Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

How Critical is Site-Specific RAN Optimization? 5G Open-RAN Uplink Air Interface Performance Test and Optimization from Macro-Cell CIR Data

Johnathan Corgan, Nitin Nair, Rajib Bhattacharjea, Wan Liu, Serhat Tadik, Tom Tsou, Timothy J. O'Shea

TL;DR

A rough magnitude of the gap that can be closed by site-specific training is illustrated, and the first answer to the question "how much can fine-tuning the RAN for site-specific channels help" is given.

Abstract

In this paper, we consider the importance of channel measurement data from specific sites and its impact on air interface optimization and test. Currently, a range of statistical channel models including 3GPP 38.901 tapped delay line (TDL), clustered delay line (CDL), urban microcells (UMi) and urban macrocells (UMa) type channels are widely used for air interface performance testing and simulation. However, there remains a gap in the realism of these models for air interface testing and optimization when compared with real world measurement based channels. To address this gap, we compare the performance impacts of training neural receivers with 1) statistical 3GPP TDL models, and 2) measured macro-cell channel impulse response (CIR) data. We leverage our OmniPHY-5G neural receiver for NR PUSCH uplink simulation, with a training procedure that uses statistical TDL channel models for pre-training, and fine-tuning based on measured site specific MIMO CIR data. The proposed fine-tuning method achieves a 10% block error rate (BLER) at a 1.85 dB lower signal-to-noise ratio (SNR) compared to pre-training only on simulated TDL channels, illustrating a rough magnitude of the gap that can be closed by site-specific training, and gives the first answer to the question "how much can fine-tuning the RAN for site-specific channels help?"

How Critical is Site-Specific RAN Optimization? 5G Open-RAN Uplink Air Interface Performance Test and Optimization from Macro-Cell CIR Data

TL;DR

A rough magnitude of the gap that can be closed by site-specific training is illustrated, and the first answer to the question "how much can fine-tuning the RAN for site-specific channels help" is given.

Abstract

In this paper, we consider the importance of channel measurement data from specific sites and its impact on air interface optimization and test. Currently, a range of statistical channel models including 3GPP 38.901 tapped delay line (TDL), clustered delay line (CDL), urban microcells (UMi) and urban macrocells (UMa) type channels are widely used for air interface performance testing and simulation. However, there remains a gap in the realism of these models for air interface testing and optimization when compared with real world measurement based channels. To address this gap, we compare the performance impacts of training neural receivers with 1) statistical 3GPP TDL models, and 2) measured macro-cell channel impulse response (CIR) data. We leverage our OmniPHY-5G neural receiver for NR PUSCH uplink simulation, with a training procedure that uses statistical TDL channel models for pre-training, and fine-tuning based on measured site specific MIMO CIR data. The proposed fine-tuning method achieves a 10% block error rate (BLER) at a 1.85 dB lower signal-to-noise ratio (SNR) compared to pre-training only on simulated TDL channels, illustrating a rough magnitude of the gap that can be closed by site-specific training, and gives the first answer to the question "how much can fine-tuning the RAN for site-specific channels help?"

Paper Structure

This paper contains 7 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Measurement System and Measurement Campaign
  5. Neural Receiver Pre-Training, Fine-tuning, and Evaluation
  6. Results
  7. Discussion, Limitations, and Conclusion

Figures (3)

  • Figure 1: 5G neural receiver training and evaluation block diagram
  • Figure 2: An example drive-map of hcapture channel sounding in Arlington, VA area. The map is an overhead view, with pink structures representing building geometry and the black points and lines representing the drive route along roads.
  • Figure 3: Comparison of the baseline neural receiver vs. one fine-tuned on site-specific data (MCS 27: 256QAM with a rate 0.93 code)