130 may include neural processing engine 160. Neural processing engine 160 may predict spatial inter-cell downlink interference experienced by the UE. Neural processing engine 160 may also communicate with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across the selected resource set.

[0047] Some UEs may be considered machine type communication (MTC) UEs or evolved or enhanced machine type communication (eMTC) UEs. MTC UEs and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, location tags, etc. that may communicate with a base station, another device (e.g., a remote device), or some other entity. . A wireless node may provide connectivity for or to a network (eg, a wide area network, such as the Internet or a cellular network), for example, via a wired or wireless communication link. Some UEs may be considered Internet of Things (IoT) devices and/or may be implemented as NB-IoT (Narrowband Internet of Things) devices. Some UEs may be considered customer premises equipment (CPE). UE 120 may be included within a housing that stores components of UE 120, such as processor components, memory components, and the like.

[0048] Generally, any number of wireless networks may be deployed in a given geographic area. Each wireless network may support a particular RAT and operate on one or more frequencies. RAT is sometimes referred to as radio technology, air interface, etc. Frequency is sometimes called carrier, frequency channel, etc. Each frequency may support a single RAT in a given geographic area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks may be deployed.

[0049] In some aspects, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) (e.g., without using base station 110 as an intermediary to communicate with each other) One or more sidelink channels may be used to communicate directly. For example, the UE 120 may communicate peer-to-peer (P2P) communications, device-to-device (D2D) communications, vehicle-to-anything (V2X) (which may include, for example, vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, etc.). They may communicate using protocols, mesh networks, and the like. In this case, UE 120 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 communicate via downlink control information (DCI), radio resource control (RRC) signaling, media access control-control element (MAC-CE), or system information (e.g., system information block (SIB)). ).

[0050] As mentioned above, FIG. 1 is provided by way of example only. Other examples may differ from those described with respect to FIG.

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

[0052] At the base station 110, a transmit processor 220 receives data from the data source 212 for one or more UEs, and receives data for each UE based at least in part on channel quality indicators (CQIs) received from the UEs. selecting one or more modulation and coding schemes (MCS) for each UE and processing the data for each UE based at least in part on the selected MCS(s) for that UE; (e.g., encoding and modulation) and provide data symbols for all UEs. Reducing MCS reduces throughput but increases transmission reliability. Transmit processor 220 also processes system information (e.g., for semi-static resource partitioning information (SRPI), etc.) and control information (e.g., CQI requests, grants, upper layer signaling, etc.), and generates overhead symbols and control symbols. can be provided. 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)). . A transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., precoding) on data symbols, control symbols, overhead symbols, and/or reference symbols when applicable; T output symbol streams may be provided to T modulators (MOD) 232a through 232t. Each modulator 232 may process a respective output symbol stream (eg, for orthogonal frequency division multiplexing (OFDM), etc.) to obtain an output sample stream. Each modulator 232 may further process (eg, convert to analog, amplify, filter, and upconvert) the output sample stream to obtain a downlink signal. T downlink signals from modulators 232a through 232t may be transmitted via T antennas 234a through 234t, respectively. According to various aspects described in more detail below, a synchronization signal may be generated using location encoding to convey additional information.

[0053] At UE 120, antennas 252a-252r may receive downlink signals from base station 110 and/or other base stations and may provide received signals to demodulators (DEMOD) 254a-254r, respectively. Each demodulator 254 may condition (eg, filter, amplify, downconvert, and digitize) the received signal to obtain input samples. Each demodulator 254 may further process the input samples (eg, for OFDM, etc.) to obtain received symbols. A MIMO detector 256 may obtain received symbols from all R demodulators 254a-254r, perform MIMO detection on the received symbols if applicable, and provide detected symbols. Receive processor 258 processes (e.g., demodulates and decodes) the detected symbols, provides decoded data for UE 120 to data sink 260, and decoded control and system information to controller/processor 280. can be provided. A channel processor may determine reference signal received power (RSRP), received signal strength indicator (RSSI), reference signal received quality (RSRQ), channel quality indicator (CQI), and the like. In some aspects, one or more components of UE 120 may be included in a housing.

[0054] On the uplink, at the UE 120, a transmit processor 264 receives data from a data source 262 and control information (e.g., for reporting comprising RSRP, RSSI, RSRQ, CQI, etc.) from a controller/processor 280. and may receive and process. Transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from transmit processor 264 are precoded by a TX MIMO processor 266, if applicable, further processed by modulators 254a-254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to the base. may be transmitted to station 110. At base station 110, uplink signals from UE 120 and other UEs are received by antenna 234, processed by demodulator 254, detected by MIMO detector 236 if applicable, and decoded by the UE 120. may be further processed by receive processor 238 to obtain received data and control information. Receive processor 238 may provide decoded data to data sink 239 and decoded control information to controller/processor 240. Base station 110 may include a communications unit 244 and communicate with network controller 130 via communications unit 244 . Network controller 130 may include a communications unit 294, a controller/processor 290, and memory 292.

[0055] Controller/processor 240 of base station 110 of FIG. 2 and/or controller/processor 280 of UE 120 may provide location-based downlink interference assistance information for UE 120, as described in more detail elsewhere. One or more techniques related to machine learning may be implemented to make predictions. For example, controller/processor 280 of UE 120 of FIG. 2 may implement or direct the operation of the process of FIG. 8 and/or other processes as described, for example. Additionally, controller/processor 240 of base station 110 of FIG. 2 may implement or direct the operations of the processes of FIGS. 9-12 and/or other processes as described, for example. Memories 242 and 282 may store data and program codes for base station 110 and UE 120, respectively. Scheduler 246 may schedule UEs for data transmission on the downlink and/or uplink.

