Channel state information

Abstract

Embodiments of the present disclosure relate to channel state information. A method, an apparatus and a computer program are described, comprising: receiving data transmitted on a wireless channel (the data encoding a first estimate of channel state information of the wireless channel); decoding the data to generate a second estimate of the channel state information of the wireless channel; and generating a channel state information output by modifying the second estimate of the channel state information based at least in part on the first error indication.

Description

Technical Field

[0001] The present specification relates to channel state information in wireless communication systems. Background Art

[0002] The present description relates to channel state information in a wireless communication system.For example, an estimate of channel state information may be sent by a device (eg, user equipment) on a channel of a wireless communication system. Summary of the invention

[0003] In a first aspect, the present specification describes an apparatus comprising: a component for receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; a component for decoding the data to generate a second estimate of the channel state information of the wireless channel; and a component for generating a channel state information output by modifying the second estimate of the channel state information based at least in part on a first error indication (e.g., a binary scalar), wherein the first error indication indicates an estimation error in the first channel state information estimate generated at the device.

[0004] In a second aspect, the specification describes an apparatus comprising: means for receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; means for decoding the data to generate a second estimate of the channel state information of the wireless channel; and means for generating a channel state information output by modifying the second estimate of the channel state information based at least in part on partially correcting an error introduced in the data transmission on the wireless connection between the device and the network node. Alternatively or additionally, the second estimate of the channel state information may be modified based at least in part on a first error indication (e.g., a binary scalar) indicating an estimation error in the first channel state information estimate generated at the device.

[0005] Some example embodiments of the first and second aspects further include a component for generating a first error indication. The component for generating the first error indication may include a first machine learning module (e.g., another neural network). Some example embodiments further include a component for training the first machine learning module by minimizing a loss function including labeled data.

[0006] In some example embodiments of the first and second aspects, the means for generating the channel state information output comprises a second machine learning module (e.g., a second neural network). Some example embodiments of the first and second aspects further comprise means for training the second machine learning module based on a comparison of the generated channel state information with the labeled channel state information data.

[0007] In some example embodiments of the first and second aspects, the means for generating the channel state information output is configured to at least partially correct errors introduced in the data sent on the wireless connection between the device and the network node. The apparatus may also include means for detecting errors introduced in the data sent on the wireless connection between the device and the network node. The detection means may be implemented using a machine learning module, a neural network, or some other module. For example, the second machine learning module discussed above may be used.

[0008] In the first and second aspects, the means may include: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the execution of the apparatus.

[0009] In a third aspect, the present specification describes a method comprising: receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decoding the data to generate a second estimate of the channel state information of the wireless channel; and generating a channel state information output by modifying the second estimate of the channel state information based at least in part on a first error indication (e.g., a binary scalar), the first error indication indicating an estimation error in the first channel state information estimate generated at the device. The method may also include generating a first error indication. In addition, generating the channel state information output may include at least partially correcting an error introduced in the data on the wireless connection between the device and the network node.

[0010] In a fourth aspect, the present specification describes a method comprising: receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decoding the data to generate a second estimate of the channel state information of the wireless channel; and generating a channel state information output by modifying the second estimate of the channel state information based at least in part on partially correcting an error introduced in the data transmission on the wireless connection between the device and the network node. Alternatively or additionally, the second estimate of the channel state information may be modified based at least in part on a first error indication (e.g., a binary scalar) indicating an estimated error in the first channel state information estimate generated at the device. The method may also include generating a first error indication. In addition, generating the channel state information output may include at least partially correcting an error introduced in the data on the wireless connection between the device and the network node.

[0011] The first error indication may be generated using a first machine learning module (eg, another neural network).Some example embodiments of the third and fourth aspects further include training the first machine learning module by minimizing a loss function including the labeled code data.

[0012] A second machine learning module (eg, a second neural network) may be used to generate the channel state information output. Some example embodiments of the third and fourth aspects further include training the second machine learning module based on a comparison of the generated channel state information with the labeled channel state information data.

