Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Based CKM Construction with Image Super-Resolution

Shiyu Wang, Xiaoli Xu, Yong Zeng

TL;DR

An effective deep learning-based CKM construction method that leverages the image SR network known as SRResNet is proposed that outperforms interpolation-based methods such as nearest neighbour and bicubic interpolation, as well as the SRGAN method in CKM construction.

Abstract

Channel knowledge map (CKM) is a novel technique for achieving environment awareness, and thereby improving the communication and sensing performance for wireless systems. A fundamental problem associated with CKM is how to construct a complete CKM that provides channel knowledge for a large number of locations based solely on sparse data measurements. This problem bears similarities to the super-resolution (SR) problem in image processing. In this letter, we propose an effective deep learning-based CKM construction method that leverages the image SR network known as SRResNet. Unlike most existing studies, our approach does not require any additional input beyond the sparsely measured data. In addition to the conventional path loss map construction, our approach can also be applied to construct channel angle maps (CAMs), thanks to the use of a new dataset called CKMImageNet. The numerical results demonstrate that our method outperforms interpolation-based methods such as nearest neighbour and bicubic interpolation, as well as the SRGAN method in CKM construction. Furthermore, only 1/16 of the locations need to be measured in order to achieve a root mean square error (RMSE) of 1.1 dB in path loss.

Deep Learning-Based CKM Construction with Image Super-Resolution

TL;DR

An effective deep learning-based CKM construction method that leverages the image SR network known as SRResNet is proposed that outperforms interpolation-based methods such as nearest neighbour and bicubic interpolation, as well as the SRGAN method in CKM construction.

Abstract

Channel knowledge map (CKM) is a novel technique for achieving environment awareness, and thereby improving the communication and sensing performance for wireless systems. A fundamental problem associated with CKM is how to construct a complete CKM that provides channel knowledge for a large number of locations based solely on sparse data measurements. This problem bears similarities to the super-resolution (SR) problem in image processing. In this letter, we propose an effective deep learning-based CKM construction method that leverages the image SR network known as SRResNet. Unlike most existing studies, our approach does not require any additional input beyond the sparsely measured data. In addition to the conventional path loss map construction, our approach can also be applied to construct channel angle maps (CAMs), thanks to the use of a new dataset called CKMImageNet. The numerical results demonstrate that our method outperforms interpolation-based methods such as nearest neighbour and bicubic interpolation, as well as the SRGAN method in CKM construction. Furthermore, only 1/16 of the locations need to be measured in order to achieve a root mean square error (RMSE) of 1.1 dB in path loss.

Paper Structure

This paper contains 15 sections, 4 equations, 7 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Architecture and Methodology
  4. Network Architecture
  5. Training Process
  6. Numerical Results
  7. Simulation Setup
  8. Datasets
  9. Pixel-data Correlation
  10. Performance and Stability
  11. Accuracy
  12. Performance under Different SR Factors
  13. Performance of AoA prediction
  14. Discussion
  15. Conclusion

Figures (7)

  • Figure 1: Analogy between CKM construction using sparse data and image super-resolution.
  • Figure 2: Illustrating of the training and inference phases of deep learning-based CKM construction.
  • Figure 3: Mapping between pixel values in CKM images and channel knowledge. (a) AoA map. (b) Path loss map.
  • Figure 4: Visualization of 4$\times$ super-resolved path loss maps. (CKMImageNet)
  • Figure 5: Comparison of RMSE under different SR factors. (RadioMapSeer)
  • ...and 2 more figures