Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Phase-Only Positioning in Distributed MIMO Under Phase Impairments: AP Selection Using Deep Learning

Fatih Ayten, Musa Furkan Keskin, Akshay Jain, Mehmet C. Ilter, Ossi Kaltiokallio, Jukka Talvitie, Elena Simona Lohan, Mikko Valkama

TL;DR

This work tackles centimeter-level localization using carrier phase observations in a distributed MIMO setting under phase synchronization errors. It combines a hyperbola-intersection-based phase-only positioning with a deep-learning AP-selection framework that chooses two ambiguities to minimize the localization error, and it trains a differential ambiguity estimator followed by a regression-based selector to enable robust operation. Two-step training with phase-perturbation-aware data yields near-ideal accuracy (e.g., 95th percentile errors well below 1 cm) while reducing inference complexity by about 19.7% compared to using all ambiguities. The results demonstrate that phase-only positioning, when augmented with learning-based AP selection, can reliably achieve cm-level localization in realistic 6G deployments and offer practical latency benefits through localized processing and reduced computation at the central unit.

Abstract

Carrier phase positioning (CPP) can enable cm-level accuracy in next-generation wireless systems, while recent literature shows that accuracy remains high using phase-only measurements in distributed MIMO (D-MIMO). However, the impact of phase synchronization errors on such systems remains insufficiently explored. To address this gap, we first show that the proposed hyperbola intersection method achieves highly accurate positioning even in the presence of phase synchronization errors, when trained on appropriate data reflecting such impairments. We then introduce a deep learning (DL)-based D-MIMO antenna point (AP) selection framework that ensures high-precision localization under phase synchronization errors. Simulation results show that the proposed framework improves positioning accuracy compared to prior-art methods, while reducing inference complexity by approximately 19.7%.

Phase-Only Positioning in Distributed MIMO Under Phase Impairments: AP Selection Using Deep Learning

TL;DR

This work tackles centimeter-level localization using carrier phase observations in a distributed MIMO setting under phase synchronization errors. It combines a hyperbola-intersection-based phase-only positioning with a deep-learning AP-selection framework that chooses two ambiguities to minimize the localization error, and it trains a differential ambiguity estimator followed by a regression-based selector to enable robust operation. Two-step training with phase-perturbation-aware data yields near-ideal accuracy (e.g., 95th percentile errors well below 1 cm) while reducing inference complexity by about 19.7% compared to using all ambiguities. The results demonstrate that phase-only positioning, when augmented with learning-based AP selection, can reliably achieve cm-level localization in realistic 6G deployments and offer practical latency benefits through localized processing and reduced computation at the central unit.

Abstract

Carrier phase positioning (CPP) can enable cm-level accuracy in next-generation wireless systems, while recent literature shows that accuracy remains high using phase-only measurements in distributed MIMO (D-MIMO). However, the impact of phase synchronization errors on such systems remains insufficiently explored. To address this gap, we first show that the proposed hyperbola intersection method achieves highly accurate positioning even in the presence of phase synchronization errors, when trained on appropriate data reflecting such impairments. We then introduce a deep learning (DL)-based D-MIMO antenna point (AP) selection framework that ensures high-precision localization under phase synchronization errors. Simulation results show that the proposed framework improves positioning accuracy compared to prior-art methods, while reducing inference complexity by approximately 19.7%.
Paper Structure (13 sections, 1 equation, 3 figures, 1 table)

This paper contains 13 sections, 1 equation, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Architecture
  3. Phase-only Positioning
  4. Hyperbola Intersection Method
  5. Proposed AP Selection Method
  6. Inference Complexity
  7. Simulation Results
  8. Training of Proposed Neural Networks
  9. Inference Complexity Reduction
  10. Differential Ambiguity Estimation Results
  11. AP Selection Results
  12. Conclusion
  13. ACKNOWLEDGMENTS

Figures (3)

  • Figure 1: Uplink UE positioning in a distributed AP deployment, where only carrier phase measurements are taken into account for positioning.
  • Figure 2: Block diagram of the proposed phase-only positioning approach.
  • Figure 3: (a) Accuracy and positioning performance with different training and test set combinations; (b) ECDF of the proposed approach and benchmarks; (c) complementary ECDF of the proposed approach and benchmarks.