[0013] Some example embodiments of the third and fourth aspects further include detecting an error introduced in the data sent on the wireless connection between the device and the network node. The detection component can be implemented using a machine learning module, a neural network, or some other module. For example, the second machine learning module discussed above can be used.

[0014] In a fifth aspect, the present specification describes computer readable instructions which, when executed by a computing device, cause the computing device to (at least) perform any method as described herein (including the method of the third or fourth aspect described above).

[0015] In a sixth aspect, the present specification describes a computer-readable medium (such as a non-volatile computer-readable medium) comprising program instructions stored thereon for (at least) executing any method described herein (including the method of the third or fourth aspect described above).

[0016] In a seventh aspect, the present specification describes a device comprising: at least one processor; and at least one memory, the at least one memory comprising computer program code, which, when executed by the at least one processor, causes the device to (at least) perform any method described herein (including the method of the third or fourth aspect above).

[0017] In an eighth aspect, the present specification describes a device comprising: at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, causes the device to (at least) perform any method described herein (including the method of the third or fourth aspect described above).

[0018] In a ninth aspect, the present specification describes a computer program comprising instructions that, when executed by an apparatus, cause the apparatus to: receive data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decode the data to generate a second estimate of the channel state information of the wireless channel; and generate a channel state information output by modifying the second estimate of the channel state information based at least in part on a first error indication (e.g., a binary scalar), the first error indication indicating an estimation error in the first channel state information estimate generated at the device. The apparatus is also caused to generate the first error indication. In addition, generating the channel state information output may include at least partially correcting an error introduced in the data on the wireless connection between the device and the network node.

[0019] In a tenth aspect, the present specification describes a computer program comprising instructions that, when executed by an apparatus, cause the apparatus to: receive data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decode the data to generate a second estimate of the channel state information of the wireless channel; and generate a channel state information output by modifying the second estimate of the channel state information based at least in part on partially correcting an error introduced in the data transmission on the wireless connection between the device and the network node. Alternatively or additionally, the second estimate of the channel state information may be modified based at least in part on a first error indication (e.g., a binary scalar) indicating an estimated error in the first channel state information estimate generated at the device. The apparatus is also caused to generate the first error indication. In addition, generating the channel state information output may include at least partially correcting an error introduced in the data on the wireless connection between the device and the network node.

[0020] In an eleventh aspect, the present specification describes: a receiver module (or some other component) for receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of a wireless channel determined at the device; a decoder, such as an AIML decoder, (or some other component) for decoding the data to generate a second estimate of the channel state information of the wireless channel; and a processor, such as one or more machine learning modules, (or some other component) for generating a channel state information output by modifying the second estimate of the channel state information based at least in part on a first error indication (e.g., a binary scalar), the first error indication indicating an estimation error in the first channel state information estimate generated at the device.

[0021] In a twelfth aspect, the present specification describes: a receiver module (or some other component) for receiving data sent by a device of a wireless communication system on a channel of the wireless communication system (the device may be a user device or user equipment of a mobile communication system), wherein the data encodes a first estimate of channel state information of a wireless channel determined at the device; a decoder, such as an AIML decoder, (or some other device), for decoding the data to generate a second estimate of the channel state information of the wireless channel; and a processor, such as one or more machine learning modules, (or some other device), for generating a channel state information output by modifying the second estimate of the channel state information based at least in part on partially correcting errors introduced in the data transmission on the wireless connection between the device and the network node. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Exemplary embodiments will now be described by way of non-limiting example with reference to the following schematic drawings, in which:

[0023] Figures 1 to 4 is a block diagram illustrating a system according to an example embodiment;

[0024] Figures 5 to 8 is a flow chart illustrating an algorithm according to an example embodiment;

[0025] Fig. 9 is a block diagram illustrating a system according to an example embodiment;

[0026] Fig.10 is a schematic diagram of components of one or more of the previously described example embodiments; and

[0027] Fig.11 A tangible medium for storing computer readable code which, when executed by a computer, can perform methods according to example embodiments described herein is shown. DETAILED DESCRIPTION

[0028] The scope of protection sought by various embodiments of the invention is set out by the independent claims. Embodiments and features described in this specification that do not fall within the scope of the independent claims, if any, are to be construed as examples useful for understanding the various embodiments of the invention.

