Granted Patent B2

US 12,267,186 · App. 18/471,589 · Granted Apr 1, 2025

Inventors: Aliye Kaya (Murray Hill, NJ); Luiz Fernando Medeiros (Espoo, FI)

Assignee: Nokia Solutions and Networks Oy

H04L25/0204H04L5/0048H04L25/0224

Abstract

Claims (80)

1. An apparatus comprising at least one processor, and at least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to:

receive a sequence from a network element of a radio access network, wherein the sequence is encoded with a preamble matrix comprising a plurality of entries, wherein at least a subset of the plurality of entries indicate random-access preambles, and the preamble matrix has been generated randomly or based on a plurality of network entities or user equipment;

decode the sequence, wherein the sequence is decoded by using a decoder that was trained by:

creating a first matrix comprising a plurality of random-access preamble sets;

selecting a sample batch from the first matrix;

inputting the sample batch to an encoder with at least one neural network layer;

receiving a sequence as an output from the encoder, wherein the sequence is encoded with the sample batch;

inputting the sequence to the decoder with at least one neural network layer;

receiving a second matrix as an output from the decoder;

determining a binary cross-entropy loss comparing the sample batch and the second matrix;

propagating the binary cross-entropy loss to the decoder and the encoder via an optimizer; and

repeating the selection of the sample batch, the inputting of the sample batch, the receiving of the sequence, the inputting of the sequence, the receiving of the second matrix, the determining, and the propagating until the binary cross-entropy loss is below a threshold;

generate a root sequence and a cyclic shift based at least partly on the decoding;

generate a random-access preamble based on the root sequence and the cyclic shift; and

transmit the random-access preamble to the network element.

2. The apparatus according to claim 1 , wherein rows of the preamble matrix indicate cyclic shifts of the random-access preambles and columns of the preamble matrix indicate root sequences of the random-access preambles, or the rows indicate the root sequences and the columns indicate the cyclic shifts.

3. The apparatus according to claim 1 , wherein the plurality of entries comprises at least two sets of values or symbols, and the subset comprises one set of values or symbols from the at least two sets of values or symbols.

4. The apparatus according to claim 1 , wherein the decoding comprises mapping the sequence to the preamble matrix,

wherein the apparatus is further caused to:

select an entry from the at least subset of the plurality of entries comprised in the preamble matrix,

wherein the root sequence and the cyclic shift are generated based on a column and a row of the entry in the preamble matrix.

5. The apparatus according to claim 1 , wherein the decoding comprises generating the root sequence and the cyclic shift from the sequence.

6. A method comprising:

receiving a sequence from a network element of a radio access network, wherein the sequence is encoded with a preamble matrix comprising a plurality of entries, wherein at least a subset of the plurality of entries indicate random-access preambles, and the preamble matrix has been generated randomly or based on a plurality of network entities or user equipment;

decoding the sequence, wherein the sequence is decoded by using a decoder that was trained by:

creating a first matrix comprising a plurality of random-access preamble sets;

selecting a sample batch from the first matrix;

inputting the sample batch to an encoder with at least one neural network layer;

receiving a sequence as an output from the encoder, wherein the sequence is encoded with the sample batch;

inputting the sequence to the decoder with at least one neural network layer;

receiving a second matrix as an output from the decoder;

determining a binary cross-entropy loss comparing the sample batch and the second matrix;

propagating the binary cross-entropy loss to the decoder and the encoder via an optimizer; and

repeating the selection of the sample batch, the inputting of the sample batch, the receiving of the sequence, the inputting of the sequence, the receiving of the second matrix, the determining, and the propagating until the binary cross-entropy loss is below a threshold;

generating a root sequence and a cyclic shift based at least partly on the decoding;

generating a random-access preamble based on the root sequence and the cyclic shift; and

transmitting the random-access preamble to the network element.