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

[0057] As mentioned above, FIG. 2 is provided as an example only. Other examples may differ from that described with respect to FIG.

[0058] In some cases, different types of devices supporting different types of applications and/or services may coexist in a cell. Examples of different types of devices include UE handsets, customer premises equipment (CPE), vehicles, Internet of Things (IoT) devices, and so on. Examples of different types of applications include Ultra Reliable Low Latency Communications (URLLC) applications, Massive Machine Type Communications (mMTC) applications, Enhanced Mobile Broadband (eMBB) applications, Vehicle-to-Everything (V2X) applications, and so on. Furthermore, in some cases a single device may support different applications or services at the same time.

[0059] FIG. 3 illustrates a system-on-chip (SOC) that may include a central processing unit (CPU) 302 or a multi-core CPU configured to generate gradients for neural network training, according to some aspects of the present disclosure. ) 300 is illustrated. SOC 300 may be included in base station 110 or UE 120. Variables (e.g., neural signals and synaptic weights), system parameters associated with computing devices (e.g., neural networks with weights), delays, frequency bin information, and task information are stored in memory associated with neural processing unit (NPU) 308. stored in a memory block associated with a CPU 302, stored in a memory block associated with a graphics processing unit (GPU) 304, or associated with a digital signal processor (DSP) 306. , may be stored in memory block 318, or may be distributed across multiple blocks. Instructions executed in CPU 302 may be loaded from program memory associated with CPU 302 or from memory block 318 .

[0060] The SOC 300 also includes additional processing blocks adapted for specific functionality, such as GPU 304, DSP 306, and 5th Generation (5G) connectivity, 4th Generation Long Term Evolution (4G LTE) connectivity, Wi-Fi Connectivity block 310, which may include Bluetooth connectivity, USB connectivity, Bluetooth connectivity, etc., and a multimedia processor 312, which may detect and recognize gestures, for example. In one implementation, the NPU is implemented in a CPU, DSP, and/or GPU. SOC 300 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.

[0061] SOC 300 may be based on the ARM instruction set. In one aspect of the present disclosure, instructions loaded into general-purpose processor 302 include program code for predicting spatial inter-cell downlink interference experienced by a UE and direction of the UE by conserving resources across a selected set of resources. and program code for communicating with a second network device to reduce spatial inter-cell downlink interference in a computer.

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

[0063] Deep learning architectures may learn hierarchies of features. For example, when presented with visual data, the first layer may learn to recognize relatively simple features in the input stream, such as edges. In another example, when presented with auditory data, the first layer may learn to recognize spectral power at particular frequencies. A second layer that takes the output of the first layer as input may be trained 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, upper layers may learn to represent complex shapes in visual data, or words in auditory data. Further higher layers may learn to recognize common visual objects or spoken phrases.

[0064] Deep learning architectures may work particularly well when applied to problems that have a natural hierarchical structure. For example, motor vehicle classification may benefit from first learning to recognize wheels, windshields, and other features. These features can be combined in higher layers in different ways to recognize cars, trucks, and airplanes.

[0065] Neural networks may be designed with various connectivity patterns. In a feedforward network, information is passed from lower layers to higher layers, with each neuron in a given layer communicating to neurons in the higher layer. As explained above, hierarchical representations may be accumulated in successive layers of the feedforward network. Neural networks may also have recurrent or (also called top-down) feedback connections. With recurrent coupling, the output from a neuron in a given layer may be communicated to another neuron in the same layer. Recurrent architectures can help recognize patterns across two or more of the input data chunks that are sequentially delivered to the neural network. The connections from neurons in a given layer to neurons in lower layers are called feedback (or top-down) connections. Networks with many feedback connections can be useful when recognition of high-level concepts can help discriminate certain low-level features of the input.

[0066] Connections between layers of a neural network may be fully connected or locally connected. FIG. 4A shows an example of a fully connected neural network 402. In the fully connected neural network 402, a neuron in the first layer sends its output to every neuron in the second layer such that each neuron in the second layer receives input from every neuron in the first layer. Can communicate. FIG. 4B shows an example of a locally connected neural network 404. In locally coupled neural network 404, neurons in a first layer may be coupled to a limited number of neurons in a second layer. More generally, the locally connected layers of the locally connected neural network 404 may be configured such that each neuron in the layer has the same or similar connectivity pattern, but with connection strengths that may have different values. (For example, 410, 412, 414, and 416). The connectivity pattern of local connections is spatially variable in the upper layers because upper layer neurons in a given region may receive inputs that are adjusted through training to the properties of a restricted portion of the total input to the network. can give rise to distinct receptive fields.

[0067] An example of a locally coupled neural network is a convolutional neural network. FIG. 4C shows an example of convolutional neural network 406. Convolutional neural network 406 may be configured such that connection strengths associated with the inputs for each neuron in the second layer are shared (eg, 408). Convolutional neural networks may be suitable for problems where the spatial location of the input is meaningful.

[0068] One type of convolutional neural network is a deep convolutional network (DCN). FIG. 4D shows a detailed example of a DCN 400 designed to recognize visual features from an image 426 input from an image capture device 430, such as an onboard camera. The DCN 400 of this example may be trained to identify traffic signs and numbers provided on the traffic signs. Of course, DCN 400 may be trained for other tasks, such as identifying lane markings or identifying traffic lights.

[0069] DCN 400 may be trained using supervised learning. During training, DCN 400 may be presented with an image, such as image 426 of a speed limit sign, and then a forward pass may be calculated to generate output 422. DCN 400 may include a feature extraction section and a classification section. Upon receiving image 426, convolution layer 432 may apply a convolution kernel (not shown) to image 426 to generate a first set of feature maps 418. As an example, the convolution kernel for convolution layer 432 may be a 5x5 kernel that produces a 28x28 feature map. In this example, four different feature maps were generated in the first set of feature maps 418, so four different convolution kernels were applied to the image 426 in the convolution layer 432. Convolution kernels are sometimes called filters or convolution filters.

