Apparatus and method for generating training data for radio aware digital twinning

Abstract

Example embodiments provide a method for obtaining marked training data for radio aware digital twinning. The method does not require any reference symbol transmission. Accordingly, downlink overhead may be reduced. An apparatus, method and computer program are disclosed.

Description

Technical Field

[0001] The present application relates generally to information technology and, in particular, to generating training data for radio-aware digital twins. Background Art

[0002] A digital twin (DT) can be a digital or virtual representation of a physical asset or process. A digital twin can be updated based on changes in the physical environment. A digital twin can be modeled by a data-driven approach using machine learning. Summary of the invention

[0003] This Summary is provided to introduce selected concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0004] Example embodiments enable the generation and acquisition of labeled training data for digital twin applications. Labeled training data can be generated without the need for dedicated reference symbol transmission for this purpose. Thus, downlink overhead can be reduced. This can be achieved by the features of the independent claims. Further implementation forms are provided in the dependent claims, the description and the drawings.

[0005] According to a first aspect, a user node is disclosed. The user node may include at least one processor; and at least one memory including computer program code; the at least one memory and the computer code are configured to, together with the at least one processor, cause an apparatus to at least: receive a message from a network node in a radio access network, the message including at least configuration information for sampling of a physical downlink channel; perform sampling on a transmission of the physical downlink channel based on the configuration information, the physical downlink channel being received on a time-frequency resource allocated for the physical downlink channel; and generate a measurement report including one or more samples from the sampled transmission; and transmit the measurement report to the network node.

[0006] According to an example embodiment of the first aspect, at least one memory and computer code are configured to, with at least one processor, a user node: store one or more samples from a sampled transmission.

[0007] According to an exemplary embodiment of the first aspect, the configuration information includes at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot where sampling starts; an index of an orthogonal frequency division multiplexing (OFDM) symbol in the time slot where sampling starts; and an index of one or more resource units on which sampling is to be performed; the number of OFDM symbols on which sampling is to be performed; and a frequency range or bandwidth on which sampling is to be performed.

[0008] According to an exemplary embodiment of the first aspect, the configuration information comprises a period for repeated sampling.

[0009] According to an exemplary embodiment of the first aspect, the configuration information comprises a position and an orientation of a user node which is to perform sampling.

[0010] According to an example embodiment of the first aspect, the configuration information comprises an allocation of uplink resources on a physical uplink channel for a user node to send a measurement report to a network node, the allocation of uplink resources comprising at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

[0011] According to an example embodiment of the first aspect, the configuration information comprises a number of quantization bits used for generating the measurement report.

[0012] According to an example embodiment of the first aspect, the configuration information comprises a threshold value indicating whether samples from a sampled transmission are to be included in the measurement report.

[0013] According to an example embodiment of the first aspect, generating the measurement report comprises at least one of quantizing one or more samples, source encoding the one or more samples, selecting one or more samples based on a threshold, and combining the one or more samples.

[0014] According to an example embodiment of the first aspect, at least one memory and computer code are configured to, with at least one processor, with a user node: transmit a measurement report based at least on a location of the user node in a radio access network and / or radio conditions of the radio access network.

[0015] According to an example embodiment of the first aspect, at least one memory and computer code are configured to, with at least one processor, a user node: modify a trajectory to arrive within an area with good coverage from a network node, or within an area of ​​coverage by a dedicated access point, or a location set by a network node for performing sampling.

[0016] According to an example embodiment of the first aspect, the measurement report comprises an indication indicating a position and / or orientation of the user node.

[0017] According to a second aspect, a method performed by a user node in a radio access network is disclosed. The method comprises: receiving a message from a network node in the radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; performing sampling of transmissions of the physical downlink channel based on the configuration information, the physical downlink channel being received on time-frequency resources allocated for the physical downlink channel; generating a measurement report comprising one or more samples from the sampled transmissions; and transmitting the measurement report to the network node.

[0018] According to an example embodiment of the second aspect, the method comprises storing one or more samples from the sampled transmission.

[0019] According to an exemplary embodiment of the second aspect, the configuration information includes at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot where sampling starts; the index of the orthogonal frequency division multiplexing OFDM symbol where the sampling starts in the time slot; and the index of one or more resource units on which sampling is to be performed; the number of OFDM symbols on which sampling is to be performed; and the frequency range or bandwidth on which sampling is to be performed.

[0020] According to an exemplary embodiment of the second aspect, the configuration information comprises a period for repeated sampling.

[0021] According to an example embodiment of the second aspect, the configuration information comprises a position and an orientation of a user node which is to perform sampling.

[0022] According to an example embodiment of the second aspect, the configuration information includes an allocation of uplink resources on a physical uplink channel for a user node to send a measurement report to a network node, the allocation of uplink resources including at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

[0023] According to an example embodiment of the second aspect, the configuration information comprises a number of quantization bits used for generating the measurement report.

[0024] According to an example embodiment of the second aspect, the configuration information comprises a threshold indicating whether samples from the sampled transmission are to be included in the measurement report.

[0025] According to an example embodiment of the second aspect, generating the measurement report comprises at least one of: quantizing one or more samples; source encoding one or more samples; selecting one or more samples based on a threshold; and combining one or more samples.

[0026] According to an example embodiment of the second aspect, the method comprises transmitting a measurement report based at least on a location of the user node in the radio access network and / or on radio conditions of the radio access network.

[0027] According to an example embodiment of the second aspect, the method comprises modifying the trajectory to arrive within an area with good coverage from a network node, or within an area of ​​coverage by a dedicated access point, or a location set by a network node for performing sampling.

[0028] According to an example embodiment of the second aspect, the measurement report comprises an indication indicating a position and / or orientation of the user node.

[0029] According to a third aspect, a computer program or a computer program product is disclosed. The computer program (product) may be configured to, when executed by a processor, cause a device to perform at least the following operations: receive a message from a network node in a radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; perform sampling on a transmission of the physical downlink channel based on the configuration information, the physical downlink channel being received on a time-frequency resource allocated for the physical downlink channel; generate a measurement report comprising one or more samples from the sampled transmission; and transmit the measurement report to the network node. The computer program may also include instructions for causing the device to perform any example embodiment of the method of the second aspect.