[0029] Like reference numerals refer to like elements throughout the description and drawings.

[0030] Figure 11 is a block diagram illustrating a system generally designated by reference numeral 10 according to an example embodiment. The system includes a device such as a user equipment (UE) 12, a channel 14, and a network node 16. The device 12 and the network node 16 communicate bidirectionally with each other via the channel 14.

[0031] In a system such as system 10, channel state information (CSI) may be required for many purposes, such as accurate precoding in massive multiple-input multiple-output (MIMO) communications using a frequency division duplex (FDD) scheme. For example, accurate CSI can be used to enable a base station (BS) to obtain a higher signal-to-noise ratio (SNR) and improve channel capacity. However, in many implementations of system 10 (e.g., an FDD network), only device 12 is capable of estimating downlink CSI. In such systems, the estimated CSI is typically shared with network nodes 16 via channel 14, which introduces communication overhead to the system.

[0032] To reduce this overhead, the CSI may be compressed and / or quantized prior to transmission. For example, the CSI data may be compressed (e.g., using vector quantization) to generate a codebook that achieves a high compression ratio (CR) (i.e., the ratio of the compressed size to the uncompressed size). (The compression ratio may be a scalar in the range of (0, 1], where a lower CR indicates more compression.) Alternatively or additionally, the CSI data may be quantized so that, for example, device 12 transmits the quantized bits via channel 14 with network node 16, which includes a dequantizer to generate a signal that a decoder may use to reconstruct the original channel state information estimate.

[0033] Schemes used to reduce transmission overhead, such as data compression and / or data quantization, may limit the accuracy of CSI reconstruction.

[0034] Figure 2 2 is a block diagram illustrating a system generally designated by reference numeral 20 according to an example embodiment. System 20 includes a channel estimator 22, an encoder 24, and a transmitter 26, which form part of an example implementation of the device 12 described above. Channel estimator 22 may be used to estimate downlink channel state information (CSI). An encoded version of the estimated CSI is sent using transmitter 26 (e.g., from device 12 to network node 16 over channel 14).

[0035] Figure 3 is a block diagram illustrating a system, generally designated by reference numeral 30, according to an example embodiment. System 30 includes a receiver 32 and a decoder 34, which may form part of the example embodiment of network node 16 described above. Receiver 32 may receive encoded CSI data transmitted by system 20. Decoder 34 decodes the encoded transmitted CSI to reconstruct the CSI estimated by channel estimator 22.

[0036] The encoder 24 and the decoder 34 may together function as an autoencoder (AE), where the encoder 24 is used to generate a compressed representation of the input CSI and the decoder 34 is used to reconstruct the CSI from the compressed information.

[0037] The encoder and decoder of the autoencoder based CSI compression arrangement can be implemented using artificial intelligence or machine learning models (AIML). These models can be trained in a variety of ways, such as: Joint training of a two-ended autoencoder model at a single side / entity (e.g., at the UE / device side of the system 10 or at the network side). This may be referred to as Type 1 training. Joint training of two-end autoencoder models on the network side and UE / device side of the system 10, respectively. This may be referred to as type 2 training. Separate training on the network side and the UE / device side, training the UE / device side CSI generation part on the UE / device side and training the network side CSI reconstruction part on the network side. This can be called type 3 training.

[0038] Joint training can refer to the code generation model (encoder) and the reconstruction model (decoder) being trained in the same loop for forward and backward propagation. Joint training can be at a single node or across multiple nodes (e.g., by gradient exchange between nodes).

[0039] The separate training may include sequential training starting with UE-side training, or sequential training starting with network-side training at the UE.

[0040] In system 20, the output of channel estimator 22 provides an imperfect channel estimate represented by eCSI as follows: eCSI=CSI+∈1

[0041] Where ∈1 is the error term introduced by the imperfect downlink channel estimation. Note that ∈1 is usually the main source of error in CSI feedback.