[0070] The 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 14x14, is smaller than the size of the first set of feature maps 418, such as 28x28. The reduced size provides similar information to subsequent layers while reducing memory consumption. The second set of feature maps 420 is passed through one or more subsequent convolutional layers (not shown) to generate one or more subsequent sets of feature maps (not shown). It can be further convolved.

[0071] In the example of FIG. 4D, a second set of feature maps 420 is convolved to generate a first feature vector 424. Additionally, the first feature vector 424 is further convolved to generate a second feature vector 428. Each feature of second feature vector 428 may include a number corresponding to a possible feature of image 426, such as "sign", "60", and "100". A softmax function (not shown) may convert numbers in second feature vector 428 to probabilities. Therefore, output 422 of DCN 400 is the probability that image 426 includes one or more features.

[0072] In this example, the probabilities at output 422 for "label" and "60" are "30", "40", "50", "70", "80", "90", and "100". etc., is higher than the probability of the other output 422. Prior to training, the output 422 produced by DCN 400 may be inaccurate. Therefore, an error may be calculated between output 422 and the target output. The target output is the ground truth of image 426 (eg, "Sign" and "60"). The weights of DCN 400 may then be adjusted such that output 422 of DCN 400 is more closely matched to the target output.

[0073] To adjust the weights, the learning algorithm may calculate a gradient vector for the weights. The slope may indicate the amount by which the error increases or decreases if the weights are adjusted. In the top layer, the gradient may directly correspond to the value of the weights connecting activated neurons in the penultimate layer and neurons in the output layer. At lower layers, the gradient may depend on the values of the weights and the calculated error gradient at the upper layer. The weights may then be adjusted to reduce the error. This manner of adjusting weights is sometimes called "backpropagation" because it involves a "backward pass" through the neural network.

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

[0075] A deep belief network (DBN) is a probabilistic model that comprises multiple layers of hidden nodes. A DBN may be used to extract a hierarchical representation of a training dataset. The DBN can be obtained by stacking layers of a Restricted Boltzmann Machine (RBM). RBM is a type of artificial neural network that can learn probability distributions over a set of inputs. RBMs are often used in unsupervised learning because RBMs can learn probability distributions in the absence of information about the class into which each input should be categorized. Using a hybrid unsupervised and supervised paradigm, the bottom RBM of a DBN can be trained in an unsupervised manner and act as a feature extractor, and the top RBM can be trained (simultaneously with the input from the previous layer and the target class). distribution) and can be trained in a supervised manner and serve as a classifier.

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

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

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

[0079] The performance of deep learning architectures may 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 improve deep learning performance. A rectified linear unit may reduce the training problem known as vanishing gradient. New training techniques may reduce over-fitting and thus allow larger models to achieve better generalization. Encapsulation techniques can extract data in a given receptive field and further enhance overall performance.

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

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

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

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

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

[0085] As explained above, inter-cell interference can result in signal (eg, signal-to-interference-plus-noise ratio (SINR)) degradation for users. Signal degradation to the user can be particularly significant when the user is at the cell edge. Furthermore, with the introduction of massive multiple-input multiple-output (MIMO) antennas in next-generation base stations (eg, 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 user experience. Furthermore, the high variability of interference makes it more difficult to implement link adaptation, such as predicting supportable modulation and coding schemes (MCS). This is difficult for latency sensitive applications with limited delay budgets. This limited delay budget may be insufficient to recover the packet through a hybrid automatic repeat request (HARQ) procedure when the selected modulation and coding scheme (MCS) is not accurate.

[0086] FIGS. 6A and 6B illustrate a communication network in which the spatial interference experienced by a user equipment (UE) is based on a downlink transmission beam from a neighbor base station to a neighbor UE, in accordance with aspects of the present disclosure. As shown in FIG. 6A, in a first interference scenario 600, a first UE 120-1 communicates with a first base station 110-1 over a downlink transmit beam i. Similarly, a second UE 120-2 communicates with neighbor base station 110-2 over downlink transmit beam j. In this example, spatial inter-cell interference from downlink transmit beam j to downlink transmit beam i results in minimal signal degradation (eg, SINR=20 dB) at first UE 120-1.

[0087] FIG. 6B shows a second interference scenario 650 in which the first UE 120-1 communicates with the first base station 110-1 over the downlink transmit beam i. In contrast, second UE 120-2 communicates with neighbor base station 110-2 through downlink transmit beam k that interferes with downlink transmit beam i. In this example, spatial inter-cell interference from downlink transmit beam k to downlink transmit beam i results in significant signal degradation (e.g., SINR = 5 dB) at the first UE 120-1, which -1 degrades the user experience.

[0088] FIG. 7 is a diagram of a communication network 700 illustrating signal strength measurements of downlink transmit beams from neighbor base stations to enable spatial inter-cell interference-aware downlink coordination in accordance with aspects of the present disclosure. be. According to aspects of the present disclosure, a neural network is trained to infer the impact of potential transmit beams of neighbor base stations (eg, gNBs) on potential victim UEs. In this example, victim user equipment (UE ₁ ) 120-1 communicates with serving base station (gNB ₁ ) 110-1 on downlink transmit beam i. Unfortunately, _the victim UE ₁ 120-1 receives _a significant receive interference.

