Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Channel Measurement to Training Data for PHY Layer AI Applications

Michael Zentarra, Julian Ahrens, Lia Ahrens

TL;DR

This paper presents a procedure for acquiring channel data by means of fast and flexible software defined radio (SDR) based channel measurements along with a method for a parameter extraction that provides configuration input to the simulator.

Abstract

Learning-based techniques such as artificial intelligence (AI) and machine learning (ML) play an increasingly important role in the development of future communication networks. The success of a learning algorithm depends on the quality and quantity of the available training data. In the physical layer (PHY), channel information data can be obtained either through measurement campaigns or through simulations based on predefined channel models. Performing measurements can be time consuming while only gaining information about one specific position or scenario. Simulated data, on the other hand, are more generalized and reflect in most cases not a real environment but instead, a statistical approximation based on a mathematical model. This paper presents a procedure for acquiring channel data by means of fast and flexible software defined radio (SDR) based channel measurements along with a method for a parameter extraction that provides configuration input to the simulator. The procedure from the measurement to the simulated channel data is demonstrated in two exemplary propagation scenarios. It is shown, that in both cases the simulated data is in good accordance to the measurements

From Channel Measurement to Training Data for PHY Layer AI Applications

TL;DR

This paper presents a procedure for acquiring channel data by means of fast and flexible software defined radio (SDR) based channel measurements along with a method for a parameter extraction that provides configuration input to the simulator.

Abstract

Learning-based techniques such as artificial intelligence (AI) and machine learning (ML) play an increasingly important role in the development of future communication networks. The success of a learning algorithm depends on the quality and quantity of the available training data. In the physical layer (PHY), channel information data can be obtained either through measurement campaigns or through simulations based on predefined channel models. Performing measurements can be time consuming while only gaining information about one specific position or scenario. Simulated data, on the other hand, are more generalized and reflect in most cases not a real environment but instead, a statistical approximation based on a mathematical model. This paper presents a procedure for acquiring channel data by means of fast and flexible software defined radio (SDR) based channel measurements along with a method for a parameter extraction that provides configuration input to the simulator. The procedure from the measurement to the simulated channel data is demonstrated in two exemplary propagation scenarios. It is shown, that in both cases the simulated data is in good accordance to the measurements
Paper Structure (10 sections, 3 equations, 5 figures, 1 table)

This paper contains 10 sections, 3 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. AI Usage in the Physical Layer
  3. Training Data Generation
  4. Data for Deep Learning
  5. Channel Measurements
  6. Channel Modelling and Simulation
  7. Measurement-aided Simulation
  8. Measurement Setup and Details
  9. Parameter Extraction & Simulation
  10. Conclusion

Figures (5)

  • Figure 1: System diagram of the procedure
  • Figure 2: Positions of the MPs in the urban measurements
  • Figure 3: Measured PDP at urban MP3
  • Figure 4: Comparison of the measured and simulated PDP, urban MP3
  • Figure 5: Comparison of the measured and simulated PDP, campus MP2