[0042] The eCSI is then encoded into a bit vector C by encoder 24 (which may form part of an AIML autoencoder).

[0043] Code C is prepared for transmission by transmitter module 26. For example, code C may undergo OFDM transmission on an uplink control channel (eg, bits may be encoded using Polar codes, modulated onto QAM symbols, and then modulated into an OFDM waveform).

[0044] The transmitted waveform (e.g., OFDM waveform) travels over a wireless propagation channel (e.g., channel 14) to a receiver 32 of system 30. During transmission, the waveform is contaminated by noise and interference. At receiver 32, the signal may undergo OFDM reception (using receiver 32) and decoding (using decoder 34) to generate an estimated code Among them, the quality of the estimate depends on the radio conditions and the robustness of the transmission scheme:

[0045] Here, ∈2 is the error at the input of decoder 34. In some example embodiments, ∈2 may be a rare event due to the very high error detection / correction probability using conventional channel coding with CRC checking. However, depending on the signal-to-noise ratio (SNR) of the received signal and the code length and code rate considered for the conventional channel coding, ∈2 may be higher. In the case where ∈2 is available, if we successfully correct the received code, then there is no need to schedule retransmission, which reduces the delay and saves resources.

[0046] The estimated code is decoded by decoder 34 and the reconstructed eCSI (expressed as ).therefore, is an imperfect estimate of the true CSI, where the imperfection has two main reasons: DL-based error ∈ 1 due to imperfect downlink channel estimation in the UE (ie, the first block where eCSI is generated). UL based errors due to imperfect uplink OFDM reception which introduces errors in the estimated codes in the gNB.

[0047] Imperfect Reconstruction It can be used, for example, to select a precoder. However inaccurate it may end up being, the choice itself may also become suboptimal.

[0048] In order to provide an accurate CSI feedback framework that is relatively unaffected by the severity of channel conditions (in both DL and UL), it is desirable for the network node 16 to reconstruct an accurate version of the CSI.

[0049] Figure 4 is a block diagram illustrating a system, generally indicated by the reference numeral 40 , in accordance with an example embodiment.

[0050] The system includes a channel estimator 41 , an encoder 42 , an OFDM transmitter module 43 , a wireless channel 44 , an OFDM receiver module 45 , a decoder 46 , an error detection module 47 and an error correction module 48 .

[0051] Channel estimator 41, encoder 42, and transmitter module 43 are similar to channel estimator 22, encoder 24, and transmitter 26, and may form part of apparatus 12 of system 10 described above. Receiver module 45, decoder 46, error detection module 47, and error correction module 48 may form part of network node 16 of system 10 described above.

[0052] OFDM receiver 45 implements means for receiving data transmitted by a device of the wireless communication system (e.g., device 12) on a channel 44 of the wireless communication system. The data encodes a first estimate of channel state information of a wireless channel determined at the device (i.e., as determined at channel estimator 41).

[0053] As described above with reference to system 20, channel estimator 41 is an imperfect channel estimator that provides an imperfect channel estimate represented by eCSI as follows: eCSI=CSI+∈1

[0054] where ∈1 is the error term introduced by the imperfect downlink channel estimation.

[0055] The eCSI is then encoded into a bit vector C by encoder 42 .

[0056] Code C is to be transmitted by the OFDM transmitter module 43. At the OFDM receiver 45, the following estimated code is generated Among them, the quality of the estimate depends on the radio conditions and the robustness of the transmission scheme:

[0057] Estimated code is passed through a decoder 46 (which may be the decoder portion of an AIML autoencoder with encoder 42) to generate a reconstructed CSI estimate Then, the reconstructed CSI estimate is sent to an error correction module 48 which seeks to remove some or all uplink and downlink errors from the reconstructed code.

[0058] Refactoring code is also routed to an error detection module 47 which detects errors in the reconstructed code and outputs a scalar e∈[0,1], where Then e=1.

[0059] The error correction module 48 receives: The reconstructed code output by the OFDM receiver 45 The reconstruction output by the decoder 46 as well as The detected error e is output by the error detection module 47.

