MISO Transmitter Training for Constant-Envelope Signal Output

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing MISO systems face challenges in efficiently transmitting signals without power inefficiencies and distortion due to power amplifiers, particularly in multiple-input scenarios, where digital predistortion methods are complex and costly, and conventional receivers may not be optimal.

Innovation Solution

Implementing a trainable transmitter algorithm using machine learning principles, such as neural networks, to convert coded bits into baseband symbols with a constant envelope, optimizing for information rate and envelope constraints, and optionally training the receiver jointly to achieve high performance without requiring modifications to conventional receivers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If digital predistortion circuits are used to compensate for power amplifier distortions, then communication performance is improved, but device complexity and power consumption increase

Engineering Contradiction:

Improvecommunication performanceVSAvoidcomplexity of predistortion circuits

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the predistortion function from complex digital circuits and implements it through a trainable algorithm that operates on baseband symbols. The algorithm learns to compensate for power amplifier distortions without requiring complex predistortion circuitry, thereby reducing device complexity while maintaining communication performance.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical/digital circuit implementation of predistortion with a software-based trainable algorithm. Instead of using complex digital predistortion circuits, the system uses a neural network or similar algorithm that processes baseband symbols to compensate for power amplifier nonlinearities, substituting hardware complexity with computational intelligence.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If digital predistortion circuits are used to compensate for power amplifier distortions, then communication performance is improved, but power consumption increases

Engineering Contradiction:

Improvecommunication performanceVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent extracts the computationally intensive predistortion function from dedicated hardware circuits and implements it through an efficient trainable algorithm. This extraction allows the system to achieve the same distortion compensation with lower power consumption by using optimized computational methods rather than power-hungry digital circuitry.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the operational parameters of the power amplifier by training the transmitter algorithm to generate baseband symbols that account for the amplifier's nonlinear characteristics. This parameter change approach allows the power amplifier to operate closer to its saturation point without requiring complex predistortion, thereby reducing power consumption while maintaining communication performance.

Inventive Principle:

Principle #35Parameter changes

3Use of energy by moving object

If power amplifier operates closer to saturation point, then power efficiency is improved, but signal distortion increases

Engineering Contradiction:

Improvepower efficiencyVSAvoidsignal distortion

Core Design Contradiction:

Use of energy by moving objectVSObject-generated harmful factors

Solution Approach 1:

The patent applies preliminary action by training the transmitter algorithm in advance to pre-compensate for power amplifier distortions. The algorithm learns the amplifier's nonlinear characteristics and adjusts the baseband symbols before they reach the power amplifier, allowing the amplifier to operate efficiently near saturation without generating harmful signal distortions.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent employs feedback mechanisms where the transmitter algorithm uses information about the power amplifier's behavior (obtained through training data or feedback loops) to adjust its output. This feedback allows the system to operate the power amplifier close to saturation while continuously compensating for distortion, thereby achieving high power efficiency without sacrificing signal quality.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12627338B2Transmitter

Publication Date: 2026.05.12 NOKIA TECHNOLOGIES OY

AI summary

An apparatus, method and computer program is described comprising: transmitting signals from a transmitter of a multiple-input single-output transmission system to a receiver of the transmission system, wherein the transmitter communicates with the receiver over a plurality of channels of the transmission system, wherein the transmitter includes a transmitter algorithm having at least some trainable weights, wherein said transmitter algorithm converts a sequence of coded bits into time domain baseband symbols for transmission over said channels; updating weights of said transmitter algorithm based on a loss function, said loss function having a first loss term, a second loss term and a variable defining a weighting of those loss terms, wherein the first parameter relates to an information rate of communications from the transmitter to the receiver; and repeating the transmitting and updating until a first condition is reached.