Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Wireless Link Quality Estimation Using LSTM Model

Yuki Kanto, Kohei Watabe

TL;DR

This paper proposes a novel WLQE model based on Long Short-Term Memory (LSTM), enabling highly accurate estimation by considering the sequential information of link quality, and demonstrates its superiority in a comparative evaluation.

Abstract

In recent years, various services have been provided through high-speed and high-capacity wireless networks on mobile communication devices, necessitating stable communication regardless of indoor or outdoor environments. To achieve stable communication, it is essential to implement proactive measures, such as switching to an alternative path and ensuring data buffering before the communication quality becomes unstable. The technology of Wireless Link Quality Estimation (WLQE), which predicts the communication quality of wireless networks in advance, plays a crucial role in this context. In this paper, we propose a novel WLQE model for estimating the communication quality of wireless networks by leveraging sequential information. Our proposed method is based on Long Short-Term Memory (LSTM), enabling highly accurate estimation by considering the sequential information of link quality. We conducted a comparative evaluation with the conventional model, stacked autoencoder-based link quality estimator (LQE-SAE), using a dataset recorded in real-world environmental conditions. Our LSTM-based LQE model demonstrates its superiority, achieving a 4.0% higher accuracy and a 4.6% higher macro-F1 score than the LQE-SAE model in the evaluation.

Wireless Link Quality Estimation Using LSTM Model

TL;DR

This paper proposes a novel WLQE model based on Long Short-Term Memory (LSTM), enabling highly accurate estimation by considering the sequential information of link quality, and demonstrates its superiority in a comparative evaluation.

Abstract

In recent years, various services have been provided through high-speed and high-capacity wireless networks on mobile communication devices, necessitating stable communication regardless of indoor or outdoor environments. To achieve stable communication, it is essential to implement proactive measures, such as switching to an alternative path and ensuring data buffering before the communication quality becomes unstable. The technology of Wireless Link Quality Estimation (WLQE), which predicts the communication quality of wireless networks in advance, plays a crucial role in this context. In this paper, we propose a novel WLQE model for estimating the communication quality of wireless networks by leveraging sequential information. Our proposed method is based on Long Short-Term Memory (LSTM), enabling highly accurate estimation by considering the sequential information of link quality. We conducted a comparative evaluation with the conventional model, stacked autoencoder-based link quality estimator (LQE-SAE), using a dataset recorded in real-world environmental conditions. Our LSTM-based LQE model demonstrates its superiority, achieving a 4.0% higher accuracy and a 4.6% higher macro-F1 score than the LQE-SAE model in the evaluation.

Paper Structure

This paper contains 13 sections, 6 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Relted Works
  3. Proposed Method
  4. Preprocess
  5. Model Architecture
  6. Training
  7. Experiments
  8. Dataset
  9. Baselines
  10. Parameter Settings
  11. Performance Metrics
  12. Performance Evaluation
  13. Conclusions

Figures (2)

  • Figure 1: The architecture of LSTM-based LQE model. This model first divides the dataset using a sliding window. Subsequently, two sequences of the trend term $x^j_t$ and the noise term ${\varepsilon}^j_t$ are created from the divided sequence. These sequences are then fed into the LSTM component, predicting the future values of the two terms. The binning component classify it into an LQ grade.
  • Figure 2: Temporal variation in RSSI and SINR samples in the SRFG dataset. The average RSRP for this sample is $-87.17$ dBm (Standard Deviation: $14.94$ dBm), and the average SINR is $8.62$ dB (Standard Deviation: $9.67$ dB).