[0060] Error correction module 48 attempts to remove the The uplink error and downlink error in , to generate an estimate close to the true CSI

[0061] Thus, decoder 46 generates a second estimate of the channel state information for the wireless channel and the error correction module generates a channel state information output by modifying a second estimate of the channel state information based at least in part on the first error indication (e). The first error indication may indicate an estimation error (ie a downlink error) in a first channel state information estimate generated at the device.Alternatively or additionally, the first error indication may indicate an uplink error introduced in data sent over a wireless connection between the device and the network node.

[0062] It should be noted that although decoder 46, error detection module 47, and error correction module 48 are shown as three separate modules, two or more of these modules may be combined into a single module (e.g., into a single neural network). For example, error detection module 47 and error correction module 48 may be integrated. However, there may be advantages to separating these modules, at least in that the training of the modules may be more easily separated.

[0063] As discussed in detail below, the error correction module 48 may be a neural network (NN) or machine learning module that can be trained to distinguish between: DL channel estimation error (at channel estimation module 41); and UL reception error.

[0064] The error detection module 47 (for generating the first error indication) may also be implemented using a neural network (NN) or a machine learning module.

[0065] Figure 5 is a flow chart illustrating an algorithm, generally designated by reference numeral 50, according to an example embodiment. Algorithm 50 may be implemented on the device side of system 40 (ie, using channel estimator 41, encoder 42, and OFDM transmitter module 43).

[0066] The algorithm 50 begins at operation 52 where a channel estimate (eg, an imperfect channel estimate) is obtained. The channel estimate may be generated using conventional methods or using machine learning methods.

[0067] At operation 54, the channel estimate is encoded (eg, using an encoder portion of an autoencoder). The encoder may be a machine learning module and may be trainable.

[0068] The encoded channel estimate is transmitted using OFDM or some other transmission arrangement at operation 56. For example, the output of operation 54 may be encoded, modulated onto QAM symbols, and then transmitted as an OFDM waveform.

[0069] Figure 6 is a flow chart illustrating an algorithm, generally designated by reference numeral 60, according to an example embodiment. Algorithm 60 may be implemented on the network side of system 40 (eg, using OFDM receiver module 45, decoder 46, error detection module 47, and error correction module 48).

[0070] Algorithm 60 begins at operation 62 where the signal transmitted in operation 56 is received (eg, using OFDM or some other reception technique).

[0071] At operation 64, the channel estimate (as initially generated in operation 52) is detected and corrected (e.g., using one or more neural networks or machine learning algorithms). As discussed in detail above, the correction may correct errors introduced by the imperfect channel estimate in operation 52, and / or errors introduced during encoding, transmission, and decoding of the channel estimate. A trainable machine learning based detection and / or correction block may be used to detect errors in the received code and / or generate a modified channel estimate.

[0072] Finally, at operation 66, the channel estimate obtained in operation 64 is used in some manner. For example, the channel estimate may be used to select a precoder for massive multiple-input multiple-output (MIMO) communications.

[0073] In system 40, error detection module 47 is typically a neural network that outputs a binary scalar indicating an error. Error detection module 47 may be trained as a binary classification task.

[0074] Binary cross entropy (CE) can be used as a cost function to train a binary classifier implemented as error detection module 47. The label used for training can be obtained by sharing the code C from a device (e.g., device 12) to a network node (e.g., node 16) using a more reliable link or by considering multiple transmissions or sharing on the cloud. Then, the label can be written as

[0075] The output e of the ML block and the label e L The cross entropy (CE) loss function between L CE=-(e (l) loge+(1-e (l) )log(1-e))

[0076] In order to train the error correction module 48, the mean square error (MSE) or squared generalized cosine similarity (SGCS) between the reconstructed CSI and the optimal / expected CSI may be considered. Note that the optimal / expected CSI as a label may be obtained by a simulator or by considering a more complex channel estimator than the channel estimator used for inference in the user equipment. For example, the user equipment uses least squares (LS) as a channel estimator in inference. However, the user equipment uses both LS and LMMSE channel estimators for data collection during the training phase).

