Link Quality Estimation Method for Wireless Sensor Networks Based on Stacked Autoencoder

Abstract

In wireless sensor networks, effective link quality estimation is the basis of topology management and routing control. Effective link quality estimation can guarantee the transmission of data, as well as improve the throughput rate, and hence, extend the life of the entire network. For this reason, a stacked autoencoder-based link quality estimator (LQE-SAE) is proposed. Specifically, the zero-filling method is developed to process the original missing link information. Then, the SAE model is used to extract the asymmetric characteristics of the uplink and downlink from the received signal strength indicator, link quality indicator, and signal-to-noise ratio, respectively. These characteristics are fused by SAE to construct the link features' vectors, which are given as inputs to the support vector classifier (SVC), for which the link quality grade is taken as its label. The experimental results in different scenarios show that the LQE-SAE has better accuracy than link quality estimators based on the SVC, ELM, and WNN. INDEX TERMS Wireless sensor networks, link quality estimation, stacked autoencoder, deep learning, asymmetry of link.

Machine Learning for Wireless Link Quality Estimation: A Survey

“…Whereas earlier research on LQE leveraged proprietary technologies [5], wireless sensor networks utilized relatively low cost hardware and open source software, therefore enabled a broader effort from the research community. This resulted in a large wave of research focusing on ad-hoc, mesh and multihop communications [8], [10], [13]- [17], [19], [38], [40], [74], all of which rely on the estimation of link quality. The nodes implementing the aforementioned technologies are still being maintained in various university testbeds.…”

A Link Quality Estimation Method for Wireless Sensor Networks Based on Deep Forest

“…For example, Sun [18] uses LSTM to determine the link reliability confidence interval, which is used to express the link quality in worst case. In addition, in some link quality estimation studies, such as those in [19] and [20], they turn the link quality estimation problem into a classification problem. Machine learning can help the link quality estimation model to continuously adapt to changes in the network environment, and to reduce the impact of interference on the link quality estimation through a feature processing technique.…”

“…To further verify the estimation ability of the link quality estimation model SCForest-LQE, we conduct more comparison experiments, and the results are shown in Figures.11-13. The gcForest-based model (gcForest), the random forest-based model [19] (RFC), the wavelet neural network-based model [13] (WNN-LQE), the naive Bayesbased model [11] (NB), the stacked autoencoder-based model [20] (LQE-SAE) and the lightweight, fluctuation insensitive multi-parameter fusion-based model [14] (LFI-LQE) are chosen to compare with the proposed estimator.…”

A Seq2Seq Learning Approach for Link Quality Estimation Based on System Metrics in WSNs

“…Link quality predictions are then obtained through the mapping function between SNR and PRR. Luo et al [21] designed a stacked autoencoder-based link quality estimator to extract link features and evaluate the features to divide links into five different quality grades. RL-Probe [19] studied the probing mechanism to estimate link quality by leveraging reinforcement learning.…”

“…Statistics-based approaches [14]- [18] aim to model link quality using statistical models such as Kalman filter and Support Vector Machine (SVM). Learning-based approaches [19]- [21] adopt deep learning techniques such as Reinforcement Learning (RL) to model the relationship between link quality and physical layer measurements.…”