Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Machine Learning based Hybrid Receiver for 5G NR PRACH

Rohit Singh, Anil Kumar Yerrapragada, Radha Krishna Ganti

TL;DR

The design of a hybrid receiver that consists of an AI/ML model for preamble detection followed by conventional peak detection for the Timing Advance estimation is described and results show superior performance compared to conventional receivers both for simulated and real hardware-captured datasets.

Abstract

Random Access is a critical procedure using which a User Equipment (UE) identifies itself to a Base Station (BS). Random Access starts with the UE transmitting a random preamble on the Physical Random Access Channel (PRACH). In a conventional BS receiver, the UE's specific preamble is identified by correlation with all the possible preambles. The PRACH signal is also used to estimate the timing advance which is induced by propagation delay. Correlation-based receivers suffer from false peaks and missed detection in scenarios dominated by high fading and low signal-to-noise ratio. This paper describes the design of a hybrid receiver that consists of an AI/ML model for preamble detection followed by conventional peak detection for the Timing Advance estimation. The proposed receiver combines the Power Delay Profiles of correlation windows across multiple antennas and uses the combination as input to a Neural Network model. The model predicts the presence or absence of a user in a particular preamble window, after which the timing advance is estimated by peak detection. Results show superior performance of the hybrid receiver compared to conventional receivers both for simulated and real hardware-captured datasets.

A Machine Learning based Hybrid Receiver for 5G NR PRACH

TL;DR

The design of a hybrid receiver that consists of an AI/ML model for preamble detection followed by conventional peak detection for the Timing Advance estimation is described and results show superior performance compared to conventional receivers both for simulated and real hardware-captured datasets.

Abstract

Random Access is a critical procedure using which a User Equipment (UE) identifies itself to a Base Station (BS). Random Access starts with the UE transmitting a random preamble on the Physical Random Access Channel (PRACH). In a conventional BS receiver, the UE's specific preamble is identified by correlation with all the possible preambles. The PRACH signal is also used to estimate the timing advance which is induced by propagation delay. Correlation-based receivers suffer from false peaks and missed detection in scenarios dominated by high fading and low signal-to-noise ratio. This paper describes the design of a hybrid receiver that consists of an AI/ML model for preamble detection followed by conventional peak detection for the Timing Advance estimation. The proposed receiver combines the Power Delay Profiles of correlation windows across multiple antennas and uses the combination as input to a Neural Network model. The model predicts the presence or absence of a user in a particular preamble window, after which the timing advance is estimated by peak detection. Results show superior performance of the hybrid receiver compared to conventional receivers both for simulated and real hardware-captured datasets.

Paper Structure

This paper contains 16 sections, 4 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background on 5G NR Physical Random Access Channel
  3. 5G Random Access Procedures
  4. PRACH Sequence Generation and Transmission
  5. Existing receivers for 5G NR PRACH
  6. Conventional approaches
  7. AI/ML approaches
  8. Proposed hybrid PRACH receiver
  9. Neural Network Architecture
  10. Dataset Generation
  11. Simulated datasets
  12. Over-the-Air (OTA) Hardware captured datasets
  13. Results
  14. Explainability of the model output
  15. Model Complexity
  16. ...and 1 more sections

Figures (9)

  • Figure 1: Power Delay Profile (PDP) of the correlation at the receiver, showing that it can be difficult to set a threshold due to multiple false peaks at low SNR.
  • Figure 2: The proposed AI/ML based hybrid architecture for the PRACH receiver.
  • Figure 3: The proposed NN architecture for PRACH user detection.
  • Figure 4: IIT-Madras 5G testbed setup with the Remote Radio Head used as a receiver and the VSG used as a transmitter.
  • Figure 5: Comparison of user detection probability of AI/ML based receiver (PDP and CDP inputs) with conventional threshold based detection
  • ...and 4 more figures