Information exchange for wireless communications
By exchanging information and using AI/ML models, network devices in wireless communication systems optimize resource allocation to reduce interference and signaling overhead, enhancing communication efficiency.
Patent Information
- Application Number
- PCT/CN2024/087403
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-04-12
- Publication Date
- 2025-07-31
AI Technical Summary
In wireless communication systems implementing sub-band or full duplex, cross-link interference between base stations and user devices is significant, leading to increased signaling overhead to alleviate interference, which existing methods fail to address effectively without degrading performance.
Network devices exchange information such as measurement results, predicted results, probabilities, preferred and non-preferred resources, and model training datasets to optimize resource allocation and reduce interference, using artificial intelligence and machine learning models to predict and adjust transmission schedules.
This approach reduces signaling overhead while effectively managing interference, improving communication efficiency and reducing cross-link interference by optimizing resource allocation based on predictive models.
Smart Images

Figure CN2024087403_31072025_PF_FP_ABST
Abstract
Description
INFORMATION EXCHANGE FOR WIRELESS COMMUNICATIONSTECHNICAL FIELD
[0001] This document is directed generally to schemes pertaining to information exchange for wireless communications.BACKGROUND
[0002] In wireless communication system, sub-band full duplex or full duplex may be implemented to improve system throughput and reduce latency. In such implementations, with the same time domain resource, a base station can simultaneously transmit a downlink (DL) signal to, and receive an uplink (UL) signal from, either different user devices or the same user device. The DL and UL signals may be communicated in different frequency resources when implementing sub-band full duplex or in the same frequency resource when implementing full duplex. However, in such implementations, crosslink interference may be much worse compared to when implementing time division duplex (TDD) . For example, a DL transmission of one base station may cause interference to the reception of the other base station. As another example, an UL transmission of one user device may cause interference to the reception of the other user device. To alleviate such interference, two base stations, or a base station and a user device, may exchange certain information, which increases signaling overhead. As such, ways to reduce signaling overhead without degrading the interference alleviation that the signaling overhead addresses may be desirable.SUMMARY
[0003] This document relates to methods, systems, apparatuses and devices for wireless communication. In some implementations, a method for wireless communication includes: transmitting, by a first network device, a signal; and in response to transmitting the signal, receiving, by the first network device from a second network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0004] In some other implementations, a method for wireless communication includes: receiving, by a second network device, a signal; and in response to receiving the signal, transmitting, by the second network device to a first network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0005] In some other implementations, a device, such as a network device, is disclosed. The device may include one or more processors and one or more memories, wherein the one or more processors are configured to read computer code from the one or more memories to implement any of the methods above.
[0006] In yet some other implementations, a computer program product is disclosed. The computer program product may include a non-transitory computer-readable program medium with computer code stored thereupon, the computer code, when executed by one or more processors, causing the one or more processors to implement any of the methods above.
[0007] The above and other aspects and their implementations are described in greater detail in the drawings, the descriptions, and the claims.BRIEF DESCRIPTION OF THE DRAWINGS
[0008] FIG. 1 shows a block diagram of an example of a wireless communication system.
[0009] FIG. 2 shows a flow chart of a method for wireless communication.
[0010] FIG. 3 shows a flow chart of another method for wireless communication.
[0011] FIG. 4 shows a block diagram of an artificial intelligence (AI) / machine learning (ML) framework.
[0012] FIG. 5 shows a timing diagram of an example of a measurement results exchange.
[0013] FIG. 6 is a timing diagram of an example of a measurement results prediction.
[0014] FIG. 7 is a schematic diagram of an example of exchanged information including a scheduling state and a probability.DETAILED DESCRIPTION
[0015] The example headings for the various sections below are used to facilitate the understanding of the disclosed subject matter and do not limit the scope of the claimed subject matter in any way. Accordingly, one or more features of one example section can be combined with one or more features of another example section. Furthermore, 5G terminology is used for the sake of clarity of explanation, but the techniques disclosed in the present document are not limited to 5G technology only, and may be used in wireless systems that implemented other protocols, e.g., 6G or beyond.
[0016] The present description describes various embodiments of systems, apparatuses, devices, and methods for wireless communications related to communication configurations between network devices to reduce signaling overhead without increasing interference.
[0017] Fig. 1 shows a diagram of an example wireless communication system 100 including a plurality of communication nodes (or just nodes) that are configured to wirelessly communicate with each other. In general, the communication nodes include at least one user device 102 and at least one network device 104. The example wireless communication system 100 in Fig. 1 is shown as including two user devices 102, including a first user device 102 (1) and a second user device 102 (2) , and two network devices 104, including a first network device 104 (1) and a second network device 104 (2) . However, various other examples of the wireless communication system 100 that include any of various combinations of one or more user devices 102 and / or one or more network devices 104 may be possible.
[0018] In general, a user device as described herein, such as the user device 102, may include a single electronic device or apparatus, or multiple (e.g., a network of) electronic devices or apparatuses, capable of communicating wirelessly over a network. A user device may comprise or otherwise be referred to as a user terminal, a user terminal device, or a user equipment (UE) . Additionally, a user device may be or include, but not limited to, a mobile device (such as a mobile phone, a smart phone, a smart watch, a tablet, a laptop computer, vehicle or other vessel (human, motor, or engine-powered, such as an automobile, a plane, a train, a ship, or a bicycle as non-limiting examples) or a fixed or stationary device, (such as a desktop computer or other computing device that is not ordinarily moved for long periods of time, such as appliances, other relatively heavy devices including Internet of things (IoT) , or computing devices used in commercial or industrial environments, as non-limiting examples) . In various embodiments, a user device 102 may include transceiver circuitry 106 coupled to an antenna 108 to effect wireless communication with the network device 104. The transceiver circuitry 106 may also be coupled to a processor 110, which may also be coupled to a memory 112 or other storage device. The memory 112 may store therein instructions or code that, when read and executed by the processor 110, cause the processor 110 to implement various ones of the methods described herein.
[0019] Additionally, in general, a network device as described herein, such as the network device 104, may include a single electronic device or apparatus, or multiple (e.g., a network of) electronic devices or apparatuses, and may comprise one or more wireless access nodes, base stations, or other wireless network access points capable of communicating wirelessly over a network with one or more user devices and / or with one or more other network devices 104. For example, the network device 104 may comprise a 4G LTE base station, a 5G NR base station, a 5G central-unit base station, a 5G distributed-unit base station, a next generation Node B (gNB) , an enhanced Node B (eNB) , or other similar or next-generation (e.g., 6G) base stations, in various embodiments. A network device 104 may include transceiver circuitry 114 coupled to an antenna 116, which may include an antenna tower 118 in various approaches, to effect wireless communication with the user device 102 or another network device 104. The transceiver circuitry 114 may also be coupled to one or more processors 120, which may also be coupled to a memory 122 or other storage device. The memory 122 may store therein instructions or code that, when read and executed by the processor 120, cause the processor 120 to implement one or more of the methods described herein.
