D2D Equalizer Mitigates Interference via Soft Value Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Device-to-device (D2D) communication systems face interference issues due to shared finite frequency resources, particularly in unlicensed spectrum without central network control, leading to performance degradation despite approaches like retransmission and interference cancellation.

Innovation Solution

An equalizer that iteratively estimates soft values of data, interference, and noise signals using mean-field estimation to isolate data signals, refining residual noise power and accounting for uncertainties, without relying on prior interference information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If retransmission and interference cancellation approaches are used in D2D communication, then data transfer reliability is improved, but system complexity and processing overhead increase

Engineering Contradiction:

Improvedata transfer reliabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical interference cancellation methods with a neural network-based signal processing system. The neural network automatically learns and adapts to interference patterns, substituting complex algorithmic processing with trained model inference, thereby maintaining reliability while reducing real-time computational complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neural network is trained in advance on datasets containing various interference scenarios and signal conditions. This preliminary training allows the system to make rapid predictions during actual D2D communication without performing complex real-time interference cancellation, reducing processing overhead while maintaining reliability.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If iterative soft value estimation with mean-field estimation is used, then signal detection precision is improved, but computational load and processing time increase

Engineering Contradiction:

Improvesignal detection precisionVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements a limited number of iterative estimation steps rather than exhaustive iteration. By performing a fixed, small number of estimation passes, the system achieves sufficient detection precision without the diminishing returns of extensive iteration, thereby reducing processing time while maintaining adequate signal detection accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system uses simplified intermediate estimates and approximations during the iterative process that are computationally inexpensive to calculate. These temporary estimates are discarded after each iteration cycle, allowing rapid recomputation without maintaining complex state information, thus reducing processing time while preserving detection precision.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Data Source

PatentUS11451260B2Methods and devices for device-to-device communications

Publication Date: 2022.09.20 INTEL CORP

AI summary

A terminal device includes a controller configured to identify a data hopping sequence for a first superframe including a plurality of frames, and a transceiver configured to switch hopping frequencies over the plurality of frames according to a data hopping sequence that excludes one or more hopping frequencies scheduled for use by a synchronization hopping sequence in one or more superframes immediately succeeding the first superframe.