[0030] According to a fourth aspect, an apparatus may include: a component for receiving a message from a network node in a radio access network, the message including at least configuration information for sampling of a physical downlink channel; a component for performing sampling on a transmission of the physical downlink channel based on the configuration information, the physical downlink channel being received on a time-frequency resource allocated for the physical downlink channel; a component for generating a measurement report including one or more samples from the sampled transmission; and a component for transmitting the measurement report to the network node. The device may also include a component for performing any example embodiment of the method of the second aspect.

[0031] According to a fifth aspect, a network node in a radio access network may include: at least one processor; and at least one memory including computer program code; the at least one memory and the computer code are configured to, together with the at least one processor, enable the network node to at least: transmit a message to a user node in the radio access network, the message including at least configuration information for sampling of a physical downlink channel; perform transmission on the physical downlink channel; receive a measurement report from the user node, the measurement report including one or more samples from the transmission; and determine one or more parameters based on the transmission and the received measurement report; and transmit one or more parameters to a digital twin application.

[0032] According to an example embodiment of the fifth aspect, at least one memory and computer code are configured to, together with at least one processor, cause a network node to: transmit a message to a user node in response to receiving a request from a digital twin application.

[0033] According to an exemplary embodiment of the fifth aspect, the configuration information includes at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot where sampling starts; the index of the OFDM symbol from which sampling starts in the time slot; the index of one or more resource units on which sampling is to be performed, the number of OFDM symbols on which sampling is to be performed, and the frequency range or bandwidth on which sampling is to be performed.

[0034] According to an exemplary embodiment of the fifth aspect, the configuration information comprises a period for repeated sampling.

[0035] According to an example embodiment of the fifth aspect, the configuration information comprises a position and an orientation of a user node which is to perform sampling.

[0036] According to an exemplary embodiment of the fifth aspect, the configuration information includes an allocation of uplink resources on a physical uplink channel for a user node to send a measurement report to a network node, and the allocation of uplink resources includes at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

[0037] According to an example embodiment of the fifth aspect, the configuration information comprises a number of quantization bits used for generating the measurement report.

[0038] According to an example embodiment of the fifth aspect, the configuration information comprises a threshold indicating whether a sample from the sampled transmission is to be included in the measurement report.

[0039] According to an example embodiment of the fifth aspect, the measurement report comprises an indication of a position and / or orientation of the user node.

[0040] In a sixth aspect, a method performed by a network node in a radio access network is disclosed. The method may include: transmitting a message to a user node in the radio access network, the message including configuration information for sampling of at least a physical downlink channel; performing a transmission on the physical downlink channel; receiving a measurement report from the user node, the measurement report including one or more samples from the transmission; determining one or more parameters based on the transmission and the received measurement report; and transmitting the one or more parameters to a digital twin application.

[0041] According to an example embodiment of the sixth aspect, the method may include: transmitting a message to a user node in response to receiving a request from a digital twin application.

[0042] According to an exemplary embodiment of the sixth aspect, the configuration information includes at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot where sampling starts; the index of the OFDM symbol from which sampling starts in the time slot; the index of one or more resource units on which sampling is to be performed; the number of OFDM symbols on which sampling is to be performed; and the frequency range or bandwidth on which sampling is to be performed.

[0043] According to an exemplary embodiment of the sixth aspect, the configuration information includes a period for repeated sampling.

[0044] According to an example embodiment of the sixth aspect, the configuration information comprises a position and an orientation of a user node which is to perform sampling.

[0045] According to an example embodiment of the sixth aspect, the configuration information includes an allocation of uplink resources on a physical uplink channel for a user node to send a measurement report to a network node, and the allocation of uplink resources includes at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

[0046] According to an example embodiment of the sixth aspect, the configuration information comprises a number of quantization bits used for generating the measurement report.

[0047] According to an example embodiment of the sixth aspect, the configuration information comprises a threshold indicating whether samples from the sample transmission are to be included in the measurement report.

[0048] According to an example embodiment of the sixth aspect, the measurement report comprises an indication of a position and / or orientation of the user node.

[0049] According to the seventh aspect, a computer program or a computer program product is disclosed. The computer program (product) may be configured to cause the device to perform at least the following operations when executed by a processor: a user node in a radio access network transmits a message including at least configuration information for sampling of a physical downlink channel; performs transmission on a physical downlink channel; receives a measurement report from a user node, the measurement report including one or more samples from the transmission; determines one or more parameters based on the transmission and the received measurement report; and transmits one or more parameters to a digital twin application. The computer program may also include instructions for causing the device to perform any example embodiment of the method of the sixth aspect.

[0050] According to an eighth aspect, an apparatus may include: a component for transmitting a message to a user node in a radio access network, the message including configuration information for sampling at least for a physical downlink channel; performing a transmission on a physical downlink channel; a component for receiving a measurement report from a user node, the measurement report including one or more samples from the transmission; a component for determining one or more parameters based on the transmission and the received measurement report; and transmitting one or more parameters to a digital twin application. The apparatus may also include a component for performing any example embodiment of the method of the sixth aspect.

[0051] Many of the attendant features will be more readily understood by reference to the following detailed description considered in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are included to provide a further understanding of example embodiments and constitute a part of this specification, illustrate example embodiments and together with the description help explain example embodiments. In the drawings:

[0053] Figure 1 An example of a communication network including at least one network node and at least one user node according to an example embodiment is shown;

[0054] Figure 2 An example of a message sequence chart for generation of training data for a digital twin according to an example embodiment is shown;

[0055] Figure 3 An example of an apparatus configured to practice one or more example embodiments is shown;

[0056] Figure 4 An example of a flowchart illustrating a method of performing sampling by a user node to train a digital twin according to an example embodiment; and

[0057] Figure 5 An example of a flowchart of a method for obtaining measurement reports by a network node to train a digital twin according to an example embodiment is shown.