[0020] In various embodiments, two communication nodes in the wireless system 100-such as a user device 102 and a network device 104, two user devices 102 without a network device 104, or two network devices 104 without a user device 102-may be configured to wirelessly communicate with each other in or over a mobile network and / or a wireless access network according to one or more standards and / or specifications. In general, the standards and / or specifications may define the rules or procedures under which the communication nodes can wirelessly communicate, which, in various embodiments, may include those for communicating in millimeter (mm) -Wave bands, and / or with multi-antenna schemes and beamforming functions. In addition or alternatively, the standards and / or specifications are those that define a radio access technology and / or a cellular technology, such as Fourth Generation (4G) Long Term Evolution (LTE) , Fifth Generation (5G) New Radio (NR) , or New Radio Unlicensed (NR-U) , as non-limiting examples.
[0021] Additionally, in the wireless system 100, the communication nodes are configured to wirelessly communicate signals between each other. In general, a communication in the wireless system 100 between two communication nodes can be or include a transmission or a reception, and is generally both simultaneously, depending on the perspective of a particular node in the communication. For example, for a given communication between a first node and a second node where the first node is transmitting a signal to the second node and the second node is receiving the signal from the first node, the first node may be referred to as a source or transmitting node or device, the second node may be referred to as a destination or receiving node or device, and the communication may be considered a transmission for the first node and a reception for the second node. Of course, since communication nodes in a wireless system 100 can both send and receive signals, a single communication node may be both a transmitting / source node and a receiving / destination node simultaneously or switch between being a source / transmitting node and a destination / receiving node.
[0022] Also, particular signals can be characterized or defined as either an uplink (UL) signal, a downlink (DL) signal, or a sidelink (SL) signal. An uplink signal is a signal transmitted from a user device 102 to a network device 104. A downlink signal is a signal transmitted from a network device 104 to a user device 102. A sidelink signal is a signal transmitted from one user device 102 to another user device 102, or a signal transmitted from one network device 104 to another network device 104. Also, for sidelink transmissions, a first / source user device 102 directly transmits a sidelink signal to a second / destination user device 102 without any forwarding of the sidelink signal to a network device 104. Similarly, a first / source network device 104 directly transmits a sidelink signal to a second / destination network device 104 without any forwarding of the sidelink signal to a user device 102.
[0023] Additionally, at least some signals communicated between communication nodes in the system 100 may be characterized or defined as a data signal or a control signal. In general, a data signal is a signal that includes or carries data, such multimedia data (e.g., voice and / or image data) , and a control signal is a signal that carries control information that configures the communication nodes in certain ways in order to communicate with each other, or otherwise controls how the communication nodes communicate data signals with each other. Also, certain signals may be defined or characterized by combinations of data / control and uplink / downlink / sidelink, including uplink control signals, uplink data signals, downlink control signals, downlink data signals, sidelink control signals, and sidelink data signals.
[0024] For at least some specifications, such as 5G NR, data and control signals are transmitted and / or carried on physical channels. Generally, a physical channel corresponds to a set of time-frequency resources used for transmission of a signal. Different types of physical channels may be used to transmit different types of signals. For example, physical data channels (or just data channels) , also herein called traffic channels, are used to transmit data signals, and physical control channels (or just control channels) are used to transmit control signals. Example types of traffic channels (or physical data channels) include, but are not limited to, a physical downlink shared channel (PDSCH) used to communicate downlink data signals, a physical uplink shared channel (PUSCH) used to communicate uplink data signals, and a physical sidelink shared channel (PSSCH) used to communicate sidelink data signals. In addition, example types of physical control channels include, but are not limited to, a physical downlink control channel (PDCCH) used to communicate downlink control signals, a physical uplink control channel (PUCCH) used to communicate uplink control signals, and a physical sidelink control channel (PSCCH) used to communicate sidelink control signals. As used herein for simplicity, unless specified otherwise, a particular type of physical channel is also used to refer to a signal that is transmitted on that particular type of physical channel, and / or a transmission on that particular type of transmission. As an example illustration, a PDSCH refers to the physical downlink shared channel itself, a downlink data signal transmitted on the PDSCH, or a downlink data transmission. Accordingly, a communication node transmitting or receiving a PDSCH means that the communication node is transmitting or receiving a signal on a PDSCH.
[0025] Additionally, for at least some specifications, such as 5G NR, and / or for at least some types of control signals, a control signal that a communication node transmits may include control information comprising the information necessary to enable transmission of one or more data signals between communication nodes, and / or to schedule one or more data channels (or one or more transmissions on data channels) . For example, such control information may include the information necessary for proper reception, decoding, and demodulation of a data signals received on physical data channels during a data transmission, and / or for uplink scheduling grants that inform the user device about the resources and transport format to use for uplink data transmissions. In some embodiments, the control information includes downlink control information (DCI) that is transmitted in the downlink direction from a network device 104 to a user device 102. In other embodiments, the control information includes uplink control information (UCI) that is transmitted in the uplink direction from a user device 102 to a network device 104, or sidelink control information (SCI) that is transmitted in the sidelink direction from one user device 102 (1) to another user device 102 (2) , or from one network device 104 (1) to another network device 104 (2) .
[0026] Fig. 2 is a flow chart of an example method 200 for wireless communication related to signaling between two network devices 104 (1) , 104 (2) . At block 202, a first network device 104 (1) transmits a signal. At block 204, in response to transmitting the signal, the first network device 104 (1) receives from a second network device 104 (2) at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0027] Fig. 3 is a flow chart of another example method 300 for wireless communication related to signaling between two network devices 104 (1) , 104 (2) . At block 302, a second network device 104 (2) receives a signal. At block 304, in response to receiving the signal, the second network device 104 (2) transmits to a first network device 104 (1) at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0028] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one measurement result, wherein the at least one measurement result is based on a set of one or more resources, and wherein each resource of the set corresponds to a respective one of the at least one measurement result.
[0029] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted result, and wherein each of the at least one predicted result corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0030] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted preferred resource, and wherein each of the at least one predicted preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0031] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted non-preferred resource, and wherein each of the at least one predicted non-preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0032] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits at least one of: the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability, and wherein the at least one of the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability is determined based on a model and an input for the model comprises at least one of the at least one measurement result or at least one time instance of the at least one measurement result.
[0033] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted result, wherein each of the at least one predicted result corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one accuracy probability. In some of these implementations, the at least one accuracy probability is determined based on a threshold.
[0034] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted preferred resource, wherein each of the at least one predicted preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one preferred probability.
[0035] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one predicted non-preferred resource, wherein each of the at least one predicted non-preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one non-preferred probability.
[0036] In some implementations of the method 200 and / or the method 300, a model has a requirement, and in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, the first network device 104 (1) receives from the second network device 104 (2) an indication that the model cannot satisfy the requirement.
[0037] In some implementations of the method 200 and / or the method 300, a model has a requirement, and in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, the second network device 104 (2) changes the model to a different model, or indicates to the first network device 104 (1) that the model cannot satisfy the requirement.