[0077] Figure 7 is a flow chart illustrating an algorithm generally indicated by reference numeral 70 according to an example embodiment. Algorithm 70 may be used to train error detection module 47.

[0078] Algorithm 70 begins at operation 72 where a code associated with a channel estimate is received (e.g., a reconstructed code output by OFDM receiver 45 is received). ).

[0079] At operation 74 of algorithm 70, the transmitted code (eg, a more reliable version of code C) is retrieved. The code received at this operation represents labeled data that can be used for training.

[0080] At operation 76 of algorithm 70 , the error detection module 47 is trained by minimizing the loss function based on the codes received in operations 72 and 74 .

[0081] Of course, algorithm 70 is highly schematic and many modifications are possible. For example, operations 72 and 74 may be reversed, or may be performed in parallel.

[0082] Figure 8 8 is a flow chart illustrating an algorithm generally indicated by reference numeral 80 in accordance with an example embodiment. Algorithm 80 may be used to train error correction module 48.

[0083] Algorithm 80 begins at operation 82, where a channel state information estimate is generated (eg, by an instance of error correction module 48).

[0084] At operation 84 of algorithm 80, labeled channel state information data is received. The labeled data is considered to be more accurate (or more reliable) than the data acquired in operation 82.

[0085] At operation 86 of algorithm 80 , the error correction module 48 is trained by minimizing a loss function based on the channel state information obtained in operations 82 and 84 .

[0086] Of course, algorithm 80 is highly schematic and many modifications are possible. For example, operations 82 and 84 may be reversed, or may be performed in parallel.

[0087] Fig. 9 is a block diagram illustrating a system, generally designated by the reference numeral 90, in accordance with an example embodiment. The system 90 has many similarities to the system 40 described above.

[0088] In system 90, two sets of outputs are provided by the error detection module 97 of system 90. These outputs include: Scalar e∈[0,1] (as above), where if Then e = 1 (a smaller value of e means higher probability); Binary vector i e , used to determine which elements / segments in the code are affected due to UL channel noise.

[0089] The information in e can help find the code The index of the element in the code that is affected by the UL channel noise (for scalar quantization) or the index of the segment (for vector quantization). In the event that an error is detected in one of the segments / elements of

[0090] Thus, the error detection module 97 not only detects errors in the reconstructed code, but also outputs the index of the segment / element that needs to be corrected.

[0091] Depending on the type of quantization considered (scalar or vector quantization), we can determine the number of elements / segments in the code, which also defines the dimension of the binary vector. An indication of the possibility of the training error detection block 97 is that the code generated by the encoder occupies only a portion of the code space. This property has been seen and used in training schemes for training NWs first, in which a single decoder decompresses codes from different UEs with different encoders.

[0092] The NN1 block implementing the error detection block 97 can be viewed as a multi-class classifier, where the decision on the state of each element / segment is a separate class, resulting in a number of classes equal to the binary vector i e We can use the cross entropy loss function to train the classifier. For example, the jth entry of the label can be obtained as

[0093] Different correction mechanisms / algorithms may be considered to correct the elements / segments affected by UL channel noise. As an example, the code correction block (e.g., code correction block 48) in the above embodiments may search for all or some possible quantization levels / codewords for the affected segments. The search aims to find the following quantization level / codeword: the quantization level / codeword results in a new code that follows the distribution of the codes in the training data set.

[0094] Another possibility is to select for the affected segment the quantization level / codeword that results in the highest value of e if we feed the candidate code to a trained error detection module.

[0095] In another example embodiment, the error correction module may be additionally fed with a channel correlation function, the channel correlation function being one of the following: Estimated by the gNB and / or predicted using any other UL data traffic. Estimated and reported by the UE, for example, the UE may report the maximum Doppler shift and maximum delay spread, and the gNB may use the selected model to determine the channel correlation in the time / frequency domain.

[0096] In another embodiment, the error correction module may be provided on the device side. For example, the error correction module may be provided between the channel estimation module 41 and the encoder module 42. In this case, the error correction module may receive the eCSI and optionally the channel correlation function and the estimated SINR as input.

