Machine Learning for Wireless Link Quality Estimation: A Survey

Abstract

Since the emergence of wireless communication networks, a plethora of research papers focus their attention on the quality aspects of wireless links. The analysis of the rich body of existing literature on link quality estimation using models developed from data traces indicates that the techniques used for modeling link quality estimation are becoming increasingly sophisticated. A number of recent estimators leverage Machine Learning (ML) techniques that require a sophisticated design and development process, each of which has a great potential to significantly affect the overall model performance. In this paper, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based Link Quality Estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community. Having analyzed the scientific body of the survey, we review existing open source datasets suitable for LQE research. Finally, we round up our survey with the lessons learned and design guidelines for MLbased LQE development and dataset collection.

Link-Layer Retransmission-based Error-Control Protocols in FSO Communications: A Survey

“…Considering such HARQ protocol design in the context of FSO-based satellite/aerial-assisted IoVs networks would be exciting and a possible direction for future study. • Machine learning techniques have effectively advanced the state-of-the-art for many research problems in wireless communication networks [153]. To enhance the performance of systems using HARQ protocols, which imposes additional delay and energy consumption due to retransmissions required, machine learning techniques have been recently investigated in [154].…”

Towards Dependable IoT via Interface Selection: Predicting Packet Delivery at the End Node in LoRaWAN Networks

“…The use of machine learning techniques to estimate the link quality of a wireless link has received considerable attention by the research community. We refer the reader to Cerar et al [16] for an exhaustive and up-to-date survey on the topic. According to [16], existing works on link quality estimation using machine learning mainly use either classification or regression techniques.…”

“…We refer the reader to Cerar et al [16] for an exhaustive and up-to-date survey on the topic. According to [16], existing works on link quality estimation using machine learning mainly use either classification or regression techniques. Models such as naive Bayes, logistic regression, Artificial Neural Networks (ANN), e.g., [17][18][19], and more recently, Support Vector Machines (SVM), such as in [20], are commonly used.…”

“…The Packet Delivery Rate (PDR) is also usually immediately available due to the transmission of an ACK per each packet received. These metrics, as we can see in the works overviewed in [16], are the usual inputs of machine learning algorithms used for link quality estimation in wireless networks. In this work, we aim to extend related work to enable an end node in LoRaWAN to estimate whether a packet will be received by the gateway, with limited information: No feedback (only the information that is locally available to the node) or with sporadic feedback (at the link or application layer) sent from the gateway to the end node.…”

Combining Q-Learning and Multi-Layer Perceptron Models on Wireless Channel Quality Prediction

“…While the quality of a link is eventually influenced by a relatively limited number of observations, the so-called set of metrics. (Cerar et al, 2018) collects the metrics that can be used to measure the radio link quality. Each metric can also be used as an input for another metric.…”