[0058] In the drawings, the same reference numerals are used to denote the same components. DETAILED DESCRIPTION

[0059] Reference will now be made in detail to example embodiments, examples of which are illustrated in the accompanying drawings. The specific embodiments provided below in conjunction with the drawings are intended as a description of this example and are not intended to represent the only form in which this example may be constructed or utilized. The description sets forth the functions of the example and possible sequences of operations for constructing and operating the example. However, the same or equivalent functions and sequences may be implemented by different examples.

[0060] A digital twin (DT) is a digital or virtual representation of a physical asset, system, or process. Using a digital twin can help predict problems and find the best solutions even before they actually occur. DT can leverage a wide range of technologies, including IoT, machine learning, and big data, to create digital simulation models that can change as physical entities change. Based on historical knowledge and data from other systems, DT can continuously learn from sources connected to physical entities and update itself accordingly in real time. DT can focus on maintaining a complete history and up-to-date information of physical assets / systems to support intelligent and data-backed decisions. Digital twins can provide feedback on how to optimize operations and achieve higher levels of productivity and efficiency.

[0061] DT can depict the network and users, for example, by digital modeling of the external environment of network elements and service characteristics. Radio-aware DT refers to a digital representation of the radio propagation environment. Radio-aware DT can have knowledge of the radio network. The knowledge of the wireless network can include all sending and receiving nodes, the location of the nodes, and the radio capabilities of the nodes. DT can maintain a database called a radio environment map (REM). REM can have information about radio propagation and / or channel quality in a geographical area of ​​the radio network. The radio network can be divided into boxes of, for example, N×M square meters.

[0062] Such a DT can map independent variables in a communication system to the signal to interference and noise ratio (SINR) / block error rate (BLER) of a communication link between nodes of the communication system. The nodes may include, for example, user equipment (UE) and base station (BS). For example, the independent variables may include, for example, interference source location, orientation and trajectory, transmit power, time and frequency resource allocation, and propagation environment characteristics.

[0063] Digital twin applications can be used, for example, in the fields of manufacturing, automotive, healthcare, and environmental industries. In the factory of the future, at least some UEs may be machines. Machines may include, for example, automated guided vehicles (AGVs), unmanned aerial vehicles (UAVs), drones, and / or fixed machines. The trajectories of these UEs are known or can be precisely controlled.

[0064] By predicting the radio conditions at the UE without explicit measurements or reference symbol transmission, radio-aware DT can be used to proactively or intentionally perform time-frequency resource allocation, modulation and coding scheme (MCS) adaptation, decisions about handover, etc. Therefore, radio-aware DT can improve the spectrum and energy efficiency of the network.

[0065] Radio-aware DTs may require an accurate model of the propagation environment. DT and REM databases may need to be constantly updated to account for changes in the environment. Some methods for modeling the radio propagation environment, such as ray tracing, may not be accurate because they do not capture all modes of electromagnetic propagation. In addition, some methods, such as finite element methods, may be too computationally intensive to be used in real-time operations. Data-driven methods using machine learning can provide a good compromise between modeling accuracy and computational complexity.

[0066] Machine learning models for radio sensing DT may require a large amount of labeled training data, which needs to be obtained from measurements. Such data may also be required to keep the REM database updated. Making these measurements may require reference symbols, such as UE-specific demodulation reference symbols (DMRS) or channel state information reference symbols (CSI-RS) to be transmitted, which increases the total overhead. In time-varying propagation environments with a large number of sensor nodes, such as warehouses or ports, measurements need to be made regularly, and the overhead may become too large.

[0067] Furthermore, for example, AGVs and UAVs may be equipped with inexpensive narrowband RX dedicated radio frequency (RF) chains whose sole purpose is to generate measurement data at various antenna positions and orientations simultaneously. Thus, measurements may be performed in the downlink (DL). Therefore, uplink (UL) measurements (with UL / DL reciprocity at the BS) may not be a viable option for generating labeled training data.

[0068] One approach involves using UE-specific CSI-RS and / or DMRS transmitted by the network. The UE can then use these reference symbols to perform measurements and send them back to the network. However, this approach requires additional overhead that varies with the number of UEs in the network.

[0069] Minimization of Drive Tests (MDT) is a standardized feature in 3GPP LTE / NR. In MDT, normal UEs can be made to collect certain key performance indicators (KPIs), such as radio link failures, which can then be reported back to the network. The report can include the location of the UE. In this way, operators can collect useful information about the actual performance in a live network. However, this method requires the transmission of additional reference symbols for measurement.

[0070] Analog channel state information (CSI) is the concept of the UE amplifying the unquantized received observations and forwarding them back to the network. While this concept also has the feature of not requiring additional reference symbol transmissions to update the DT, it is corrupted by additional noise and interference at the base station. Therefore, the quality of the labeled training data for the DT may be poor.

[0071] According to an example embodiment, a method for obtaining labeled training data for a DT is provided. Advantageously, the example embodiment can reduce the downlink overhead of reference symbol transmission when generating labeled training data for a machine learning model of a radio propagation environment. The method can include compressing measurement information to be sent from a UE to a network. The method can also obtain channel state information at the network from UE measurements.

[0072] As described above, example embodiments can achieve lower DL overhead. When training a machine learning model for radio-aware DT, a large amount of measurement data may be required. Therefore, transmitting CSI-RS and DMRS for this purpose will increase the DL overhead. To this end, in the proposed method, the UE can be configured to observe user or control plane data and transmit unprocessed or quantized samples back to the network. The received samples can be transmitted with additional tags, such as the time and frequency location of the resource unit and / or the position and orientation of the UE when receiving the samples. The method does not require the transmission of dedicated reference symbols in the DL. Since there is no additional DL overhead associated with the method, transmitting the original / quantized samples back to the network can quickly generate a large amount of labeled training data for the machine learning algorithm. The network then analyzes the data transmitted back and obtains relevant parameters, such as SINR / channel statistics.

[0073] Example embodiments may enable measurements with higher time-frequency resolution. Typically, CSI-RS or DMRS are limited by their proximity in time or frequency, since transmitting these reference symbols in time or frequency typically increases the DL overhead. Therefore, reference symbol-based measurements may have low resolution. However, since the proposed method relies on sending samples of DL user plane data or control plane data back to the network, the time-frequency resolution can be as high as a single RE, i.e., 1 subcarrier spacing in frequency and 1 OFDM symbol duration in time. This enables the DT to learn a high-resolution model of the channel evolution in time and frequency.