[0038] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives from the second network device 104 (2) at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.
[0039] In some implementations of the method 200 and / or the method 300, the second network device 104 (2) transmits to the first network device 104 (1) at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.
[0040] In some implementations of the method 200 and / or the method 300, , the first network device 104 (1) receives and / or the second network device 104 (2) transmits at least one of: the at least one predicted scheduling state or the at least one second probability, wherein the at least one of the at least one predicted scheduling state or the at least one second probability is determined based on a model and an input for the model comprises at least one of: at least one previous scheduling state or data to be transmitted.
[0041] In some implementations of the method 200 and / or the method 300, the first network device 104 (1) receives and / or the second network device 104 (2) transmits the at least one second probability, and wherein one of the at least one second probability corresponding to one of the at least one transmission resource comprises a probability that the second network device 104 (2) schedules a transmission on the one of the at least one transmission resource or a probability that the second network device 104 (2) does not schedule the transmission on the one of the at least one transmission resource.
[0042] In some implementations of the method 200 and / or the method 300, the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability corresponds to a respective one of at least one transmission resource.
[0043] Further details of actions performed by communication nodes in the wireless communication system 100, any or all of which may be implemented in any of various implementations of the method 200, the method 300, and / or other methods, are now described.
[0044] In some implementations of the wireless communication system 100, an artificial intelligence (AI) and or a machine learning (ML) model (collectively referred to herein as an AI / ML model) may be a data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. As used herein, “model” is a general term used to describe a processing method that a communication node (e.g., a user device 102 or a network device 104) is configured to perform and / or a functionality, a feature, and / or a feature group that a communication node (e.g., a user device 102 and / or a network device 104) is configured to have. In this context, the term “model” may be used herein to refer to and / or include a functionality, a function, a functionality module, a function module, a processing method, an information processing method, an implementation, a feature, a feature group, a configuration, a configuration set, a dataset (e.g., for model training) , and / or a data-driven algorithm, in any of various implementations. Different models may be associated with different configurations (e.g., a radio resource control (RRC) configuration) . The term ‘model activation’ may refer to activation of a corresponding configuration for a communication node (e.g., a user device 102 or a network device 104) . Similarly, model deactivation, switching and fallback may refer to deactivation of the corresponding configuration, switching of the corresponding configuration and fallback to the corresponding configuration without the model, respectively. As used herein, the term ‘beam’ is equivalent to or comprises a quasi-co-location (QCL) state, a transmission configuration indicator (TCI) state, a beam state, a spatial relation (also called herein spatial relation information) , a reference signal (RS) , a RS resource, a spatial filter or pre-coding. The term ‘beam identification or identifier (ID) ’ is equivalent to or comprises at least one of the following: a QCL state index, a TCI state index, a spatial relation state index, a reference signal index, a spatial filter index, a precoding index, a CSI-RS resource indicator (CRI) , a SSB resource indicator (SSBRI) , a CSI resource set ID, a CSI resource setting ID, or a reporting setting ID. The term ‘time instance’ is equivalent to or comprises at least one of the following: a slot, a sub-slot, a symbol, a sub-symbol, a frame, a sub-frame, a transmission occasion, a millisecond, a microsecond or other typical units for time. The term ‘measurement result’ represents the channel information that is obtained by measurement. The term ‘channel information’ refers to a general term that can be obtained by UE measurement or is related to the model input / output. The term ‘channel information’ is equivalent to or comprises at least one of the following: a beam ID, channel state information (CSI) , a reference signal received power (RSRP) , a reference signal received quality (RSRQ) , a signal to interference &noise ratio (SINR) , a received signal strength indicator (RSSI) , a channel quality indicator (CQI) , a precoding matrix indicator (PMI) , a rank indicator (RI) , a layer indicator (LI) , a signal to noise ratio (SNR) , a block error rate (BLER) , a channel phase information, a channel impulse response information, a timing information, a confidence level / information, a probability, a channel matrix (e.g., in spatial-frequency domain or in angular-delay domain) , a precoding matrix, a location, fingerprinting based on channel observation, a new measurement and / or an enhancement of existing measurement (e.g., line of sight (LOS) / non-line of sight (NLOS) identification, a timing and / or an angle of measurement, and / or a likelihood of measurement) . The term ‘prediction result’ represents the channel information that is obtained by model inference.
[0045] Fig. 4 shows a block diagram of an example AI / ML framework, which may be implemented in one or more communication nodes of the wireless communication system 100.
[0046] Embodiment 1
[0047] In some implementations, a first network device (e.g., a first base station) 104 (1) or a second network device (e.g., a second base station) 104 (2) may configure a first set of one or more resources. Each of the one or more resources of the first set may be identified by a respective one of one or more resource indexes. Additionally, a given resource of the first set may include at least one of a reference signal or a time and / or a frequency resource for measurement. In addition or alternatively, in some implementations, the reference signal may include at least one of: a channel state information reference signal (CSI-RS) or a synchronization signal and physical broadcast channel (PBCH) block (SSB) . In addition or alternatively, the time and / or frequency resource for measurement may include at least one of a received signal strength indication (RSSI) resource or a reference signal receiving quality (RSRQ) resource. In addition or alternatively, the first network device 104 (1) and the second network device 104 (2) may exchange a configuration of the first set of one or more resources. For example, the first network device 104 (1) may send the configuration of the first set of one or more resources to the second network device 104 (2) .
[0048] Additionally, in some implementations, the first network device (e.g., first base station) 104 (1) may send the reference signal. The second network device (e.g., second base station) 104 (2) may measure the first set of one or more resources and obtain one or more measurement results. The one or more measurement results may include at least one of: a reference signal receiving power (RSRP) , a RSSI, a RSRQ, or a signal to interference plus noise ratio (SINR) , as non-limiting examples. The second network device 104 (2) may send the measurement result (s) to the first network device 104 (1) . In addition, the second network device 104 (2) may send one or more time instances of the one or more resources to the first network device 104 (1) together with the one or more measurement results. The one or more time instances may be or include time information of the one or more resources (e.g., frame index, sub-frame index, slot index, sub-slot index, orthogonal frequency division multiplexing (OFDM) symbol index, millisecond, or microsecond of the one or more resources) . For example, the time information of a given resource R1 (where R1 is the resource index of the given resource) may be or include a frame index F1 and a slot index SL 1. The second network device 104 (2) may measure the resource R1 and determine a measured RSRP RP1. In turn, the second network device 104 (2) may send at least one of a resource index R1, a frame index 1, a slot index SL1, or the measured RSRP RP 1 to the first network device 104 (1) .
[0049] Additionally, in some implementations, the first network device (e.g., first base station) 104 (1) and / or the second network device (e.g., second base station) 104 (2) may use the measurement result (s) to train a model.
