Apparatus and method for optimizing physical layer parameter
AssigneeSamsjung Electronics Co., Ltd.
InventorsKee-Bong Song, Ahmed A. Abotabl, Jung Hyun Bae
Life of this patent
Estimating the term…
Abstract
An apparatus and method for optimizing a physical layer parameter is provided. According to one embodiment, an apparatus includes a first neural network configured to receive a transmission environment and a block error rate (BLER) and generate a value of a physical layer parameter; a second neural network configured to receive the transmission environment and the BLER and generate a signal to noise ratio (SNR) value; and a processor connected to the first neural network and the second neural network and configured to receive the transmission environment, the generated physical layer parameter, and the generated SNR, and to generate the BLER.
Claims20
An apparatus, comprising:
- a first neural network configured to receive a transmission environment and a block error rate (BLER) and generate a value of a physical layer parameter;
- a second neural network configured to receive the transmission environment and the BLER and generate a signal to noise ratio (SNR) value;
- and
- a processor connected to the first neural network and the second neural network and configured to receive the transmission environment, the generated physical layer parameter, and the generated SNR value, and to generate the BLER.
A method, comprising:
- initializing a first neural network and a second neural network;
- determining if a mean squared error test (MSEtest) value is greater than a threshold;
- if the MSEtest value is greater than a threshold, then
- selecting a batch of transmission environments;
- generating a physical layer parameter value by the first neural network;
- generating a signal to noise ratio (SNR) value by the second neural network;
- simulating a batch of transmission environments by a processor to obtain a block error rate (BLER);
- updating the physical layer parameter value by the first neural network using the BLER;
- updating the SNR value by the second neural network using the BLER;
- and
- returning to determining if the MSEtest value is greater than a threshold;
- and if the MSEtest value is not greater than the threshold, then
- stopping.
Dependencies are inferred from the claim text.