[0074] Figure 1 An example of a communication network 100 including at least one network node and at least one user node is shown. A network node may also be referred to as a base station, such as a gNB. The communication network 100 may include one or more core network elements, such as, for example, an access and mobility management function (AMF) and / or a user plane function (UPF). The communication network 100 may also include one or more client nodes, which may also be referred to as user nodes or UEs. For example, the communication network 100 may include a UE 104. The network elements AMF / UPF and gNB may generally be referred to as network nodes or network devices.

[0075] In an embodiment, UE 104 may be an AGV, UAV, drone, or some other mobile measurement platform. In an embodiment, UE 104 may be any mobile or fixed machine, for example, operating in a factory environment. In an embodiment, UE 104 may be or include a sensor node. The sensor node may be able to perform some processing, collect sensory information, location information (e.g., if the sensor node is not fixed at a certain location), and / or communicate with other connected nodes (such as base station 102) in the network. UE 104 may communicate with one or more of the base stations via a wireless radio channel. The communication between UE 104 and BS 102 may be bidirectional. Therefore, any of the devices may be configured to operate as a transmitter and / or receiver.

[0076] The base station and the UE may be configured to communicate with the core network element via a communication interface (e.g., a control plane interface or a user plane interface). The base station may also be referred to as a radio access network (RAN) node, and they may be part of a radio access network between the core network and the UE. Typically, a base station may include any suitable radio access point. In an embodiment, the communication network 100 may include one or more access points (APs), which may be low-range high-bandwidth access points, such as at millimeter wave or THz frequencies.

[0077] Although depicted as a single device, a network node may not be a stand-alone device, but rather a distributed computing system coupled to a remote radio head, for example. Various signaling information may be exchanged in the communication network 100 to provide information related to transmission parameters and allocation of radio resources for data transmission. The signaling information may be provided at various layers of the protocol stack.

[0078] The communication network 100 may include one or more digital twins. A digital twin may be an application running on a computing device. The DT may be configured to accurately model devices, communication links, operating environments, and / or applications running on the network. The digital twin may be a radio-aware digital twin. In an embodiment, the data associated with the DT may be distributed on a network, such as on a cloud or on several servers. Other nodes in the communication network may be physical twins, which are the basis and data source for the digital model of the DT. The DT may be, for example, a host of a data model, historical data of a physical twin, decision support, and / or artificial intelligence. The communication between the DT and other nodes may be bidirectional. The DT and other nodes may exchange data and control commands. The DT may, for example, request labeled training data from the BS 102 to update a machine learning model of the radio propagation environment of the network.

[0079] In an embodiment, UE 104 may observe the samples based on a configuration provided by BS 102, and BS 102 may be configured to provide the samples as labeled training data. BS 102 may be configured to transmit signal 106 via PDSCH / PDCCH. UE 104 may be configured to measure samples of the received PDSCH / PDCCH signal and send one or more of the received PDSCH / PDCCH samples 108 back to BS 102 via a physical uplink channel.

[0080] The communication network 100 may be configured, for example, according to a fifth generation digital cellular communication network defined by the Third Generation Partnership Project (3GPP). In one example, the communication network 100 may operate according to 3GPP 5G-NR. However, it should be understood that the example embodiments presented herein are not limited to the example network and may be applied to any current or future wireless or wired communication network or combination thereof, such as other types of cellular networks, short-range wireless networks, broadcast or multicast networks, etc.

[0081] Figure 2 An example of a message sequence chart for generating labeled training data of a radio network for a radio-aware DT according to an example embodiment is shown.

[0082] At 202 , the digital twin 200 may send a measurement request to the base station 102 to obtain labeled training data.

[0083] At 204, the base station 102 may configure measurement resources for the UE 104. In one embodiment, the BS 102 may send the time-frequency index of the PDSCH / PDCCH RE (resource unit) that the UE 104 expects to observe and send back to the network. The BS 102 may therefore, for example, send configuration information for sampling a received physical downlink signal, which is represented herein as a PDSCH / PDCCH signal, in a message. The configuration information may indicate the time-frequency resource on which the sampling is performed. The BS 102 may send the configuration information in response to receiving a measurement request from the DT 200 at 202. In an embodiment, the observed REs may correspond to PDSCH / PDCCH for different UEs. The BS 102 may also allocate uplink resources in the configuration so that the UE 104 sends a measurement report including the received samples back to the BS 102. The BS 102 may be configured to send the configuration information to the UE 104, for example, via a physical downlink control channel such as a PDCCH.

[0084] In an embodiment, BS 102 may instruct UE 104 to periodically sample transmissions received via a set of resource units. BS 102 may, for example, provide UE 104 with the respective time-frequency indices of REs on which sampling needs to be performed and the time period. Then, UE 104 may be configured to periodically sample received signals according to the RE pattern and the time period.

[0085] The configuration information may include, for example, a frame number, a time slot number in a frame identified by the frame number, a frequency range / bandwidth, an orthogonal frequency division multiplexing (OFDM) symbol index, a selected resource unit, and / or a period, for example, identified by an index of a resource unit. For example, the UE 104 may be configured to: start with OFDM symbol N1 in time slot S1 of frame F1 on bandwidth B1, and index every Pth OFDM symbol as RE1...RE " The K REs of the frame may be sampled. The frame number and the time slot number may indicate the time slot configured to start sampling. The OFDM symbol index may indicate the OFDM symbol configured to start sampling (e.g., within the time slot identified by the time slot index). The configuration information may include the location and / or orientation of the user node to perform sampling.

[0086] In an embodiment, BS 102 may be configured to instruct UE 104 to periodically sample transmissions over a plurality of OFDM symbols. In this case, the configuration information may include a frame number, a time slot number, an OFDM symbol index, the number of OFDM symbols on which sampling is to be performed, a bandwidth on which sampling is to be performed, and / or a period. The period may include, for example, an instruction to repeat sampling in every P OFDM symbols. Thus, it may be expected that the UE samples M consecutive OFDM symbols starting with OFDM symbol N1 in time slot S1 of frame F1 over bandwidth B1 with a period of P (P>M) OFDM symbols.