[0089] In this example, spatial inter-cell interference for victim UE ₁ 120-1 is mitigated through coordination with neighbor base station gNB ₂ 110-2. For example, neighbor base station gNB ₂ 110-2 transmits on downlink beam j to avoid transmitting energy in the direction of downlink transmit beam k on the resources serving victim UE ₁ 120-1. It is possible. Aspects of the present disclosure provide a method for transmitting on downlink beam j on the resources used to serve victim UE ₁ 120-1 to avoid interference for victim UE ₁ 110-1. It coordinates with base station gNB ₂ 110-2.

[0090] According to aspects of the present disclosure, a neural network of serving base station gNB ₁ 110-1 infers the impact of a downlink transmit beam of neighbor base station gNB ₂ 110-2 on victim UE ₁ 120-1. will be trained. In these aspects of the present disclosure, serving base station gNB ₁ 110-1 receives downlink transmissions by neighbor base station gNB ₂ 110-2 on the time/frequency resources used to serve victim UE ₁ 120-1. It coordinates with neighbor base station gNB ₂ 110-2 to prohibit communication on beam k. In some configurations, prediction of inter-cell interference is performed using machine learning with a neural processing engine (NPE), for example, as shown in FIG.

[0091] FIG. 8 illustrates 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, in accordance with aspects of the present disclosure. FIG. In aspects of the present disclosure, a database stores information regarding the impact of potential transmit beams of neighbor base stations (eg, gNBs) on potential victim UEs. In these aspects of the present disclosure, the database includes UE channel state information (CSI) reference signals (CSI) to enable database lookups to determine potential effects from neighbor base stations on potential victim UEs. - RS) Stores measurement reports, beam information and UE location.

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

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

[0094] In some aspects of this disclosure, base station 110 periodically sends precoded CSI-RS signals to served UE 120. Served UE 120 may use the received CSI-RS signals to estimate channel conditions. The served UE 120 also uses the received CSI-RS signals to identify the single beam or beam combination that yields the strongest received signal quality (e.g., the strongest beam) to aid in data channel precoding. Can be used. Additionally, CSI-RS signals from other cells may be measured. For example, a 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 uses the measured CSI-RS signals of other cells to identify whether the neighbor cell is stronger than the current serving cell, which may trigger a handover. In practice, the CSI-RS measurements performed by the UE are reported by the UE 120 to the serving cell 110.

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

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

[0097] In some aspects of this disclosure, neural network training is performed at neighbor cell(s), such as neighbor base station gNB ₂ 110-2 shown in FIG. 7. In these aspects of the present disclosure, the serving cell base station gNB ₁ 110-1 sends the UE location information to the neighbor base station gNB ₂ 110-2 to perform neural network training at the neighbor base station gNB ₂ 110-2. 802 and an interference measurement report. In other aspects of the disclosure, training of the neural network is performed at a centralized node. In these aspects of the present disclosure, the serving cell base station gNB ₁ 110-1 provides the centralized node with the UE location 802, serving cell identity (ID), neighbor Send cell ID and interference measurement report.

[0098] Once the neural network is trained to infer the influence of the neighbor base station's transmit beam on the victim UE, the network device (eg, gNB) coordinates with the neighbor base station. In these aspects of the present disclosure, network device cooperation may prevent communication of downlink transmit beams by neighbor base stations on time/frequency resources used to serve the victim UE. For example, as shown in FIG. 7, UE ₁ 120-1 experiences significant interference from downlink transmit beam k of neighbor base station (gNB ₂ ) 110-2. In this example, spatial inter-cell interference causes neighbor base station gNB ₂ 110-2 to transmit energy in the direction of downlink transmit beam k on the resources used to serve UE ₁ 120-1. When avoided, it is relieved.

[0099] According to aspects of the present disclosure, undesirable neighbor cell beams are identified based on several criteria according to a predicted interference-based distribution. For example, the criterion may be a mean or percentile above a predetermined threshold. Additionally, this spatial interference characterization coordinates scheduling between nearby cells, such as neighbor base station gNB ₂ 110-2, to prevent high interference events, as shown in FIGS. 9-11, for example. can be used for

[00100] FIG. 9 illustrates, for example, UEs 120 (120-1, ..., 120-N) and a serving cell 900 for spatial inter-cell interference-aware downlink coordination in a serving cell 900, in accordance with various aspects of the present disclosure. and base stations 110-2, . . . of neighbor cells 950 (950-1, . . . , 950-N). ．． ．． , 110-N.

[00101] In accordance with aspects of the present disclosure, base station 110-1 of serving cell 900 transmits signals in serving cell 900 from different potential downlink transmit beams of neighbor cells 950 (950-1,..., 950-N) Predict potential downlink interference experienced by UEs 120 (120-1,..., 120-N). For example, base station 110-1 of serving cell 900 identifies a subset of served UEs 120 for which the potential negative impact caused by intercell downlink interference from neighbor cell 950 exceeds 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 UE is receiving. For example, UEs that receive delay-sensitive traffic and/or reliable traffic may be selected as part of a potential victim subset of UEs.

[00102] At time t0, base station 110-1 of serving cell 900 sends a request message to potentially interfering neighbor cells 950 for each victim subset of UEs 120. The request message may include a proposal indicating a requested list of beam indices that potentially interfering neighbor cells 950 are requested to avoid. Further, the request message may indicate the requested time/frequency resources (eg, time slots/resource blocks (RBs)) for which protection is requested. For example, the request message may indicate the amount of resources to protect. Base station 110-1 may determine how much bandwidth the vulnerable UE needs, eg, 1/4 of the allocated resources. In some implementations, a predefined set of time/frequency resources is configured for each cell, so the signaling of the request message at time t0 may simply refer to the index of the proposed set of resources. Alternatively, time/frequency resource selection is left as a decision for neighbor cell 950.