[0050] Additionally, in some implementations, the second network device (e.g., second base station) 104 (2) may send the measurement result (s) to the first network device (e.g., first base station) 104 (1) periodically, such as according to and / with a specific period. In addition or alternatively, in some implementations, the second network device 104 (2) may send measurement results of only a subset of the first set of one or more resources. In particular of these implementations, the first network device 104 (1) may indicate the subset of the first set of one or more sources to the second network device 104 (2) . For example, the first network device 104 (1) may use a bitmap to indicate the subset of the first set of one or more resource. The length of the bitmap may be equal to the number of resources in the first set. Each bit may correspond to a respective one of the one or more resources of the first set. For example, a first bit value (e.g., '0' ) of given bit may indicate that a corresponding resource is not included in the subset and / or the second network device 104 (2) may not send the measurement results of the corresponding resource. A second bit value (e.g., '1' ) of a given bit may indicate that the corresponding resource is included in the subset and / or the second network device 104 (2) may send the measurement results of the corresponding resource.
[0051] The second base station may send the measurement results of all the resources in the first set every several periods.
[0052] Fig. 5 shows a timing diagram of an example of a measurement results exchange. As an example with reference to Fig. 5, suppose there are eight resources in total, denoted by resource 1-8. Further, suppose a subset of the resources includes resource 3 and resource 5. Further, suppose a period of measurement exchange is P, and that the second network device 104 (2) sends the measurement results for all of the resources every 5P.
[0053] In furtherance of the example, suppose at a first time instance t1, the second network device 104 (2) sends the measurement results of all of the resources (e.g., resources 1-8) . Additionally, suppose at the next four time instances (i.e., a second time instance t2, a third time instance t3, a fourth time instance t4, and a fifth time instance t5) the second network device 104 (2) sends the measurement results of resource 3 and resource 5. Then, at sixth time instance t6, the second network device 104 (2) send the measurement results of all the of resources (i.e., resources 1-8) .
[0054] In addition or alternatively, in some implementations, the second network device 104 (2) may send the measurements of the subset of the first set of one or more resources, where the subset may be changed cyclically. For example, the subset may be changed every one or more specific periods. Correspondingly, the second network device 104 (2) may send the measurement result (s) of a different set of one or more resources at different time instances.
[0055] To illustrate, referring to the timing diagram of Fig. 5, at the first time instance t1, the second network device 104 (2) may send the measurement results of the first two resources (i.e., resources 1 and 2) . At the second time instance t2, the second network device 104 (2) may send the measurement results of the next two resources (i.e., resources 3 and 4) . At the third time instance t3, the second network device 104 (2) may send the measurement results of the next two resources (i.e., resources 5 and 6) . At the fourth time instance t4, the second network device 104 (2) may send the measurement results of the last two resources (i.e., resources 7 and 8) . At the fifth time t5, the second network device 104 (2) may send the measurement results of the first two resources (i.e., resources 1 and 2) .
[0056] Accordingly, such implementations of exchanged information may reduce overhead between the first and second network devices 104 (1) , 104 (2) .
[0057] Embodiment 2
[0058] Additionally, in some implementations, the first network device (e.g., first base station) 104 (1) and / or the second network device (e.g., second base station) 104 (2) may configure a second set of one or more resources. In addition or alternatively, the first network device 104 (1) and / or the second network device 104 (2) may configure a third set of one or more resources. In some of these implementations, the second set of one or more resources may be a subset of the third set of one or more resources. For example, all of the resources of the second set may also be included in the third set. For at least some of these implementations, the third set may further include one or more additional resources. Additionally or alternatively, the period of a resource in the second set may be a multiple of the period of the resource in the third set. For example, the period of a resource in the third set may be P and the period of the resource in the second set may be A*P, where A is an integer.
[0059] Additionally, in some implementations, measurement result (s) of the second set or the third set may be used to train a model.
[0060] Additionally, in some implementations, at one time instance, the network device (e.g., second base station) 104 (2) may measure the second set and obtain the measurement result (s) of the second set. At least one of the measurement result (s) of the second set and the time instance of the second set may be an input of the model. For some of these implementations, the input may also include the measurement result (s) of the second set in one or more previous time instances. Based on the inputs, the output may include at least one of: one or more predicted results or one or more first probabilities. In some of these implementations, the predicted result (s) predicted by the second network device 104 (2) may include the result (s) of the one or more resources that is not in the second set and / or included in the third set. Additionally or alternatively, the prediction result (s) may include the result (s) of the one or more resources in a future time instance. The future time instance is the time instance after the time instance of the measured second set. A first probability of a resource may be or include an accuracy probability of the resource predicted by the second network device 104 (2) . For each predicted resource, there may be one or more first probability.
[0061] Additionally, in some implementations, the second network device (e.g., second base station) 104 (2) may send one or more results to the first network device (e.g., first base station) 104 (1) . Each result for a resource may include at least one of: a resource index of the resource, a time instance of the resource, a measurement result of the resource, a predicted result of the resource, a time instance of the predicted result, or a first probability of the resource.
[0062] Fig. 6 is a timing diagram of an example of measurement results prediction. Suppose in an example with reference to Fig. 6 that the second resource set includes resource 1 and resource 2. Further, suppose that the third resource set include the resource 1, resource 2, resource 3 and resource 4. At the fifth time instance t5, the second network device 104 (2) may measure resource 1 and resource 2. The measurement results of resource 1 and resource 2 are referred to as S5, 1 and S5,2, respectively. In some implementations, S5, 1 and S5, 2 may be the measurement results after filtering. In addition or alternatively, in some implementations, the second network device 104 (2) may obtain the measurement results at the first, second, third, and fourth instances t1, t2, t3 and t4 based on a previous measurement. The measurement results are shown below in Table 1. For at least some implementations, these measurement results may be the input of the model. The output may include the predicted results of resource 3 (e.g., S5, 3) and a corresponding first probability p5, 3, the predicted results of resource 4 (e.g., S5, 4) and the corresponding first probability p5, 4 at the fifth time instance t5. In addition, the output may include the predicted results of resource 1 (e.g., S6, 1) and the corresponding first probability P6, 1, the predicted results of resource 2 (e.g., S6, 2) and the corresponding first probability P6, 2, predicted results of resource 3 (e.g., S6, 3) and the corresponding first probability P6, 3, and / or the predicted results of resource 4 (e.g., S6, 4) and the corresponding first probability P6, 4 at the sixth time instance t6.
[0063] Table 1
[0064] Additionally, in some implementations, the second network device 104 (2) may send the measured results (e.g., at least one of S5, 1 and S5, 2) to the first network device 104 (1) . Additionally or alternatively, the second network device 104 (2) may send the predicted results and / or the first probability, and / or the time instance (e.g., at least one of S5, 3, p5, 3, S5, 4, p5, 4, S6, 1, P6, 1, S6, 2, P6, 2, S6, 3, P6, 3, S6, 4, P6, 4, t5, t6) to the first network device 104 (1) . In some of these implementations, there may be predicted results in one or more of the other time instances (e.g., one or more of t1, t2, t3, t4, etc) even though such is not indicated in Table 1.
