Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Anomaly Detection-Based UE-Centric Inter-Cell Interference Suppression

Kwonyeol Park, Hyuckjin Choi, Beomsoo Ko, Minje Kim, Gyoseung Lee, Daecheol Kwon, Hyunjae Park, Byungseung Kim, Min-Ho Shin, Junil Choi

TL;DR

This work tackles inter-cell interference in dense 5G NR by introducing a UE-centric scheme that uses Z-score normalization with a deep SVDD anomaly detector (ZRD-SVDD) to detect interference and drive adaptive interference whitening. The method demonstrates superior detection accuracy with limited training data and achieves performance close to genie-aided IW, validated through numerical simulations and TE experiments on TDL-A/B/C channels. Key contributions include a practical, semi-supervised training approach, a compact test-phase decision rule, and substantial throughput and BLER gains in realistic channel conditions. The approach offers a scalable, UE-side interference suppression mechanism with clear implications for improving reliability and efficiency in next-generation cellular networks.

Abstract

The increasing spectral reuse can cause significant performance degradation due to interference from neighboring cells. In such scenarios, developing effective interference suppression schemes is necessary to improve overall system performance. To tackle this issue, we propose a novel user equipment-centric interference suppression scheme, which effectively detects inter-cell interference (ICI) and subsequently applies interference whitening to mitigate ICI. The proposed scheme, named Z-refined deep support vector data description, exploits a one-class classification-based anomaly detection technique. Numerical results verify that the proposed scheme outperforms various baselines in terms of interference detection performance with limited time or frequency resources for training and is comparable to the performance based on an ideal genie-aided interference suppression scheme. Furthermore, we demonstrate through test equipment experiments using a commercial fifth-generation modem chipset that the proposed scheme shows performance improvements across various 3rd generation partnership project standard channel environments, including tapped delay line-A, -B, and -C models.

Anomaly Detection-Based UE-Centric Inter-Cell Interference Suppression

TL;DR

This work tackles inter-cell interference in dense 5G NR by introducing a UE-centric scheme that uses Z-score normalization with a deep SVDD anomaly detector (ZRD-SVDD) to detect interference and drive adaptive interference whitening. The method demonstrates superior detection accuracy with limited training data and achieves performance close to genie-aided IW, validated through numerical simulations and TE experiments on TDL-A/B/C channels. Key contributions include a practical, semi-supervised training approach, a compact test-phase decision rule, and substantial throughput and BLER gains in realistic channel conditions. The approach offers a scalable, UE-side interference suppression mechanism with clear implications for improving reliability and efficiency in next-generation cellular networks.

Abstract

The increasing spectral reuse can cause significant performance degradation due to interference from neighboring cells. In such scenarios, developing effective interference suppression schemes is necessary to improve overall system performance. To tackle this issue, we propose a novel user equipment-centric interference suppression scheme, which effectively detects inter-cell interference (ICI) and subsequently applies interference whitening to mitigate ICI. The proposed scheme, named Z-refined deep support vector data description, exploits a one-class classification-based anomaly detection technique. Numerical results verify that the proposed scheme outperforms various baselines in terms of interference detection performance with limited time or frequency resources for training and is comparable to the performance based on an ideal genie-aided interference suppression scheme. Furthermore, we demonstrate through test equipment experiments using a commercial fifth-generation modem chipset that the proposed scheme shows performance improvements across various 3rd generation partnership project standard channel environments, including tapped delay line-A, -B, and -C models.

Paper Structure

This paper contains 17 sections, 3 theorems, 35 equations, 14 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System and channel model
  4. Conventional IW scheme and limitations
  5. Proposed Scheme: Z-Refined Deep SVDD
  6. ZRD-SVDD components
  7. Training phase of ZRD-SVDD
  8. Test phase of ZRD-SVDD
  9. Performance Evaluation
  10. Experimental environments and datasets
  11. Numerical simulations
  12. Experiments using TE
  13. Baselines
  14. Complexity analysis
  15. Performance metrics
  16. ...and 2 more sections

Key Result

Theorem 1

For a finite number of samples $T_s$, the discrepancy between the sample covariance and the true covariance satisfies the following inequality where $\hat{{\mathbf{R}}}_m = \frac{1}{T_s} \sum_{t=1}^{T_s} {\mathbf{u}}_{m,t} {\mathbf{u}}_{m,t}^\mathrm{H}$ is the sample covariance with the $t$-th received interference plus noise signal ${\mathbf{u}}_{m,t}$, and $\epsilon$ denotes a design parameter

Figures (14)

  • Figure 1: Block diagram of the proposed scheme.
  • Figure 2: System model for the case of $N_c = 2$.
  • Figure 3: Framework for ZRD-SVDD.
  • Figure 4: Experimental scenario for the case of $N_c = 1$.
  • Figure 5: Environment for the TE experiments.
  • ...and 9 more figures

Theorems & Definitions (6)

  • Theorem 1
  • proof
  • Lemma 1
  • proof
  • Lemma 2
  • proof