[00103] At time t1, base stations 110-2 through N of aggressor neighbor cell 950 respond with response message(s) that are received by base station 110-1 of serving cell 900 at time t1. The response message may be an acceptance of the proposal indicated by the request message. For example, the response message may indicate an agreement to limit transmitted energy in the identified beam direction for the mentioned time/frequency resource. Alternatively, the response message may include potential or alternative proposals for time/frequency resources to be protected. For example, the response message received at time t1 may include an alternative proposal for a different set of resources when the proposal (eg, serving proposal) in the request message from serving cell 900 is not accepted.

[00104] The serving cell 900 may periodically repeat the spatial inter-cell downlink interference prediction as the victim UE 120 changes location, channel conditions change, and/or traffic demands change. 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 predictions about the new conditions. Further, at time t3, neighbor cell 950 may respond to the updated request message with an updated response message as well. Once the interference threat for 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 cancellation request message at time t4 when victim UE 120 enters idle mode.

[00105] FIG. 10 illustrates, for example, a UE 120 (120-1,..., 120-N) and a serving cell for spatial inter-cell interference-aware downlink coordination in a neighbor cell 950, in accordance with various aspects of this disclosure. 9 is a timing diagram illustrating an example process performed by base station 110-1 of 900 and base station 110-2 of neighbor cell 950. FIG.

[00106] In aspects of this disclosure, prediction of spatial inter-cell downlink interference is performed in neighbor cells 950, sometimes referred to as aggressor neighbor cells 950. In these aspects of the present 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 the vulnerable UE(s), (2) a UE interference tolerance threshold, and/or (3) a subset of resource demands.

[00107] The request message sent by base station 110-1 of serving cell 900 at time t0 may omit resource requirements, which is optional. When the request message omits resource demands, the resources to be protected 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 certain set of metrics representing the UE's location. Additionally, there may be a predefined set of time/frequency resources configured for each cell. In this configuration, the request message signaling sent at time t0 may simply refer to an index of the proposed set of resources that satisfies the UE resource demands.

[00108] In these aspects of the present disclosure, the base station 110-2 of the aggressor neighbor cell 950, in response to the request message at time t0, determines that the interference from the transmit beam of the aggressor neighbor cell 950 exceeds the UE interference threshold. Predict whether the host will cause a detrimental effect on the victim UE that exceeds the target UE. In response to the predicted adverse impact, at time t1, base station 110-2 of aggressor neighbor cell 950 instructs serving cell 900 to transmit in the prohibited beam direction for the victim UE's requested time/frequency resources. send a response message indicating consent to limit the energy used. Potentially, the response message at time t1 includes a proposal or (if the resource demand is not accepted) an alternative proposal for time/frequency resources for the protected UE, such as a resource set to be protected.

[00109] In some implementations, the base station 110-1 of the serving cell 900 detects the protected UE 120 and the protected UE 120 when the UE 120 changes location, channel conditions change, or traffic demand changes. Periodically assess the location and vulnerability of resources. In response to any of these changed conditions, at time t2, serving cell 900 may send an updated request message with the new conditions. After predicting whether the downlink interference will be harmful to the updated set of vulnerable UEs 120, at time t3, base station 110-2 of aggressor neighbor cell 950 sends an updated response message. Respond to the updated request message by: In this example, once the interference threat to the vulnerable set of UEs 120 disappears, at time t4, base station 110-1 of serving cell 900 may send a cancellation message to aggressor neighbor cell 950 to terminate resource protection.

[00110] FIG. 11 illustrates, for example, UEs 120 (120-1,..., 120-N) and serving cells for spatial inter-cell interference-aware downlink coordination at a central node 960, in accordance with various aspects of this disclosure. 9 is a timing diagram illustrating an example process performed by base station 110-1 of 900, a central node, and base station 110-2 of aggressor neighbor cell 950. FIG.

[00111] In some implementations, prediction may be performed at a central node 960, such as network controller 130. For example, 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 t1, base station 110-1 of serving cell 900 sends a message to central node 960 regarding the identified vulnerable UE. This message may indicate all or a subset of (1) the location of the vulnerable UE(s), (2) the vulnerable UE's interference threshold, and (3) the traffic load. As discussed above, the UE location may include (1) the UE's (x,y,z) coordinates from a positioning source (e.g., geolocation), and/or (2) a metric representing the UE's location within the serving cell 900. may be represented using a combination of sets of . The positioning source may be, for example, a Global Navigation Satellite System (GNSS) location server, a 5G NR location server, or other location server. Further, the set of metrics representing the UE location may include the reference signal received power (RSRP) of the serving cell 900, the serving cell precoder (e.g., the strongest transmit beam direction), the serving cell channel quality indicator (CQI), and/or the serving cell 900 and the UE 120. may include a path loss estimate between Other UE sensor information may also be included in the vulnerable UE message at time t0.

[00112] In operation, the central node 960 predicts whether the degradation caused by interference from the downlink transmit beam of the aggressor neighbor cell 950 to the victim UE 120 exceeds a UE interference threshold. At time t1, the central node 960 sends a cooperation request message to the aggressor neighbor cell 950 when the interference of the neighbor cell downlink transmission beam exceeds the UE interference threshold. The request message may include a proposal to protect the UE by limiting the transmitted energy in the specified beam direction for the requested time/frequency resources referenced by the request message. In response, at time t2, base station 110-2 of aggressor neighbor cell 950 sends a response message to 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 suggest an alternative plan to protect the UE. At time t3, central node 960 sends a response message to serving cell 900 that may indicate the set of protected resources for the protected UE.

[00113] In some implementations, the central node 960 periodically assesses the location and vulnerability of the protected UE(s) and protected resources. The periodic evaluation may determine whether a change in the UE's location, the UE's channel conditions, and/or the traffic demand for the UE is detected. In response to the detected change, at time t4, central node 960 may send an updated request message to aggressor neighbor cell 950 based on the changed conditions. In response, at time t5, base station 110-2 of aggressor neighbor cell 950 may respond to the updated request message with an updated response message indicating the updated protected resources. At time t6, central node 960 sends a response message to serving cell 900 that may inform base station 110-1 of the updated set of protected resources.

