ML Interference Detection in Tiered Shared Spectrum
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In tiered licensing deployments, General Authorized Access (GAA) users experience interference from other GAA users without protection, as spectrum access systems do not provide information about these users, leading to challenges in identifying and mitigating interfering signals.
Innovation Solution
A system utilizing a local spectrum access database and machine-learning based signal separation techniques to identify and mitigate interfering signals from other GAA users by applying IQ samples to deep neural networks for source separation, and adjusting carrier frequencies or adding interfering signals to the database to avoid interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If GAA users share spectrum in tiered licensing deployments, then spectrum utilization and network scalability are improved, but interference from other GAA users occurs without protection
Solution Approach 1:
The system performs preliminary interference detection by analyzing received signals to identify multiple independent signals before they cause harmful effects. The base station proactively detects interfering GAA user signals and mitigates them through coordination, preventing degradation of network performance rather than reacting after interference occurs.
Solution Approach 2:
The system establishes a feedback mechanism where base stations exchange interference detection information through the spectrum access system. When a base station detects interfering signals from GAA users, it reports this information back to the SAS, which then coordinates with other base stations to mitigate the interference, creating a closed-loop system that continuously improves spectrum sharing efficiency.
2Device complexity
If spectrum access systems do not provide information about GAA users, then system complexity and information management overhead are reduced, but interference detection and mitigation capability deteriorates
Solution Approach 1:
The system enables base stations to perform self-service interference detection by autonomously analyzing received signals to identify multiple independent signals. Instead of relying on the SAS to provide interference information, the base station independently detects interfering GAA user signals and reports findings to the SAS, reducing the information management burden on the SAS while maintaining detection capability.
3Reliability
If base stations use dedicated processing hardware, then processing reliability and signal quality are improved, but deployment cost and single point of failure risk increase
Solution Approach 1:
The system implements a universal base station architecture where a single base station can serve multiple cells and handle multiple GAA user deployments. The base station's signal processing capabilities are designed to be multi-functional, enabling it to detect and mitigate interference from multiple different GAA users across different geographic areas, reducing the need for dedicated hardware at each deployment location.
Data Source
AI summary
Described are examples for machine learning based interference detection for tiered licensing deployments. A network entity in a general authorized access (GAA) deployment checks a local spectrum access database of GAA users to determine that a portion of shared use spectrum is free from known local users in a geographic area. The network entity receives samples of a wireless signal including at least a desired signal on the portion of shared use spectrum. The network entity determines whether the wireless signal includes multiple independent signals. The network entity identifies an interfering signal in response to determining that the wireless signal includes multiple independent signals.