[0087] In an embodiment, BS 102 may be configured to instruct UE 104 to sample the transmission of the physical downlink channel over a number of OFDM symbols when UE 104 reaches a certain position L1 and 3D orientation O1 along its trajectory. In this case, the configuration information may include the position, the number of OFDM symbols on which sampling is to be performed, and / or the bandwidth on which sampling is to be performed.

[0088] The configuration information provided at 204 may include a configuration for resources for reporting sampled transmissions. The configuration may include, for example, a UL bandwidth portion, a UL PRB (physical resource block) index for transmitting the measurement report, an index of at least one UL time slot, and / or an index of at least one UL frame. The UE 104 may be configured to upload measurements on the configured UL resources. The configuration information may also include a number of quantization bits used to generate the measurement report, for example, to compress the samples before sending them to the BS 102. The configuration information may include a threshold value indicating whether to include samples from the sampled transmission in the measurement report. The threshold value may be related to the amplitude or power of the received samples.

[0089] At 206 , UE 104 may be configured to confirm configuration information to BS 102 .

[0090] At 208, BS 102 may be configured to transmit samples, for example, on a physical downlink shared channel. At 210, UE 104 may perform sampling of transmissions of PDSCH / PDCCH based on the configuration information received at operation 204. UE 104 may collect samples of the configured physical time-frequency resources, i.e., sample transmissions of the physical downlink channel on the time-frequency resources. UE 104 may be configured to store the samples.

[0091] To reduce UL transmission overhead, UE 104 may be configured to compress sampled transmissions. In an embodiment, UE 104 may be configured to compress data using quantization. UE 104 may be configured to quantize sampled transmissions sample by sample. Overhead may be determined directly based on the number of quantization bits. Based on the parameters being estimated, BS 102 may determine the number of quantization bits for the sample and provide the number of quantization bits in the configuration information at 204.

[0092] As an alternative to sample-by-sample quantization, compression can be accomplished by UE 104 with vector quantization. In vector quantization, the quantizer does not operate sample-by-sample, but rather operates on a vector of N REs on which the sampling is performed. Such a quantizer can provide improved performance in terms of quantization noise, but the complexity is higher than sample-by-sample quantization.

[0093] In an embodiment, the quantized bits or the unquantized bits may be source coded. Thus, redundancy may be reduced.

[0094] In an embodiment, BS 102 may be configured to instruct UE 104 to sample from multiple sets of REs. UE 104 may be configured to analyze each set of REs (or OFDM symbols) and transmit only the set that UE 104 determines to be useful. For example, UE 104 may transmit only the set for which the signal-to-noise ratio (SNR) exceeds a predetermined threshold. The predetermined threshold may be determined by BS 102. For example, the predetermined threshold for SNR may be set by BS 102 for the sampled transmissions in the configuration information at 204. Instead of SNR, BS 102 may configure the threshold for any other quantity.

[0095] In an embodiment, compression can be performed by combining multiple received samples. For example, BS102 can be configured to instruct UE 104 to transmit a set of samples and. For example, the samples can be transmitted using PDSCH transmission with quadrature phase shift keying (QPSK) modulation. Since BS102 knows the transmitted symbols, BS102 can be configured to request UE 104 to combine received symbols corresponding to the same transmitted symbols. For example, if the received observations are r1, r2, r3, and r4, BS102 can request UE 104 to report r1+r3 and r2+r4 instead of all four received observations. Therefore, BS102 knows that the same symbol is transmitted in r1 and r3 and r2 and r4, respectively.

[0096] At 212, UE 104 may generate and transmit a measurement report including a sample of the transmission sampled at operation 210. UE 104 is configured to forward the quantized and compressed samples to BS 102. The labeled training data generated for radio sensing DT is relatively delay-insensitive. In other words, the measurement report may be received at the network after a few seconds or minutes (depending on how fast the propagation environment changes). In an embodiment, the samples may be forwarded together with the position and 3D orientation of UE 104, associated with the time of the samples. Since the transmission may not be delay-sensitive, UE 104 may, for example, transmit the samples as enhanced mobile broadband (eMBB) traffic rather than ultra-reliable low-latency communication (URLLC) traffic. When the number of samples received is large, the transmission may also occur at a higher modulation and coding scheme due to the longer length of the codeword.

[0097] UE 104 may be configured to wait (or the trajectory may be modified) so that the measurement report may be uploaded to BS 102 at a very high data rate. In an embodiment, UE 104 may be configured to wait so that when transmitting the received samples, UE 104 is in an area with good coverage from BS 102. Thus, the transmission may occur with a higher modulation and coding scheme. Instead of waiting, the trajectory of UE 104 may be modified for improved coverage. The trajectory of UE 104 may be modified, for example, by DT 200 or BS 102. UE 104 may transmit the measurement report based at least on the location of UE 104 in the radio access network and / or the radio conditions of the radio access network.

[0098] In an embodiment, a network may include multiple dedicated APs with short coverage areas and relatively large bandwidths (e.g., at mmWave or THz frequencies). The dedicated APs may be installed in an area associated with the network to be modeled. The area may include, for example, a factory site. The UE 104 may store sampled transmissions until it is near a dedicated AP and then offload a large number of sampled transmissions.

[0099] In an embodiment, UL transmissions may be scheduled or initiated by DT 200 or BS 102 so that samples are sent when network traffic is low.

[0100] The network (such as BS102) can know both the desired DL signal and the interfering DL signal transmitted on the RE. In other words, the sampling of the DL transmission is already available at the network. Given this information, the network can obtain channel estimates for both the desired channel and the interfering channel. Since both data and channel estimates are available, the network can be configured to calculate UL / DL SINR, channel statistics, or any other parameters required for training the radio perception DT, and update the associated REM database. At 214, BS102 can be configured to provide labeled training data to the radio perception digital twin 200 based on the sampling received from UE 104. The labeled training data may include one or more parameters determined by BS102 based on the transmitted and received sampling.