[00114] Once the interference threat disappears, at time t7, serving cell 900 may send a cancellation message to central node 960 and trigger a termination message to terminate resource protection at time t8. Some implementations including a central node may be beneficial when multiple aggressor neighbor cells are potentially causing interference to the victim UE.

[00115] FIG. 12 is a flowchart illustrating an example process 1200, eg, performed by a network device, for neural network-based spatial inter-cell interference learning in accordance with various aspects of this disclosure. The example process 1200 is an example of a network extension for neural network-based spatial inter-cell interference-aware downlink coordination.

[00116] As shown in FIG. 12, in some aspects the process 1200 includes predicting spatial inter-cell downlink interference experienced by the UE (block 1202). For example, a base station (eg, using controller/processor 240 and/or memory 242) can predict spatial downlink intercell downlink interference. Prediction may be performed at a serving base station, an aggressor base station, or a central node. In some aspects, the prediction is based on the UE's location, UE interference tolerance threshold, and/or resource demand for the UE.

[00117] In some aspects, the process 1200 includes communicating with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across the selected resource set ( 1204). For example, the base station (e.g., using antenna 234, DEMOD/MOD 232, TX MIMO processor 230, transmit processor 220, controller/processor 240, and/or memory 242) can eliminate spatial inter-cell downlink interference in the direction of the UE. can communicate with a second network device to reduce In some aspects, protected resources include prohibited beam indices, time/frequency resources to be protected, and/or amounts of resources to be protected.
Exemplary aspects
[00118] Aspect 1: A method of wireless communication by a first network device, the method comprising: predicting spatial inter-cell downlink interference experienced by the UE; and conserving resources across a selected set of resources. communicating with a second network device to reduce spatial inter-cell downlink interference in a method.

[00119] Aspect 2: The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the method comprises: 2. The method of aspect 1, further comprising selecting a UE whose interference exceeds a predetermined threshold and transmitting a request message to a second network device.

[00120] Aspect 3: The method of aspect 1 or 2, wherein the request message indicates a beam that causes excessive interference.

[00121] Aspect 4: The method of aspect 1 or 2, wherein the request message indicates time/frequency resources to be protected.

[00122] Aspect 5: The method of aspect 1 or 2, wherein the request message indicates an amount of resources to protect, and the amount is determined based on the UE's traffic demand.

[00123] Aspect 6: The method of aspect 1 or 2, wherein the request message indicates an index of the selected resource set within a predetermined list of resource sets.

[00124] Aspect 7: The method of aspect 1 or 2, further comprising receiving a response message indicating acceptance of the proposal indicated by the request message.

[00125] Aspect 8: The method of aspect 1 or 2, further comprising receiving a response message indicating an alternative proposal for a different set of resources.

[00126] Aspect 9: 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 method according to aspect 1 or 2, further comprising:

[00127] Aspect 10: The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the method comprises determining, from the second network device, a location of the UE, a UE interference tolerance threshold, and/or a UE interference tolerance threshold. or any of aspects 1-9, further comprising receiving a request message indicating a resource demand for the UE, making a prediction based on the request message, and sending a response message to a second network device. The method described in.

[00128] Aspect 11: as in any of aspects 1-10, further comprising receiving updates of a UE location, a UE interference tolerance threshold, and/or a resource demand for the UE from the second network device. the method of.

[00129] Aspect 12: The first network device comprises a central node, the second network device comprises a serving cell, and the method comprises determining, from the second network device, a location of a UE, a UE interference tolerance threshold, and/or a or receiving a first request message indicating a resource demand for the UE, making a prediction based on the first request message, and transmitting a second request message requesting resource protection to an aggressor neighbor cell. The method of aspect 1, further comprising: transmitting a response message to the second network device indicating the protected resource.

[00130] Aspect 13: The method of aspect 12 further comprises updating the prediction based on an updated UE location, updated channel conditions for the UE, and/or updated resource demand for the UE. Method described.

[00131] Aspect 14: An apparatus for wireless communication by a first network device, the apparatus comprising means for predicting spatial downlink intercell interference experienced by a UE and conserving resources across a selected set of resources. and means for communicating with a second network device to reduce spatial downlink inter-cell interference in the direction of the UE.

[00132] Aspect 15: The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the apparatus comprises a spatial downlink cell predicted by the first network device. 15. The apparatus of aspect 14, further comprising means for selecting a UE and means for transmitting a request message to a second network device, the UE having inter-interference exceeding a predetermined threshold.

[00133] Aspect 16: The apparatus of aspect 15, further comprising means for receiving a response message indicating acceptance of the proposal indicated by the request message.

[00134] Aspect 17: The apparatus of aspect 15, further comprising means for receiving a response message indicating an alternative proposal for a different set of resources.

[00135] Aspect 18: 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. 16. The apparatus according to aspect 15, further comprising means.

[00136] Aspect 19: The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the apparatus receives information from the second network device about a UE's location, a UE interference tolerance threshold, and/or a UE interference tolerance threshold. or means for receiving a request message indicating resource needs for the UE, means for making a prediction based on the request message, and means for sending a response message to a second network device. 15. The device according to 14.

[00137] Aspect 20: The apparatus of aspect 19, further comprising means for receiving updates of a UE location, a UE interference tolerance threshold, and/or a resource demand for the UE from the second network device.