[0097] In order to implement the different architectures described herein, coordination may be performed between the device side and the network side. For example, if the tasks of CSI correction and error detection / correction are distributed between the device side and the network side, the network side should coordinate these tasks, for example by activating / deactivating UE-based modules. On the contrary, if the network decides to perform all the described tasks itself, it can trigger the device to operate in an energy saving mode (EEM), where for example: The device can use a simple downlink channel estimator such as least squares (relying on the gNB for CSI correction). The device may defer estimation and reporting of channel correlation function and / or SINR conditions, etc.

[0098] For completeness, Fig.10 is a schematic diagram of components of one or more example embodiments described previously, which are hereinafter collectively referred to as processing system 300. Processing system 300 may be, for example, an apparatus as recited in the claims.

[0099] The processing system 300 may have a processor 302, a memory 304 tightly coupled to the processor and including a RAM 314 and a ROM 312, and an optional user input 310 and a display 318. The processing system 300 may include one or more network / device interfaces 308 for connecting to a network / device, for example, a wired or wireless modem. The network / device interface 308 may also operate as a connection to other devices such as devices / devices that are not network-side devices. Thus, direct connections between devices / devices are possible without network involvement.

[0100] The processor 302 is connected to each of the other components so as to control the operation thereof.

[0101] The memory 304 may include non-volatile memory, such as a hard disk drive (HDD) or a solid state drive (SSD). Among other things, the ROM 312 of the memory 304 stores an operating system 315 and may store software applications 316. The processor 302 uses the RAM 314 of the memory 304 to temporarily store data. The operating system 315 may include code that implements aspects of the algorithms and sequences 50, 60, 70, and 80 described above when executed by the processor. Note that in the case of a small device / apparatus, the memory may be best suited for small size use, i.e., a hard disk drive (HDD) or a solid state drive (SSD) is not always used.

[0102] Processor 302 may take any suitable form. For example, it may be a microcontroller, multiple microcontrollers, a processor, or multiple processors.

[0103] The processing system 300 may be a stand-alone computer, server, console or a network thereof. The processing system 300 and the required structural components may all be inside a device / apparatus, such as an IoT device / apparatus, i.e., embedded in a very small size.

[0104] In some example embodiments, the processing system 300 may also be associated with external software applications. These applications may be applications stored on a remote server device / apparatus and may be run partially or exclusively on the remote server device / apparatus. These applications may be referred to as cloud-hosted applications. The processing system 300 may communicate with the remote server device / apparatus to utilize the software applications stored there.

[0105] Fig.11A tangible medium in the form of a removable memory unit 365 storing computer readable code is shown, which when run by a computer can perform a method according to the above-described example embodiments. The removable memory unit 365 can be a memory stick, such as a USB memory stick, with an internal memory 366 storing computer readable code. The computer system can access the internal memory 366 via a connector 367. Of course, other forms of tangible storage media can be used, which will be obvious to those of ordinary skill in the art. The tangible medium can be any device / equipment capable of storing data / information that can be exchanged between devices / equipment / networks.

[0106] Embodiments of the present invention may be implemented in software, hardware, application logic, or a combination of software, hardware, and application logic. The software, application logic, and / or hardware may reside in a memory, or on any computer medium. In an example embodiment, the application logic, software, or instruction set is maintained on any of various conventional computer-readable media. In the context of this document, a "memory" or "computer-readable medium" may be any non-transitory medium or device that may contain, store, communicate, propagate, or transmit instructions for use by or in conjunction with an instruction execution system, device, or apparatus, such as a computer.

[0107] Where relevant, references to "computer-readable medium", "computer program product", "tangibly embodied computer program", etc. or "processor" or "processing circuitry", etc. should be understood to include not only computers with different architectures (e.g., single / multi-processor architectures and sequential / parallel architectures), but also special-purpose circuits (e.g., field programmable gate arrays FPGAs, application-specific circuits ASICs, signal processing devices / apparatuses, and other devices / apparatuses). References to computer programs, instructions, codes, etc. should be understood to express software for programmable processor firmware (e.g., programmable content of hardware devices / apparatuses) as instructions for a processor or configured settings or configuration settings for a fixed-function device / apparatus, gate array, programmable logic device / apparatus, etc.

