Loading patent…
AssigneeNokia Solutions and Networks Oy
InventorsSelahattin GOKCELI, Sahan Damith LIYANAARACHCHI, Dani Johannes KORPI
Estimating the term…
A technical solution is provided, which enables low-Peak-to-Average Power Ratio (PAPR) waveform design by using Machine Learning (ML)-based constellation shaping in a wireless communication network. Original bits are processed by an autoencoder comprising an encoder and a decoder. The encoder obtains a vector of data symbols by mapping the original bits to a constellation diagram and transmits it to the decoder while applying a random Power Amplifier (PA) model. The decoder obtains restored bits by decoding the received vector of data symbols in accordance with a detection algorithm. Further, a loss function value is calculated based on the original and restored bits. The autoencoder is then trained by jointly correcting the constellation diagram and the detection algorithm based on the loss function value. The processing, calculation and training steps are repeated by using the corrected constellation diagram and detection algorithm until a target training condition is met.
An apparatus for performing Machine Learning (ML)-based constellation shaping in a wireless communication network, comprising:
A method for performing Machine Learning (ML)-based constellation shaping in a wireless communication network, comprising:
A computer program product comprising a non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer code which, when executed by at least one processor, causes the at least one processor to:
Dependencies are inferred from the claim text.