[00138] Aspect 21: The first network device comprises a central node, the second network device comprises a serving cell, and the apparatus receives information from the second network device about a UE's location, a UE interference tolerance threshold, and/or a UE interference tolerance threshold. or means for receiving a first request message indicating a resource demand for the UE; and means for making a prediction based on the first request message; and a second request requesting resource protection from the aggressor neighbor cell. 15. The apparatus of aspect 14, further comprising means for sending a message and means for sending a response message indicating the protected resource to the second network device.

[00139] Aspect 22: An aspect further comprising means for updating the prediction based on an updated UE location, updated channel conditions for the UE, and/or updated resource demand for the UE. 22. The device according to 21.

[00140] Aspect 23: A first network device comprising a processor, a memory coupled to the processor, and instructions stored in the memory, wherein the instructions, when executed by the processor, a second network device for predicting spatial inter-cell downlink interference experienced by the UE and reducing spatial inter-cell downlink interference in the direction of the UE by conserving resources over a selected resource set; a first network device operable to communicate with the first network device;

[00141] Aspect 24: The first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the instructions provide the first network device with a predicted intercell downlink. 24. The first network device of aspect 23, further comprising selecting a UE whose interference exceeds a predetermined threshold and transmitting a request message to the second network device.

[00142] Aspect 25: The first network device comprises a neighbor cell, the second network device comprises a serving cell, and instructions are provided from the second network device to the first network device, the location of the UE, the UE interference. further causing the second network device to receive a request message indicating an acceptable threshold and/or resource demand for the UE, make a prediction based on the request message, and send a response message to the second network device. , the first network device according to aspect 23.

[00143] Aspect 26: The first network device comprises a central node, the second network device comprises a serving cell, and instructions are sent to the first network device from the second network device, the location of the UE, the UE interference. receiving a first request message indicating a tolerance threshold and/or a resource demand for the UE; and making a prediction based on the first request message; 24. The first network device of aspect 23, further causing the second network device to send a request message of 2 and to send a response message indicating the resource to be protected.

[00144] Aspect 27: Instructions direct the first network device to make a prediction based on an updated UE location, updated channel conditions for the UE, and/or updated resource demands for the UE. 27. The first network device of aspect 26, further causing updating to occur.

[00145] Aspect 28: A non-transitory computer readable medium having program code recorded thereon, the program code being executed by a processor of a first network device for predicting spatial inter-cell downlink interference experienced by a UE. a non-transitory network device comprising: program code; and program code for communicating with a second network device to reduce spatial inter-cell downlink interference in the direction of the UE by conserving resources across a selected set of resources. computer readable medium.

[00146] Aspect 29: The first network device comprises a neighbor cell, the second network device comprises a serving cell, and the non-transitory computer-readable medium receives information from the second network device, the location of the UE, the UE interference tolerance. Program code for receiving a request message indicating a threshold and/or resource demand for a UE, making a prediction based on the request message, and sending a response message to a second network device. 30. The non-transitory computer-readable medium of aspect 28, further comprising program code.

[00147] Aspect 30: The first network device comprises a central node, the second network device comprises a serving cell, and the non-transitory computer-readable medium receives information from the second network device, the location of the UE, the UE interference tolerance. program code for receiving a first request message indicating a threshold and/or a resource demand for the UE; and program code for making a prediction based on the first request message; and program code for transmitting a response message indicating the protected resource to the second network device. Transient computer-readable medium.

[00148] The above disclosure provides examples and descriptions and is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of the embodiments.

[00149] The term "component" as used shall be broadly construed as hardware, firmware, and/or a combination of hardware and software. The processors used are implemented in hardware, firmware, and/or a combination of hardware and software.

[00150] Several aspects are described regarding thresholds. Depending on the context, meeting the threshold used means that the value is greater than the threshold, greater than or equal to the threshold, less than the threshold, or less than the threshold. It can refer to less than or equal to, equal to a threshold value, not equal to a threshold value, etc.

[00151] It will be apparent that the systems and/or methods described may be implemented in different forms of hardware, firmware, and/or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and/or methods is not limiting of aspects. Accordingly, the operations and behaviors of the systems and/or methods are described without reference to specific software code, and software and hardware designed to implement the systems and/or methods are based at least in part on the description. It is understood that this can be done.

[00152] Although certain combinations of features are recited in the claims and/or disclosed herein, these combinations are not intended to limit the disclosure of the various aspects. In fact, many of these features may be combined in ways not specifically specified in the claims and/or disclosed herein. Although each dependent claim set forth below may be directly dependent on only one claim, the disclosure of various aspects includes each dependent claim in combination with any other claim in the claims. . A phrase referring to "at least one of" a list of items refers to any combination of those items, including a single member. As an example, "at least one of a, b, or c" refers to a, b, c, a-b, a-c, b-c, and a-b-c, as well as multiples of the same element. (for example, a-a, a-a-a, a-ab, a-ac, a-bb, a-c-c, bb, bb-b , b-b-c, c-c, and c-c-c, or any other order of a, b, and c).

[00153] No element, act, or instruction used should be construed as critical or required unless explicitly described as such. Also, the articles "a" and "an" used include one or more items and can be used interchangeably with "one or more." Additionally, the terms "set" and "group" as used include one or more items (e.g., related items, unrelated items, combinations of related and unrelated items, etc.); Can be used interchangeably with "one or more." If only one item is intended, the phrase "only one" or similar phraseology is used. Additionally, terms such as "has," "have," and "having" as used are open-ended terms. Further, the phrase "based on" means "based at least in part on," unless specified otherwise.