[0101] For example, UE 104 may be a single antenna UE that receives payload data in the DL. Alternatively, UE 104 may be a multi-antenna UE. The network may have, for example, a total of L cells. UE 104 may be connected to a single serving cell, and there may be L-1 cells interfering with the UE. In the network, there may be more than L-1 interfering cells, but only the interference of the L-1 interfering cells may be above the noise floor.

[0102] Therefore, the nth symbol received at UE 104 can be written as: Among them, h $ is the channel between the lth BS and the UE, and x $n is the nth symbol transmitted by BS l. n is the additive white Gaussian noise at UE 104. It can be expressed as x n =[x 1n ,…,x ％n ] T and h=[h1,…,h ％ ] T A block fading model can be assumed where the channel remains approximately fixed within a coherent block.

[0103] By aggregating coherent blocks y = [y1, ..., y ( ] T For P ≥ L observations in the UE, we can obtain y = Xh + w, where X = [x1,…,x ( ] T .

[0104] Once UE 104 sends y back to BS 102 in the UL, BS 102 can calculate the value of y by multiplying y by X. + To recover h, where A + Denotes the Moore-Penrose pseudo-inverse matrix of A. Since X is a random matrix with entries from the QAM constellation, it may be column-full rank with high probability.

[0105] For a configuration with M antennas and using the precoding vector p $ The channel value h seen at UE 104 is $ is the effective channel, and is the channel vector and the precoding vector p $ In particular, in And h $+ is the channel value between UE 104 and antenna m of BS1. In this case, BS102 can estimate the “effective channel” h based on the above method. $ .

[0106] At 216, the digital twin 200 may train a machine learning model of the radio propagation environment using the labeled training data provided by the BS 102. Additionally, the data may be used to update the REM database.

[0107] Figure 3 An example of an apparatus 300 configured to practice one or more example embodiments is shown.

[0108] The apparatus 300 may include at least one processor 302. The at least one processor 302 may include, for example, one or more various processing devices such as, for example, a coprocessor, a microprocessor, a controller, a digital signal processor (DSP), processing circuitry with or without an accompanying DSP, or various other processing devices including integrated circuits (such as, for example, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), microcontroller units (MCUs), hardware accelerators, special purpose computer chips, etc.).

[0109] The apparatus 300 may also include at least one memory 304. The memory 304 may be configured to store, for example, computer program code 306, such as operating system software and application software. The memory 304 may include one or more volatile memory devices, one or more non-volatile memory devices, and / or a combination thereof. For example, the memory 304 may be embodied as a magnetic storage device (such as a hard disk drive, a magnetic tape, etc.), an optical magnetic storage device, or a semiconductor memory (such as a mask ROM, a PROM (programmable ROM), an EPROM (erasable PROM), a flash ROM, a RAM (random access memory), etc.).

[0110] The device 300 may also include one or more communication interfaces 308, which are configured to enable the device 300 to transmit information to other devices and / or receive information from other devices. The communication interface 308 can be configured to provide at least one wireless radio connection, such as, for example, a 3GPP mobile broadband connection (e.g., 3G, 4G, 5G). However, the communication interface 308 can be configured to provide one or more other types of connections, such as a wireless local area network (WLAN) connection, such as, for example, standardized by the IEEE 802.11 series or the Wi-Fi Alliance; a short-range wireless network connection, such as, for example, Bluetooth, NFC (near field communication) or RFID connection; a wired connection, such as, for example, a local area network (LAN) connection, a universal serial bus (USB) connection, or an optical network connection, etc.; or a wired Internet connection. The communication interface 308 may include or be configured to be coupled to at least one antenna to transmit and / or receive radio frequency signals. One or more of the various types of connections may also be implemented as a separate communication interface, which may be coupled to or configured to be coupled to multiple antennas.

[0111] The apparatus 300 may also include a user interface 310, which includes an input device and / or an output device. The input device may take various forms, such as a keyboard, a touch screen, or one or more embedded control buttons. The output device may include, for example, a display, a speaker, a vibration motor, etc.

[0112] When the device 300 is configured to implement some functions, some components and / or multiple components of the device 300 (such as, for example, at least one processor 302 and / or memory 304) can be configured to implement the functions. In addition, when the at least one processor 302 is configured to implement some functions, the functions can be implemented using the program code 306 included in, for example, the memory 304.

[0113] The functions described herein may be performed at least in part by one or more computer program product components such as software components. According to an embodiment, the device 300 includes a processor or a processor circuit system (e.g., a microcontroller) configured by a program code, and when the program code is executed, the processor or processor circuit is configured by the program code to perform the described operations and embodiments of the functions. Alternatively or additionally, the functions described herein may be performed at least in part by one or more hardware logic components. For example, but not limited to, illustrative types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and graphics processing units (GPUs).

[0114] The apparatus 300 includes components for performing at least one method described herein. In one example, the components include the at least one processor 302, and the at least one memory 304 includes program code 306, which is configured to cause the apparatus 300 to perform the method when executed by the at least one processor 302.

[0115] The apparatus 300 may include, for example, a computing device, such as, for example, a base station, a network node, a server device, a client node, a mobile phone, a tablet computer, a laptop computer, an Internet of Things (IoT) device, etc. In one example, the apparatus 300 may include a vehicle, such as, for example, an unmanned aerial vehicle. In an embodiment, the computing device may be configured to store and / or run an application that provides a digital twin of a radio propagation environment. Although the apparatus 300 is shown as a single device, it should be understood that the functionality of the apparatus 300 may be distributed to multiple devices wherever applicable. For example, the apparatus 300 may be distributed to multiple devices to implement an example embodiment as a cloud computing service.

[0116] Figure 4 An example of a flow chart of a method 400 for performing measurements by a user node to train a digital twin is shown according to an example embodiment.

[0117] At 402, the method may include receiving a message from a network node in a radio access network, the message including at least configuration information for sampling of a physical downlink channel. A user node may receive configuration information from the network node for performing sampling on a transmission of the physical downlink channel received via a physical time-frequency resource. The physical time-frequency resource may be an OFDM symbol or a subcarrier within an OFDM symbol. The smallest physical time-frequency resource may include one subcarrier in one OFDM symbol, referred to as a resource unit.

