Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a network node may obtain an erroneous packet from a first communication device. The network node may output an indication of bit error rate information, based on the erroneous packet, to a second communication device to facilitate error mitigation at the second communication device. Numerous other aspects are described.

A radio communication link is established between first and second nodes in a cellular network, which comprise at least channel coding and decoding of first and second Physical Layer (PHY) and first and second Medium Access Control (MAC) sublayers.

User data is transmitted from the first node to the second node while applying a PHY Forward Error Correction (FEC) algorithm in transmission for coding and in reception for decoding by the first and second PHY layers.

It is computed a value of a PHY-FEC error metric with respect to errors in the user data received by the second node that are uncorrected by the PHY FEC algorithm.

The received user data including the uncorrected errors is transferred from the second PHY layer to the second MAC sublayer, subject to the value of the PHY-FEC error metric being less than a threshold used by an error tolerance procedure.

Methods for the distributed reception of receivers without significantly increasing the performance requirements of the system. In particular, this object is achieved by a method which is able to strongly improve the quality of the individual samples and thus of the signal emitted by the network in a receiver network with low complexity, without requiring a central coordinator, by means of a continuous, receiver-internal, independent combination of the received data through separate antennas, or which is able to increase the spatial coverage per receiver while maintaining the same quality of wireless transmission rates per microphone, as well as realize every scenario lying in between these extremes.

An apparatus, method and computer program is described comprising receiving data at a receiver of a transmission system; using a receiver algorithm to convert data received at the receiver into an estimate of the first coded data, the receiver algorithm having one or more trainable parameters; generating an estimate of first data bits by decoding the estimate of the first coded data, said decoding making use of an error correction code of said encoding of the first data bits; generating a refined estimate of the first coded data by encoding the estimate of the first data bits; generating a loss function based on a function of the refined estimate of the first coded data and the estimate of the first coded data; updating the trainable parameters of the receiver algorithm in order to minimise the loss function; and controlling a repetition of updating the trainable parameters by generating, for each repetition, for the same received data, a further refined estimate of the first coded data, a further loss function and further updated trainable parameters.

A faulted message element in 5G or 6G can often be identified according to its modulation parameters, including a large deviation of the branch amplitudes from the predetermined amplitude levels of the modulation scheme, and/or the SNR of the branch amplitudes, and/or an amplitude variation of the raw signal or the branches during the message element, and/or an inconsistency between the modulation state as determined by the amplitude and phase of the raw waveform versus the amplitudes of the orthogonal branch signals, among other measures of modulation quality. An AI model may be necessary to correlate the various quality measures, and optionally to determine the correct demodulation of faulted message elements. Costly, time-consuming retransmissions may be avoided by determining the correct demodulation of each message element at the receiver, thereby improving throughput and reliability with fewer delays.

Various embodiments described herein provide for a mechanism for detecting failure in the operation of FEC of a physical layer device, such as a physical layer device of a networking application that seeks to meet a functional safety standard (e.g., ISO 26262). In particular, some embodiments described herein provide one of several methods for detecting a failure in the operation of a FEC decoder of a physical layer device.

For example, an apparatus may include an encoder configured to encode data into a plurality of codewords according to a parity function for a transmission modulated according to a Differential Modulation (DM) scheme, and/or a decoder to decode received codewords of the transmission.

A receiving station performs first signal detection processing on a received radio signal, performs a retransmission request to a transmitting station in a case in which a code error is detected in a detected radio packet for user data, and enqueues the radio packet in a reception buffer in a case in which no code error is detected. In parallel with the first signal detection processing, the receiving station performs second signal detection processing on the received signal with a longer processing delay than that of the first signal detection processing, and in a case in which no code error is detected in the detected radio packet for user data, the receiving station enqueues the radio packet in the reception buffer. The receiving station outputs, at a predetermined timing, the radio packet for user data with no code error detected, the radio packet being enqueued in the reception buffer.

Disclosed is a method by which a terminal decodes a codeword in a wireless communication system. Specifically, the method may comprise: receiving a plurality of codewords; and decoding the plurality codewords on the basis of successive interference cancellation (SIC). In particular, the SIC may be performed on the basis of a decoding policy for decoding the plurality of codewords. In particular, the decoding policy may be determined by a neural network trained on the basis of a state and a reward related to the plurality of codewords.

A method for reconstructing uncorrectable forward error correction (FEC) data includes generating and transcoding a known bit sequence and transmitting a FEC encoded codeword that includes a payload containing the transcoded known bit sequence through a component under test. The method further includes receiving the FEC encoded codeword transmitted via the component under test and determining that the encoded contents of the FEC encoded codeword contains a number of symbol errors that exceeds a predefined threshold. The method also includes utilizing stored scramble seed bits corresponding to an immediately preceding FEC encoded codeword and the transcoded known bit sequence to generate a reconstructed codeword.