Claims (30)

A method of wireless communication by a first network device, the method comprising:
predicting spatial inter-cell downlink interference experienced by the UE;
communicating with a second network device to reduce the spatial inter-cell downlink interference in the direction of the UE by conserving resources across a selected resource set;
A method of providing. the first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the method comprises:
selecting, by the first network device, the UE for which the predicted inter-cell downlink interference exceeds a predetermined threshold;
sending a request message to the second network device;
2. The method of claim 1, further comprising: 3. The method of claim 2, wherein the request message indicates beams that cause excessive interference. 3. The method of claim 2, wherein the request message indicates time/frequency resources to be protected. 3. The method of claim 2, wherein the request message indicates an amount of resources to protect, the amount being determined based on the UE's traffic demand. 3. The method of claim 2, wherein the request message indicates an index of the selected resource set within a predetermined list of resource sets. 3. The method of claim 2, further comprising receiving a response message indicating acceptance of the proposal indicated by the request message. 3. The method of claim 2, further comprising receiving a response message indicating alternative offers for a different set of resources. 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. The method according to claim 2. the first network device comprises a neighbor cell, the second network device comprises a serving cell, and the method comprises:
receiving a request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
making a prediction based on the request message;
sending a response message to the second network device;
2. The method of claim 1, further comprising: 11. The method of claim 10, further comprising receiving updates of the UE location, the UE interference tolerance threshold, and/or the resource demand for the UE from the second network device. the first network device comprises a central node, the second network device comprises a serving cell, and the method comprises:
receiving from the second network device a first request message indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
making a prediction based on the first request message;
sending a second request message requesting resource protection to the aggressor neighbor cell;
sending a response message to the second network device indicating a protected resource;
2. The method of claim 1, further comprising: 13. The method of claim 12, further comprising updating the predicting based on an updated UE location, updated channel conditions for the UE, and/or updated resource demand for the UE. Method. An apparatus for wireless communication by a first network device, the apparatus comprising:
means for predicting spatial downlink intercell interference experienced by a UE;
means for communicating with a second network device to reduce the spatial downlink inter-cell interference in the direction of the UE by conserving resources across a selected set of resources;
A device comprising: the first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the apparatus comprises:
means for selecting, by the first network device, the UE for which the predicted spatial downlink inter-cell interference exceeds a predetermined threshold;
means for sending a request message to the second network device;
15. The apparatus of claim 14, further comprising: 16. The apparatus of claim 15, further comprising means for receiving a response message indicating acceptance of the proposal indicated by the request message. 16. The apparatus of claim 15, further comprising means for receiving a response message indicating alternative offers for a different set of resources. further 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. 16. The apparatus of claim 15, comprising: the first network device comprises a neighbor cell, the second network device comprises a serving cell, and the apparatus comprises:
means for receiving a request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
means for predicting based on the request message;
means for sending a response message to the second network device;
15. The apparatus of claim 14, further comprising: 20. The apparatus of claim 19, further comprising means for receiving updates of the UE location, the UE interference tolerance threshold, and/or the resource demand for the UE from the second network device. the first network device comprises a central node, the second network device comprises a serving cell, and the apparatus comprises:
means for receiving a first request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
means for predicting based on the first request message;
means for transmitting a second request message requesting resource protection to the aggressor neighbor cell;
means for transmitting a response message to the second network device indicating a protected resource;
15. The apparatus of claim 14, further comprising: 22. The method of claim 21, further comprising means for updating the predicting based on an updated UE location, updated channel conditions for the UE, and/or updated resource demand for the UE. The device described. a processor;
a memory coupled to the processor;
instructions stored in the memory;
, wherein the instructions, when executed by the processor, cause the first network device to:
predicting spatial inter-cell downlink interference experienced by the UE;
communicating with a second network device to reduce the spatial inter-cell downlink interference in the direction of the UE by conserving resources across a selected resource set;
A first network device operable to perform a first network device. the first network device comprises a serving cell, the second network device comprises a potentially interfering neighbor cell, and the instructions cause the first network device to:
selecting the UE for which the predicted inter-cell downlink interference exceeds a predetermined threshold;
sending a request message to the second network device;
24. The first network device of claim 23, further comprising: the first network device comprises a neighbor cell, the second network device comprises a serving cell, and the instructions cause the first network device to:
receiving a request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
making a prediction based on the request message;
sending a response message to the second network device;
24. The first network device of claim 23, further comprising: the first network device comprises a central node, the second network device comprises a serving cell, and the instructions cause the first network device to:
receiving from the second network device a first request message indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
making a prediction based on the first request message;
sending a second request message requesting resource protection to the aggressor neighbor cell;
sending a response message to the second network device indicating a protected resource;
24. The first network device of claim 23, further comprising: The instructions cause the first network device to update the prediction based on an updated UE location, updated channel conditions for the UE, and/or updated resource demands for the UE. 27. The first network device of claim 26, further configured to: a non-transitory computer readable medium having program code recorded thereon, the program code being executed by a processor of a first network device;
a program code for predicting spatial inter-cell downlink interference experienced by a UE;
program code for communicating with a second network device to reduce the spatial inter-cell downlink interference in the direction of the UE by conserving resources across a selected set of resources;
A non-transitory computer-readable medium comprising: the first network device comprises a neighbor cell, the second network device comprises a serving cell, and the non-transitory computer readable medium comprises:
program code for receiving a request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
Program code for making a prediction based on the request message;
program code for sending a response message to the second network device;
29. The non-transitory computer-readable medium of claim 28, further comprising:. The first network device comprises a central node, the second network device comprises a serving cell, and the non-transitory computer readable medium comprises:
program code for receiving a first request message from the second network device indicating a location of the UE, a UE interference tolerance threshold, and/or a resource demand for the UE;
Program code for predicting based on the first request message;
Program code for transmitting a second request message requesting resource protection to an aggressor neighbor cell;
Program code for transmitting a response message to the second network device indicating a protected resource;
29. The non-transitory computer-readable medium of claim 28, further comprising:.

Images