[0118] According to an example embodiment, the method may include: indicating, by a network node, to a user node, the location in time and frequency of certain resource elements (REs) allocated for a physical downlink shared channel (PDSCH) or a physical downlink control channel (PDCCH) on which sampling is performed. The method may also include indicating, by the network node, to the user node, the physical location and 3D orientation of the user node that needs to be sampled.

[0119] At 404, the method may include: based on the configuration information, performing sampling on a transmission of a physical downlink channel, the transmission of the physical downlink channel being received on a time-frequency resource allocated for the physical downlink channel. The user node may sample the transmission received via the physical downlink channel based on the configuration. The sampling may be stored at the user node. The method may also include compressing the sampling to be sent from the UE to the network. The user node may, for example, quantize the received sampling in the RE.

[0120] At 406, the method may include generating a measurement report including one or more samples from the sampled transmission.

[0121] At 408, the method may include transmitting a measurement report to the network node. The user node may send one or more samples to the network node via a physical uplink channel, such as a physical uplink shared channel (PUSCH). In an embodiment, the configuration information may include instructions for reporting the samples on the physical uplink channel.

[0122] In an embodiment, the user node may be configured to wait until the user node is within a good coverage area from a network node before sending a sample. In an embodiment, the user node may be configured to wait until it is near a dedicated low range high bandwidth access point before sending a sample to a network node. In an embodiment, the UE 104 may send the 3D position and orientation of the UE 104 along with the sample when sampling the network node.

[0123] In an embodiment, the user node may be configured to change its trajectory to reach a good coverage area or coverage area of ​​a dedicated access point, or a location indicated by BS120 for performing sampling. In an embodiment, the user node may be configured to wait until network traffic is low before sending a sample to the network node. In an embodiment, the user node may be configured to compress the sample before sending the sample to the network node. Compression may be performed based on instructions in the configuration information received from the network node. In an embodiment, UE104 may determine its position and / or orientation during sampling, and may include an indication of the determined position and / or orientation in an indication measurement report. This may be in response to receiving a request to do so from BS102, such as as part of the configuration information of operation 204.

[0124] Figure 5 An example of a flow chart of a method 500 for obtaining measurement reports by a network node to train a digital twin according to an example embodiment is shown.

[0125] At 502, the method may include receiving a request for labeled training data from a digital twin. The digital twin may include an application running on a computing device such as a network node. Operation 502 may be optional.

[0126] At 504, the method may include transmitting a message to a user node in the radio access network, the message including configuration information for at least sampling of a physical downlink channel. The network node may configure the user node to perform sampling on transmissions of the physical downlink channel received via the physical time-frequency resources. The network node may be configured to send the configuration information to the user node in response to a request received from the digital twin application.

[0127] At 506, the method may include performing transmission on a physical downlink channel.The network node may transmit data to the user node, for example, over a physical downlink channel.

[0128] At 508, the method may include receiving a measurement report from the user node, the measurement report including one or more samples from the transmission.When sampling, the network node may receive one or more samples of the sampled transmission and the 3D position and orientation of the UE from the user node over a physical uplink channel.

[0129] At 510, the method may include determining one or more parameters based on the transmitted and received measurement reports. The network node may determine one or more parameters for training a machine learning model of a radio propagation environment modeled by a digital twin application. The one or more parameters may be determined based on data transmitted by the network node and samples measured by the user node. The parameters may include, for example, UL / DL SINR or channel statistics. The method may also include obtaining channel state information from a user node measurement report at the network.

[0130] At 512, the method may include transmitting one or more parameters to the digital twin application. The network node may be configured to send the parameters to the digital twin application as labeled training data.

[0131] Another feature of the method is derived directly from the functions and parameters of the devices (such as network nodes and user nodes), as described in the attached claims and throughout the specification, and therefore not repeated here. It should be noted that one or more operations of the method may be performed in a different order.

[0132] An apparatus, such as a network node, a user node, or a client node, may be configured to perform any aspect of the method described herein or cause the performance of any aspect of the method described herein. In addition, a computer program may include instructions for causing an apparatus to perform any aspect of the method described herein when executed. In addition, an apparatus may include a component for performing any aspect of the method described herein. According to an example embodiment, the component includes at least one processor, and a memory including a program code, the at least one memory and the program code being configured to cause the performance of any aspect of the method when executed by the at least one processor.

[0133] Any range or device value given herein may be expanded or altered without losing the effect sought. In addition, any embodiment may be combined with another embodiment unless explicitly not permitted.

[0134] Although the subject matter has been described in language specific to structural features and / or acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Instead, the specific features and acts described above are disclosed as examples of implementing the claims, and other equivalent features and acts are intended to fall within the scope of the claims.

[0135] It should be understood that the benefits and advantages described above may relate to one embodiment or may relate to several embodiments. The embodiments are not limited to those that solve any or all of the problems described, or those that have any or all of the benefits and advantages described. It should also be understood that reference to "an" item may refer to one or more of those items.

[0136] The operations of the methods described herein may be performed in any suitable order, or simultaneously where appropriate. Additionally, individual blocks may be deleted from any method without departing from the scope of the subject matter described herein. Aspects of any embodiment described above may be combined with aspects of any of the other embodiments described to form additional embodiments without losing the effects sought.

[0137] The term "comprising" is used herein to mean including the identified methods, blocks or elements, but such blocks or elements do not include an exclusive list and the method or apparatus may contain additional blocks or elements.

[0138] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementations only (such as implementations in analog and / or digital circuits only) and (b) combinations of hardware circuits and software, such as (if used): (i) a combination of analog and / or digital hardware circuits with software / firmware, and (ii) any portion of a hardware processor (including a digital signal processor) with software, software, and memory that work together to enable a device such as a mobile phone or server to perform various functions) (c) hardware circuits and / or processors that require software (e.g., firmware) for operation, such as a microprocessor or portion of a microprocessor, but the software may not be present when not required for operation. This definition of circuitry applies to all uses of this item in this application, including in any claims.