[0065] In addition or alternatively, in some implementations based on the measurement results, the second network device (e.g., second base station) 104 may determine a preferred resource (such as a preferred beam) and / or a non-preferred resource (such as a non-preferred beam) . In some implementations, a preferred resource includes or refers to that a beam or a signal from the first network device (e.g., first base station) 104 corresponding to the preferred resource that may have less interference from the perspective of the second network device 104 (2) , and thus is preferred by the second network device 104 (2) . Additionally, a non-preferred resource includes or refers to a beam or a signal from the first network device 104 (1) corresponding to the non-preferred resource may have higher interference from the perspective of the second network device 104 (2) and thus is not preferred by the second network device 104 (2) . In any of various implementations, the second network device 104 (2) may send a preferred resource index for a preferred resource and / or a non-preferred resource index for a non-preferred resource to the first network device 104 (1) .
[0066] Additionally, in some implementations, at least one of the preferred resource index or the non-preferred resource index may be an input of the model. Based on the input, the output of the model may include at least one of a predicted preferred resource index or a predicted non-preferred resource index. The predicted preferred resource index and / or the predicted non-preferred resource may include the index of the resource that is included in the third resource set or not included in the second resource set. In additionally or alternatively, the predicted beam index or the predicted non-preferred beam index may include the index of the resource at a future time instance. The output may include a second probability of the resource. The second probability may include a preferred probability or a non-preferred probability. For a given resource, the preferred probability may be the probability that the second network device 104 (2) prefers the given resource and the non-preferred probability may be a probability that the second network device 104 (2) does not prefer the given resource.
[0067] Still referring to the example in Fig. 6, the preference of a resource is shown in Table 2 below. Based on a measurement, the second network device 104 (2) may determine that resource 1 and resource 2 are each a not preferred resource at the fifth time instance t5. These determinations of the non-preference of resource 1 and resource 2 may be the input to the model. The output may include that resource 3 is preferred and a corresponding second probability is p5, 3 at the fifth time instance t5. Additionally, resource 4 is a non-preferred resource, and the corresponding second probability is p5, 4 at the fifth time instance t5. In addition, the predicted non-preferred beam includes resource 1 and resource 4, and their respective second probability is P6, 1 and P6, 4 at the sixth time instance t6. The predicted preferred beam includes resource 2 and resource 3, and their respective probabilities are P6, 2 and P6, 3 at the sixth time instance t6. In some of these implementations, there may be a predicted preferred beam or a non-preferred beam in the other time instances (e.g., time instances t1, t2, t3, t4, etc) even though they are not shown in Table 2.
[0068] Table 2
[0069] In other implementations, the second network device 104 (2) may determine the predicted preferred resource and / or the predicted non-preferred resource based on the predicted results. For a given resource, the predicted preferred probability or the predicted non-preferred probability may be equal to, or the same as, the accuracy probability.
[0070] Additionally, in some implementations, the first network device (e.g., first base station) 104 (1) may receive at least one of the preferred resource, the non-preferred resource, the predicted preferred resource, the predicted non-preferred resource, the time instance of the predicted preferred resource or predicted non-preferred resource, or the second probability. The first network device 104 (1) may use the beam corresponding to the preferred resource, where possible. In addition or alternatively, the first network device 104 (1) may not use the beam corresponding to the non-preferred resource, where possible. For example, the first network device 104 (1) may use the beam corresponding to resource 2 or resource 3 where possible before or after the sixth time instance t6 or not use the beam corresponding to resource 1 and resource 4 where possible before or after the sixth time instance t6. In doing so, the cross link interference between the first network device 104 (1) and the second network device 104 (2) can be reduced.
[0071] Additionally, in some implementations, the second network device (e.g., second base station) 104 (2) may use an error range or a first error threshold to determine whether a predicted result is accurate or whether the predicted result can satisfy a requirement. For one resource, if the difference between the predicted result and the actual result is within the error range, or less than or equal to the error threshold, the predicted result may be considered as accurate or satisfied. Such prediction (i.e., a prediction that is determined to satisfy a requirement) is referred to as qualified prediction. Additionally, if the difference between the predicted result and the actual result is not within the error range, or is greater than the error threshold, the predicted result may be considered to be inaccurate and / or not satisfied. Such prediction (i.e., a prediction that is determined to not satisfy a requirement) is referred to as unqualified prediction. Additionally, in some implementations, the second network device 104 (2) may determine whether the predicted result is accurate when the second network device 104 (2) is able to obtain the actual result. The second network device 104 (2) may obtain the actual result based on the measurement of the second set of one or more resources or the third set of one or more resources. For example, the second network device 104 (2) may obtain the actual result of the resource at a future time instance. The second network device 104 (2) may obtain the actual results of the resource that is included in the third set of one or more resources based on the measurement of the second set or the third set. The error range or a first error threshold may be exchanged between the first network device 104 (1) and the second network device 104 (2) . Still referring to the example in Fig. 6, the second network device 104 (2) may be able to obtain the predicted result of resource 1 (e.g., S6, 1) . The second network device 104 (2) may be able to obtain the actual measurement result at sixth time instance t6 by measuring resource 1. The difference of S6, 1 of the actual measurement result may be used to determine whether the predicted results is satisfied.
[0072] Additionally, in some implementations, the second network device 104 (2) may determine whether the predicted result is accurate or whether the predicted result can satisfy the requirement within a time duration or within a specific time instance (or predictions) . A second threshold may be used to determine whether the model can satisfy the requirement. The second threshold, the length of the time duration, and / or the number of the specific time instances (or predictions) may be determined by the first network device 104 (1) or the second network device 104 (2) in any of various implementations. The second threshold, the length of the time duration, and / or the number of the specific time instants (or predictions) may be exchanged between the first network device 104 (1) and the second network device 104 (2) in any of various implementations.
[0073] Additionally, in some implementations, if a number of qualified predictions or a qualified ratio is less than or equal to the second threshold, the model may be identified or considered as not satisfied or not able to satisfy the requirement. The second network device (e.g., second base station) 104 may change the model or the second network device 104 (2) may indicate to the first network device (e.g., first base station) 104 (1) that the model cannot satisfy the requirement. The first network device 104 (1) may indicate another model to the second network device 104 (2) . Correspondingly, the second network device 104 (2) may use another model for prediction. If a number of qualified predictions or a qualified ratio is greater than or equal to the second threshold, the model may be identified or considered as satisfied or able to satisfy the requirement. The second network device (e.g., second base station) 104 (2) may continue using this model for prediction.
[0074] Through performance of the above-described implementations, a proper or optimal model may be used to improve the prediction accuracy and reduce the exchanged information overhead. In addition, the first network device 104 (1) and / or the second network device 104 (2) may know the measurement results and / or beam preferences within the future time period. This, in turn, may help the first network device 104 (1) and / or the second network device 104 (2) to reduce the cross link interference effectively.