[0108] If desired, the different functions discussed herein may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the above functions may be optional or may be combined. Similarly, it should also be understood that Figures 5 to 8 The flowcharts are merely examples, and the different operations depicted therein may be omitted, reordered, and / or combined.

[0109] It should be understood that the above exemplary embodiments are only illustrative and do not limit the scope of the present invention.Other changes and modifications will be apparent to those skilled in the art after reading this specification.

[0110] Furthermore, the disclosure of the present application should be understood to include any novel feature or any novel combination of features disclosed herein, whether explicitly or implicitly, or any generalization thereof, and during the prosecution of the present application or any application derived therefrom, new claims may be formulated to cover any such feature and / or combination of such features.

[0111] Although various aspects of the invention are set out in the independent claims, further aspects of the invention comprise other combinations of features from the described example embodiments and / or the dependent claims with features of the independent claims and not just the combinations explicitly set out in the claims.

[0112] It is also noted herein that, although various examples are described above, these descriptions should not be viewed in a limiting sense. Rather, several changes and modifications may be made without departing from the scope of the invention as defined in the appended claims.

Claims

1. A device comprising: means for receiving data transmitted by a device of a wireless communication system on a channel of the wireless communication system, wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; means for decoding said data to generate a second estimate of said channel state information of said wireless channel; as well as means for generating a channel state information output by modifying the second estimate of the channel state information based at least in part on a first error indication, the first error indication indicating an estimation error in the first channel state information estimate generated at the device and an uplink error introduced in the data sent on the channel.

2. The apparatus of claim 1, further comprising means for generating the first error indication.

3. The apparatus of claim 2, wherein the means for generating the first error indication comprises a first machine learning module.

4. The apparatus of claim 3, further comprising means for training the first machine learning module by minimizing a loss function, the loss function comprising the labeled code data.

5. An apparatus according to any preceding claim, wherein the first error indication is a binary scalar.

6. An apparatus according to any preceding claim, wherein the means for generating the channel state information output comprises a second machine learning module.

7. The apparatus of claim 6, further comprising means for training the second machine learning module based on a comparison of the generated channel state information with labeled channel state information data.

8. An apparatus according to any one of the preceding claims, wherein the means for generating the channel state information output is configured to at least partially correct errors introduced in the data sent over the wireless connection between the device and the network node.

9. The apparatus of claim 8, further comprising means for detecting the error introduced in the data sent over the wireless connection between the device and the network node.

10. An apparatus according to any preceding claim, wherein the device is user equipment or user equipment of the mobile communication system.

11. The apparatus according to any of the preceding claims, wherein the means comprises at least one processor and at least one memory storing instructions which, when executed by the at least one processor, cause the execution of the apparatus.

12. A method comprising: receiving data transmitted by a device of a wireless communication system on a channel of the wireless communication system, wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decoding the data to generate a second estimate of the channel state information of the wireless channel; as well as A channel state information output is generated by modifying the second estimate of the channel state information based at least in part on a first error indication indicating an estimation error in the first channel state information estimate generated at the device and an uplink error introduced in the data sent on the channel. The method of claim 12 , further comprising generating the first error indication.

14. The method of claim 13, wherein generating the channel state information output comprises: Errors introduced in the data over the wireless connection between the device and the network node are at least partially corrected.

15. A computer program comprising instructions which, when executed by an apparatus, cause the apparatus to: receiving data transmitted by a device of a wireless communication system on a channel of the wireless communication system, wherein the data encodes a first estimate of channel state information of the wireless channel determined at the device; decoding the data to generate a second estimate of the channel state information of the wireless channel; as well as A channel state information output is generated by modifying the second estimate of the channel state information based at least in part on a first error indication indicating an estimation error in the first channel state information estimate generated at the device and an uplink error introduced in the data sent on the channel.

Images