[0139] As another example, as used in this application, the term circuitry also covers an implementation of only a hardware circuit or a processor (or multiple processors) or a portion of a hardware circuit or a processor and its accompanying software and / or firmware. For example, the term circuitry also covers a baseband integrated circuit or a processor integrated circuit used in a mobile device or similar integrated circuit in a server, cellular network device, or other computing or network device, if applicable to the particular claim element.

[0140] It should be understood that the above description is given as an example only, and various modifications may be made by those skilled in the art. The above description, examples and data provide a complete description of the structure and use of the exemplary embodiments. Although various embodiments have been described above with certain particularity or with reference to one or more separate embodiments, those skilled in the art may make many changes to the disclosed embodiments without departing from the scope of this specification.

Claims

1. A user node in a radio access network, comprising: at least one processor; as well as at least one memory containing computer program code; The at least one memory and the computer code are configured to, with the at least one processor, cause the user node to at least: receiving a message from a network node in the radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; performing the sampling on a transmission of the physical downlink channel based on the configuration information, the physical downlink channel being received on time-frequency resources allocated for the physical downlink channel; as well as generating a measurement report comprising one or more samples from the sampled transmission; as well as The measurement report is transmitted to the network node.

2. The user node of claim 1 , wherein the at least one memory and the computer code are configured to, together with the at least one processor, cause the user node to further execute: The one or more samples from the sampled transmission are stored.

3. A user node according to any one of the preceding claims, wherein the configuration information comprises at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot at which the sampling starts, the index of the Orthogonal Frequency Division Multiplexing (OFDM) symbol in the time slot at which the sampling begins, and the index of one or more resource units on which the sampling is to be performed, the number of OFDM symbols over which the sampling is to be performed, and The frequency range or bandwidth over which the sampling is to be performed.

4. The user node according to any one of the preceding claims, wherein the configuration information further comprises a period for repeating the sampling.

5. A user node according to any one of the preceding claims, wherein the configuration information further comprises a position and an orientation of the user node at which the sampling is to be performed.

6. A user node according to any of the preceding claims, wherein the configuration information further comprises an allocation of uplink resources on a physical uplink channel for the user node to send the measurement report to the network node, the allocation of the uplink resources comprising at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

7. The user node according to any of the preceding claims, wherein the configuration information further comprises the number of quantization bits used for generating the measurement report.

8. A user node according to any preceding claim, wherein the configuration information further comprises a threshold value indicating whether samples from the sampled transmission are to be included in the measurement report.

9. The user node according to claim 8, wherein the generating the measurement report comprises at least one of the following: quantizing the one or more samples, performing source encoding on the one or more samples, selecting the one or more samples based on the threshold, and The one or more samples are combined.

10. A user node according to any one of the preceding claims, wherein the at least one memory and the computer code are further configured to, together with the at least one processor, cause the user node to: The measurement report is transmitted based at least on a location of the user node in the radio access network and / or radio conditions of the radio access network.

11. A user node according to any one of the preceding claims, wherein the at least one memory and the computer code are further configured to, together with the at least one processor, cause the user node to: The trajectory is modified to arrive in an area with good coverage from the network node, or in an area of ​​coverage by a dedicated access point, or a location set by the network node for performing the sampling.

12. A user node according to any one of the preceding claims, wherein the measurement report further comprises an indication of the position and / or orientation of the user node.

13. A network node in a radio access network, comprising: at least one processor; as well as at least one memory containing computer program code; The at least one memory and the computer code are configured to, with the at least one processor, cause the network node to at least: transmitting a message to a user node in the radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; performing transmission on the physical downlink channel; receiving a measurement report from the user node, the measurement report comprising one or more samples from the transmission; as well as determining one or more parameters based on the transmission and the received measurement reports; as well as The one or more parameters are transmitted to the digital twin application.

14. The network node of claim 13, wherein the at least one memory and the computer code are further configured to, with the at least one processor, cause the network node to: In response to receiving a request from the digital twin application, transmitting the message to the user node.

15. The network node according to any one of claims 13 to 14, wherein the configuration information comprises at least one of the following: a frame number and a time slot number in the frame number, the frame number and the time slot number indicating the time slot at which the sampling starts, the index of the OFDM symbol in the time slot at which the sampling begins, the index of one or more resource units on which the sampling is to be performed, the number of OFDM symbols over which the sampling is to be performed, and The frequency range or bandwidth over which the sampling is to be performed. 16 . The network node according to claim 13 , wherein the configuration information further comprises a period for repeating the sampling.

17. The network node according to any one of claims 13 to 16, wherein the configuration information further comprises the position and orientation of the user node at which the sampling is to be performed.

18. A network node according to any one of claims 13 to 17, wherein the configuration information further comprises an allocation of uplink resources on a physical uplink channel for the user node to send the measurement report to the network node, the allocation of uplink resources comprising at least one of an uplink bandwidth portion, an uplink physical resource block index, an index of an uplink time slot, and an index of an uplink frame.

19. The network node according to any one of claims 13 to 18, wherein the configuration information further comprises a number of quantization bits used for generating the measurement report.

20. The network node according to any one of claims 13 to 19, wherein the configuration information further comprises a threshold indicating whether samples from the sampled transmission are to be included in the measurement report.

21. The network node according to any of claims 13 to 20, wherein the measurement report further comprises an indication of the position and / or orientation of the user node.

22. A method performed by a user node in a radio access network, the method comprising: receiving a message from a network node in the radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; performing the sampling on a transmission of the physical downlink channel based on the configuration information, the physical downlink channel being received on a time-frequency resource allocated for the physical downlink channel; generating a measurement report comprising one or more samples from the sampled transmission; as well as The measurement report is transmitted to the network node.

23. A method performed by a network node in a radio access network, the method comprising: transmitting a message to a user node in the radio access network, the message comprising at least configuration information for sampling of a physical downlink channel; performing transmission on the physical downlink channel; receiving a measurement report from the user node, the measurement report comprising one or more samples from the transmission; determining one or more parameters based on the transmission and the received measurement reports; as well as The one or more parameters are transmitted to the digital twin application.

Images