[0075] Embodiment 3
[0076] Additionally, in some implementations, a network device (e.g., base station) 104 (e.g., the first network device 104 (1) or the second network device 104 (2) may use a model to predict downlink (DL) data. For at least some of these implementations, the previous available data may be an input to the model. Also, the output may the data (or the data size) that will arrive at a future time instance. Based on the predicted DL data, the network device 104 may determine a scheduling state at a future time instance. The scheduling state in the future may include or indicate which transmission resource (s) may be used by the network device 104 in the future and which transmission resource (s) may not be used by the network device 104 in the future. The transmission resource may be the time resource and / or the frequency resource used for transmission. One transmission resource may include one or more symbols (e.g., one or more orthogonal frequency division multiplexing (OFDM) symbols) , one or more sub-slots, one or more slots, one or more sub-frames, or one or more frames in the time domain, and / or may include one or more resource elements (RE) , one or more resource blocks (RB) , one or more resource element groups (REG) , or one or more resource block groups (RBG) in the frequency domain.
[0077] Additionally, in some implementations, the first network device 104 (1) or the second network device 104 (2) may use a model to predict the scheduling state in the future. At least one of the previous scheduling state or the DL data may be the input of the model. The output may include at least one of the scheduling state in the future and a third probability. Each transmission resource may correspond to one third probability. For a given transmission resource, the third probability may be the probability that the network device 104 may schedule a transmission on the given transmission resource or the probability that the network device 104 may not schedule transmission on the given transmission resource.
[0078] Additionally, in some implementations, the network device 104 may exchange at least one of the predicted scheduling state or the third probability. At least one of the predicted scheduling state or the third probability may be exchanged per transmission resource. Additionally, in some implementations, the first network device (e.g., first base station) 104 (1) and the second network device (e.g., second base station) 104 (2) may exchange at least one of: at least one measurement result, at least one predicted result, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, or at least one probability (e.g., the first probability and / or the second probability) per transmission resource. Correspondingly, exchanged information may include at least one of the predicted scheduling state or the third probability. The exchanged information may be ordered according to the time domain or the frequency domain. For a given transmission resource, one bit may be used to indicate whether the transmission is scheduled on the given transmission resource. For example, the bit value '1' may indicate that the transmission is scheduled on the given transmission resource and the bit value '0' may indicate that the transmission is not scheduled on the given transmission resource. For the given transmission resource, one or more bits may indicate the corresponding third probability.
[0079] Fig. 7 is a schematic diagram of an example of exchanged information including a scheduling state and a third probability. One transmission resource may include one sub-frame in the time domain and a RB pair in the frequency domain. Two bits may be used to indicate the third probability as shown in the Table 3, below. Additionally, one bit may be used to indicate whether the transmission is scheduled on the transmission resource. Correspondingly, there may be three bits for each transmission resource.
[0080] Table 3
[0081] Referring to the example in Fig. 7, there are sixteen transmission resources (TR) in total, denoted by TR1-TR16. The sixteen transmission resources may be ordered first in the order of frequency domain (e.g., RB pair index) and second in the order of time domain (e.g., the sub-frame index) . Correspondingly, the exchanged information may be ordered first in the order of frequency domain (e.g., RB pair index) and second in the order of time domain (e.g., the sub-frame index) . The exchanged information is shown in Table 4 below, from left to right and / or from the first line to the last line.
[0082] Table 4
[0083] Referring to Table 4, for transmission resource 1, the bit '1' may indicate that the network device 104 may schedule transmission on transmission resource 1, and the bit '01' may indicate that the corresponding third probability is (0.7-0.8] , i.e., the probability that the base station schedules transmission on transmission resource is (0.9-1] . This means that there is still at most a 0.2 probability to not schedule transmission on transmission resource 1. For transmission resource 2, the bit '0' may indicate that the network device 104 may not schedule transmission on transmission resource 2, and the bit '11' may indicate the corresponding third probability is (0.9-1] , i.e., the probability that the base station does not schedule transmission on transmission resource is (0.9-1] . This means that there is still at most a 0.1 probability to schedule transmission on transmission resource 2. The other transmission resources are similarly indicated in Table 4.
[0084] Additionally, in some implementations, the exchanged information may only include the probability that the network device 104 may schedule transmission on the transmission resource or the probability that the network device 104 may not schedule transmission on the transmission resource. The first network device 104 (1) may send the second network device 104 (2) at least one of the predicted scheduling state or the probability. When the second network device 104 (2) receives the at least one of the predicted scheduling state or the probability, the second network device 104 (2) may first use the transmission resource that is not used by the first network device 104 (1) . Accordingly, through performance of the above-described implementations, the first network device 104 (1) and the second network device 104 (2) may use as different of transmission resources as possible to avoid the interference between each other. By relying on the model prediction, a more accurate scheduling state may be obtained, and in turn, interference handling performance may be improved.
[0085] Embodiment 4
[0086] In some implementations, the first network device (e.g., first base station) 104 (1) may perform model training for both an encoder and a decoder. The first base station 104 (1) may transfer the model of the encoder or the decoder to the second network device (e.g., second base station) 104 (2) .
[0087] Additionally, in some implementations, the first network device 104 (1) may train the decoder model. In addition or alternatively, the second network device 104 (2) may train the encoder model. The first network device 104 (1) and the second network device 104 (2) may exchange the information for the model training. The information may include at least one of: channel state information (CSI) information or gradient information. For some of these implementations, the same decoder model may be used if there are more than one second base station 104 (2) .
[0088] Additionally, in some implementations, the first network device 104 (1) may train the model for both the encoder and the decoder. The first network device 104 (1) may send the dataset of the encoder to the second base station. The second network device 104 (2) may use the dataset to train its model of the encoder.
[0089] Additionally, in some implementations, the second network device 104 (2) may measure the first set of one or more resources to obtain one or more measurement results. The measurement result (s) may be encoded with the encoder. The output of the encoder may be the encoded measurement result (s) . The second network device 104 (2) may send the encoded measurement result (s) to the first network device 104 (1) . The first network device 104 (1) may use the decoder to decode the encoded measurement result (s) to obtain the measurement result (s) . The measurement result (s) may include at least channel state information in addition to the result (s) as previously described in the above implementations.
[0090] Additionally, in some implementations, the second network device 104 (2) may send the measurement result (s) to the first network device 104 (1) . The first network device 104 (1) may use the measurement result (s) to determine a performance of the model of the decoder and / or the encoder. The first network device 104 (1) may compare the received measurement result (s) with the decoded measurement result (s) . If the received measurement results and the decoded measurement results are close (e.g., within a certain threshold, upper or lower bound, tolerance, or percent deviation or error, as non-limiting examples) , then the first network device 104 (1) may determine that the performance of the model of the decoder and / or the encoder is satisfactory. In turn, the first network device 104 (1) may continue using the decoder, and the second network device 104 (2) may continue using the encoder. On the other hand, if the received measurement result (s) and the decoded measurement results are not close (e.g., are not within a certain threshold, upper or lower bound, tolerance, or percent deviation or error, as non-limiting examples) , then the first network device 104 (1) may determine that the performance of the decoder or encoder is unsatisfactory. In turn, the first network device 104 (1) and / or the second network device 104 (2) may train a new model of the encoder and / or the decoder.