7. The method according to claim 6 , wherein rows of the preamble matrix indicate cyclic shifts of the random-access preambles and columns of the preamble matrix indicate root sequences of the random-access preambles, or the rows indicate the root sequences and the columns indicate the cyclic shifts.

8. The method according to claim 6 , wherein the plurality of entries comprises at least two sets of values or symbols, and the subset comprises one set of values or symbols from the at least two sets of values or symbols.

9. The method according to claim 6 , wherein the decoding comprises mapping the sequence to the preamble matrix,

wherein the method further comprises:

selecting an entry from the at least subset of the plurality of entries comprised in the preamble matrix,

wherein the root sequence and the cyclic shift are generated based on a column and a row of the entry in the preamble matrix.

10. The method according to claim 6 , wherein the decoding comprises generating the root sequence and the cyclic shift from the sequence.

11. A non-transitory computer readable medium comprising program instructions which, when executed by an apparatus, cause the apparatus to perform at least the following:

receiving a sequence from a network element of a radio access network, wherein the sequence is encoded with a preamble matrix comprising a plurality of entries, wherein at least a subset of the plurality of entries indicate random-access preambles, wherein the preamble matrix has been generated randomly or based on a plurality of network entities or user equipment;

decoding the sequence, wherein the sequence is decoded by using a decoder that was trained by:

creating a first matrix comprising a plurality of random-access preamble sets;

selecting a sample batch from the first matrix;

inputting the sample batch to an encoder with at least one neural network layer;

receiving a sequence as an output from the encoder, wherein the sequence is encoded with the sample batch;

inputting the sequence to the decoder with at least one neural network layer;

receiving a second matrix as an output from the decoder;

determining a binary cross-entropy loss comparing the sample batch and the second matrix;

propagating the binary cross-entropy loss to the decoder and the encoder via an optimizer; and

repeating the selection of the sample batch, the inputting of the sample batch, the receiving of the sequence, the inputting of the sequence, the receiving of the second matrix, the determining, and the propagating until the binary cross-entropy loss is below a threshold;

generating a root sequence and a cyclic shift based at least partly on the decoding;

generating a random-access preamble based on the root sequence and the cyclic shift; and

transmitting the random-access preamble to the network element.

12. The non-transitory computer readable medium according to claim 11 , wherein rows of the preamble matrix indicate cyclic shifts of the random-access preambles and columns of the preamble matrix indicate root sequences of the random-access preambles, or the rows indicate the root sequences and the columns indicate the cyclic shifts.

13. A system comprising at least one or more user devices and a network element of a radio access network;

wherein the network element is configured to:

generate a preamble matrix comprising a plurality of entries, wherein at least a subset of the plurality of entries indicate random-access preambles, and the preamble matrix is generated randomly or based on a plurality of network entities or user equipment;

obtain a sequence encoded with the preamble matrix; and

transmit the sequence to the one or more user devices;

wherein the one or more user devices are configured to:

receive the sequence from the network element;

decode the sequence, wherein the sequence is decoded by using a decoder that was trained by:

creating a first matrix comprising a plurality of random-access preamble sets;

selecting a sample batch from the first matrix;

inputting the sample batch to an encoder with at least one neural network layer;

receiving a sequence as an output from the encoder, wherein the sequence is encoded with the sample batch;

inputting the sequence to the decoder with at least one neural network layer;

receiving a second matrix as an output from the decoder;

determining a binary cross-entropy loss comparing the sample batch and the second matrix;

propagating the binary cross-entropy loss to the decoder and the encoder via an optimizer; and

repeating the selection of the sample batch, the inputting of the sample batch, the receiving of the sequence, the inputting of the sequence, the receiving of the second matrix, the determining, and the propagating until the binary cross-entropy loss is below a threshold;

generate a root sequence and a cyclic shift based at least partly on the decoding;

generate a random-access preamble based on the root sequence and the cyclic shift; and

transmit the random-access preamble to the network element.

Assignments (3)

Priority Claims (1)

Continuity (1)

References Cited (29)