Method and apparatus for decoding signal in wireless communication system
Provided is a 5 th generation (5G) or 6 th generation (6G) communication system for supporting higher data rates after 4G communication systems such as long term evolution (LTE). A communication method of a user equipment (UE) includes receiving, from a base station (BS), information about a decoding mode including bit information corresponding to the number of times of perturbation, receiving data from the BS on a Physical Downlink Shared Channel (PDSCH), and decoding the received data based on the information about the decoding mode, wherein the information about the decoding mode may be generated based on service information including at least one of Quality of Service (QoS), a service priority, packet delay performance, packet error probability performance, a requirement, or a data transmission scheme.
1. A user equipment (UE) in a wireless communication system, the UE comprising:
a transceiver; and
at least one processor operable connected to the transceiver,
the at least one processor configured to:
control the transceiver to receive, from a base station (BS), information for a decoding mode including bit information corresponding to a number of perturbations,
control the transceiver to receive, from the BS, data on a physical downlink shared channel (PDSCH),
after performing a code redundancy check (CRC) or decoding a regular low-density parity-check (LDPC) code using the received data and determining that the decoding has failed, obtain the data for which the decoding has failed,
perform perturbation on at least one bit determined by using an artificial neural network based on a determination that the decoding has failed, and
perform decoding based on a result of the perturbation,
wherein the information for the decoding mode is generated based on service information including at least one of quality of service (QoS), a service priority, packet delay performance, packet error probability performance, a requirement, or a data transmission scheme, and
wherein the artificial neural network is trained by adding an index value to a position of a bit on which the decoding has been successful as a result of performing impulsive perturbation on at least one bit of the data for which the decoding has failed.
2. The UE of claim 1 , wherein the at least one processor is further configured to control the transceiver to transmit, to the BS, at least one of UE capability information or channel state information, and
wherein the information for the decoding mode is generated by the BS based on the at least one of the UE capability information or the channel state information.
3. The UE of claim 1 , wherein the at least one processor is further configured to perform decoding by repeatedly performing as many perturbations as the number of perturbations corresponding to the bit information.
4. The UE of claim 2 , wherein the UE capability information comprises at least one of information for whether the UE includes a perturbation decoder or a maximum number of perturbation rounds that the UE is able to perform.
5. The UE of claim 1 , wherein the at least one processor is further configured to:
after performing a CRC check or decoding an irregular LDPC code using the received data and determining that the decoding has failed, obtain the data for which the decoding has failed;
perform an impulsive perturbation on at least one bit of the data for which the decoding has failed; and
determine a reference value to be compared with an order of a variable node based on a structure of the irregular LDPC code, and
wherein the artificial neural network is trained by adding an index value determined according to a result of comparison between the order of the variable node and the reference value to a position of a bit on which the decoding has been successful as a result of performing the impulsive perturbation on at least one bit of the data for which the decoding has failed.
6. A method of a user equipment (UE) in a wireless communication system, the method comprising:
receiving, from a base station (BS), information for a decoding mode including bit information corresponding to a number of perturbations;
receiving, from the BS, data on a physical downlink shared channel (PDSCH);
after performing a code redundancy check (CRC) or decoding a regular low-density parity-check (LDPC) code using the received data and determining that the decoding has failed, obtaining the data for which the decoding has failed;
performing perturbation on at least one bit determined by using an artificial neural network based on a determination that the decoding has failed; and
performing decoding based on a result of the perturbation,
wherein the information for the decoding mode is generated based on service information including at least one of quality of service (QoS), a service priority, packet delay performance, packet error probability performance, a requirement, or a data transmission scheme, and
wherein the artificial neural network is trained by adding an index value to a position of a bit on which the decoding has been successful as a result of performing impulsive perturbation on at least one bit of the data for which the decoding has failed.
7. The method of claim 6 , further comprising transmitting, to the BS, at least one of UE capability information or channel state information,
wherein the information for the decoding mode is generated by the BS based on the at least one of the UE capability information or the channel state information.
8. The method of claim 7 , wherein the UE capability information comprises at least one of information for whether the UE includes a perturbation decoder or a maximum number of perturbation rounds that the UE is able to perform.
9. The method of claim 6 , wherein performing the decoding based on the received information for the decoding mode comprises performing decoding by repeatedly performing as many perturbations as the number of perturbations corresponding to the bit information.
10. The method of claim 6 , wherein determining that the decoding has failed comprises, after performing a CRC check or decoding an irregular LDPC code using the received data and determining that the decoding has failed, obtaining the data for which the decoding has failed,
wherein the method further comprises:
performing an impulsive perturbation on at least one bit of the data for which the decoding has failed; and
determining a reference value to be compared with an order of a variable node based on a structure of the irregular LDPC code, and
wherein the artificial neural network is trained by adding an index value determined according to a result of comparison between the order of the variable node and the reference value to a position of a bit on which the decoding has been successful as a result of performing the impulsive perturbation on at least one bit of the data for which the decoding has failed.