[0091] Additionally, in some implementations, an interference level may be used to determine the performance of the model. The model of the encoder and / or the decoder may be used by the first network device 104 (1) and / or the second network device 104 (2) . The second network device 104 (2) may measure the resource to obtain the interference in accordance with the above-described implementations. If the interference (e.g., the DL interference from first network device 104 (1) to the second network device 104 (2) ) is larger than or equal to an interference threshold, then the second network device 104 (2) may determine that the performance of the model of the encoder and / or the decoder may be unsatisfactory. In turn, the first network device 104 (1) and / or the second network device 104 (2) may train the new model of the encoder and / or the decoder. On the other hand, if the interference (e.g., the DL interference from first network device 104 (1) to the second network device 104 (2) ) is smaller than or equal to an interference threshold, then the second network device 104 (2) may determine that the performance of the model of the decoder and / or the encoder may be satisfactory. In turn, the first network device 104 (1) may continue using the decoder, and / or the second network device 104 (2) may continue using the encoder.
[0092] Accordingly, through performance of these implementations, the exchanged information overhead between the first and second network devices 104 (1) , 104 (2) can be reduced and / or the accuracy of the measurement results can be improved.
[0093] In some implementations, the network device 104 may configure one or more bandwidth parts (BWP) for the user device 102. The user device 102 may receive a configuration that include one or more BWP from the network device 104. The user device 102 may receive a downlink control information (DCI) format from the network device 104. The DCI format may schedule one or more PUSCH or PDSCH. The one or more PUSCH or PDSCH may be transmitted on one or more serving cells. Each of the one or more PUSCH or PDSCH may be transmitted on the respective serving cell. The network device 104 may configure whether a BWP indicator field is included in the DCI format by a medium access control (MAC) control element (CE) or an RRC signaling. The network device 104 may transmit the MAC CE or the RRC signaling to the user device 102. The length of the BWP indicator field may be determined by the number of BWP. For example, the length of the BWP indicator field may be where X is the number of BWP and [log2X] is the ceiling operation.
[0094] Additionally, in some implementations, the network device 104 may configure the BWP indicator field to be in the DCI format. In other implementations, the BWP indicator field is in the DCI format when the network device 104 configures one or more BWP for the user device 102. The user device 102 may indicate (or report) to the network device 104 the capability of supporting BWP switching for the DCI format. For example, the user device 102 may indicate to the network device 104 whether the user device 102 can support the BWP switching for the DCI format. If the user device 102 does not support BWP switching for the DCI format, or such information is indicated by the user device 102 to the network device 104, the user device 102 may ignore the BWP indicator field or the BWP indicator field may be reserved. If the user device 102 supports BWP switching for the DCI format, or such information is indicated by the user device 102 to the network device 104, the user device 102 may not ignore the BWP indicator field or the BWP indicator field may not be reserved. Alternatively, the network device 104 may configure the BWP indicator field to not be in the DCI format.
[0095] In addition or alternatively, whether the BWP indicator field is in the DCI format is determined by the user device 102 capability. The user device 102 capability may include whether the user device 102 supports the BWP switching for the DCI format. If the user device 102 does not support BWP switching for the DCI format, or such information is indicated by the user device 102 to the network device 104, the BWP indicator field may not be included in the DCI format. If the user device 102 supports BWP switching for the DCI format, or such information is indicated by the user device 102 to the network device 104, the BWP indicator field may be included in the DCI format.
[0096] Accordingly, through performance of these implementations, the user device 102 and / or the network device 104 can determine the size of the DCI format. The user device 102 and the network device 104 may have the same understanding on the size of the DCI format and in turn the user device 102 can receive the DCI format successfully from the network device 104.
[0097] The description and accompanying drawings above provide specific example embodiments and implementations. The described subject matter may, however, be embodied in a variety of different forms and, therefore, covered or claimed subject matter is intended to be construed as not being limited to any example embodiments set forth herein. A reasonably broad scope for claimed or covered subject matter is intended. Among other things, for example, subject matter may be embodied as methods, devices, components, systems, or non-transitory computer-readable media for storing computer codes. Accordingly, embodiments may, for example, take the form of hardware, software, firmware, storage media or any combination thereof. For example, the method embodiments described above may be implemented by components, devices, or systems including memory and processors by executing computer codes stored in the memory.
[0098] Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment / implementation” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment / implementation” as used herein does not necessarily refer to a different embodiment. It is intended, for example, that claimed subject matter includes combinations of example embodiments in whole or in part.
[0099] In general, terminology may be understood at least in part from usage in context. For example, terms, such as “and” , “or” , or “and / or, ” as used herein may include a variety of meanings that may depend at least in part on the context in which such terms are used. Typically, “or” if used to associate a list, such as A, B or C, is intended to mean A, B, and C, here used in the inclusive sense, as well as A, B or C, here used in the exclusive sense. In addition, the term “one or more” as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a, ” “an, ” or “the, ” may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.
[0100] Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present solution should be or are included in any single implementation thereof. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present solution. Thus, discussions of the features and advantages, and similar language, throughout the specification may, but do not necessarily, refer to the same embodiment.
[0101] Furthermore, the described features, advantages and characteristics of the present solution may be combined in any suitable manner in one or more embodiments. One of ordinary skill in the relevant art will recognize, in light of the description herein, that the present solution can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the present solution.
[0102] The subject matter of the disclosure may also relate to or include, among others, the following aspects:
[0103] A first aspect includes a method for wireless communication that includes: transmitting, by a first network device, a signal; and in response to transmitting the signal, receiving, by the first network device from a second network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0104] A second aspect includes a method for wireless communication that includes: receiving, by a second network device, a signal; and in response to receiving the signal, transmitting, by the second network device to a first network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.
[0105] A third aspect includes any of the first or second aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one measurement result, wherein the at least one measurement result is based on a set of one or more resources, and wherein each resource of the set corresponds to a respective one of the at least one measurement result.
[0106] A fourth aspect includes any of the first through third aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one predicted result, and wherein each of the at least one predicted result corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0107] A fifth aspect includes any of the first through fourth aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one predicted preferred resource, and wherein each of the at least one predicted preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0108] A sixth aspect includes any of the first through fifth aspects, wherein the first network device receives and / or the second network device transmits the at least one predicted non-preferred resource, and wherein each of the at least one predicted non-preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources. The future time instance is after a time instance of the set of one or more resources.
[0109] A seventh aspect includes any of the first through sixth aspects, and further includes wherein the first network device receives and / or the second network device transmits at least one of: the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability, and wherein the at least one of the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability is determined based on a model and an input for the model comprises at least one of the at least one measurement result or at least one time instance of the at least one measurement result.
[0110] An eighth aspect includes any of the first through seventh aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one predicted result, wherein each of the at least one predicted result corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one accuracy probability.
[0111] A ninth aspect includes the eighth aspect, and further includes wherein the at least one accuracy probability is determined based on a threshold.
[0112] A tenth aspect includes any of the first through ninth aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one predicted preferred resource, wherein each of the at least one predicted preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one preferred probability.
[0113] An eleventh aspect includes any of the first through tenth aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one predicted non-preferred resource, wherein each of the at least one predicted non-preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one non-preferred probability.
[0114] A twelfth aspect includes any of the first through eleventh aspects, and further includes wherein a model has a requirement, the method further comprising: in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, receiving, by the first network device from the second network device, an indication that the model cannot satisfy the requirement.
[0115] A thirteenth aspect includes any of the first through twelfth aspects, and further includes wherein a model has a requirement, the method further comprising: in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, changing, by the second network device, the model to a different model, or indicating, by the second network device to the first network device, that the model cannot satisfy the requirement.
[0116] A fourteenth aspect includes any of the first through thirteenth aspects, and further includes: receiving, by the first network device from the second network device, at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.
[0117] A fifteenth aspect includes any of the first through fourteenth aspects, and further includes: transmitting, by the second network device to the first network device, at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.
[0118] A sixteenth aspect includes any of the fourteenth or fifteenth aspects, and further includes wherein the first network device receives and / or the second network device transmits at least one of: the at least one predicted scheduling state or the at least one second probability, wherein the at least one of the at least one predicted scheduling state or the at least one second probability is determined based on a model and an input for the model comprises at least one of: at least one previous scheduling state or data to be transmitted.
[0119] A seventeenth aspect includes any of the fourteenth through sixteenth aspects, and further includes wherein the first network device receives and / or the second network device transmits the at least one second probability, and wherein one of the at least one second probability corresponding to one of the at least one transmission resource comprises a probability that the second network device schedules a transmission on the one of the at least one transmission resource or a probability that the second network device does not schedule the transmission on the one of the at least one transmission resource.
[0120] An eighteenth aspect includes any of the first through seventeenth aspects, and further includes wherein the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability corresponds to a respective one of at least one transmission resource.
[0121] A nineteenth aspect includes a wireless communications apparatus that includes at least one processor and a memory, wherein the at least one processor is configured to cause the apparatus to perform any of the first through eighteenth aspects.
[0122] A twentieth aspect includes a computer program product that includes a computer-readable program medium comprising code stored thereupon, the code, when executed by a processor, causing the processor to implement any of the first through eighteenth aspects.
[0123] In addition to the features mentioned in each of the independent aspects enumerated above, some examples may show, alone or in combination, the optional features mentioned in the dependent aspects and / or as disclosed in the description above and shown in the figures.
Claims
1.A method for wireless communication, the method comprising:transmitting, by a first network device, a signal; andin response to transmitting the signal, receiving, by the first network device from a second network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.2.A method for wireless communication, the method comprising:receiving, by a second network device, a signal; andin response to receiving the signal, transmitting, by the second network device to a first network device, at least one of: at least one measurement result, at least one time instance, at least one predicted result, at least one probability, at least one preferred resource, at least one non-preferred resource, at least one predicted preferred resource, at least one predicted non-preferred resource, at least one model of an encoder, at least one model of a decoder, or at least one dataset for a model training.3.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one measurement result, wherein the at least one measurement result is based on a set of one or more resources, and wherein each resource of the set corresponds to a respective one of the at least one measurement result.4.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted result, and wherein each of the at least one predicted result corresponds to a future time instance or a respective resource that is not in the set of one or more resources, wherein the future time instance is after a time instance of the set of one or more resources.5.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted preferred resource, and wherein each of the at least one predicted preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources, wherein the future time instance is after a time instance of the set of one or more resources.6.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted non-preferred resource, and wherein each of the at least one predicted non-preferred resource corresponds to a future time instance or a respective resource that is not in the set of one or more resources, wherein the future time instance is after a time instance of the set of one or more resources.7.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits at least one of: the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability, and wherein the at least one of the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability is determined based on a model and an input for the model comprises at least one of the at least one measurement result or at least one time instance of the at least one measurement result.8.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted result, wherein each of the at least one predicted result corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one accuracy probability.9.The method of claim 8, wherein the at least one accuracy probability is determined based on a threshold.10.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted preferred resource, wherein each of the at least one predicted preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one preferred probability.11.The method of any of claims 1 or 2, wherein the first network device receives and / or the second network device transmits the at least one predicted non-preferred resource, wherein each of the at least one predicted non-preferred resource corresponds to a respective one of the at least one probability, and wherein the at least one probability comprises at least one non-preferred probability.12.The method of claim 1, wherein a model has a requirement, the method further comprising:in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, receiving, by the first network device from the second network device, an indication that the model cannot satisfy the requirement.13.The method of claim 2, wherein a model has a requirement, the method further comprising:in response to an actual number of qualified predictions within a time duration or a qualified ratio being less than a threshold number, changing, by the second network device, the model to a different model, or indicating, by the second network device to the first network device, that the model cannot satisfy the requirement.14.The method of claim 1, further comprising:receiving, by the first network device from the second network device, at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.15.The method of claim 2, further comprising:transmitting, by the second network device to the first network device, at least one of: at least one scheduling state, at least one predicted scheduling state, or at least one second probability, wherein each of the at least one predicted scheduling state and / or each of the at least one second probability corresponds to a respective one of at least one transmission resource.16.The method of any of claims 14 or 15, wherein the first network device receives and / or the second network device transmits at least one of: the at least one predicted scheduling state or the at least one second probability, wherein the at least one of the at least one predicted scheduling state or the at least one second probability is determined based on a model and an input for the model comprises at least one of: at least one previous scheduling state or data to be transmitted.17.The method of any of claims 14 or 15, wherein the first network device receives and / or the second network device transmits the at least one second probability, and wherein one of the at least one second probability corresponding to one of the at least one transmission resource comprises a probability that the second network device schedules a transmission on the one of the at least one transmission resource or a probability that the second network device does not schedule the transmission on the one of the at least one transmission resource.18.The method of claim 1 or 2, wherein the at least one predicted result, the at least one predicted preferred resource, the at least one predicted non-preferred resource, or the at least one probability corresponds to a respective one of at least one transmission resource.19.A wireless communications apparatus comprising at least one processor and a memory, wherein the at least one processor is configured to cause the apparatus to perform a method of any of claims 1 to 18.20.A computer program product comprising a computer-readable program medium comprising code stored thereupon, the code, when executed by a processor, causing the processor to implement a method of any of claims 1 to 18.
Citation Information
Patent Citations
Communication method, terminal, network device and communication system
CN117378237A
Machine learning model selection in beamformed communications
US20210328630A1
Qualifying machine learning-based CSI prediction
US20210376895A1
Machine learning models for predictive resource management
WO2023168589A1
Validation of artificial intelligence (AI) / machine learning (ML) in beam management and hierarchical beam prediction
WO2024030604A1