Native AI-Based Hybrid Deep Learning for Wireless Link Quality Prediction in NTN Waterside Scenarios

The nature of packet loss of wireless links at 2.4G band was analyzed and a wireless link quality prediction algorithm for wireless sensor networks was proposed. In the proposal, RSSI (Received Signal Strength Indicator) and LQI (Link Quality Indicator) were utilized to produce a couple of metrics of wireless link quality, named S m and delta respectively, and their distributions were studied. By using SAX (Symbol Aggregation approximately) method, the LQIs were mapped into different symbols, and summarized the preceding symbols of link quality deterioration in collection of patterns. Then the distance of a sample to patterns was used to determine the probability the link deterioration, so that the link quality of the next period was predicted. The proposed method is simple, so it is easy to implement in wireless sensor network. Finally, the experiment using practical link data showed that the proposed method can predict more than 80 percent of the link deteriorations.

Autonomous mobility machines, such as self-driving cars, transportation robots, and automated construction machines, are promising to support or enrich human lives. To further improve such machines, they will be connected to the network via wireless links to be managed, monitored, or remotely operated. The autonomous mobility machines must have self-status based on their positioning system to safely conduct their operations without colliding with other objects. The self-status is not only essential for machine operation but also it is valuable for wireless link quality management. This paper presents self-status-based wireless link quality prediction and evaluates its performance by using a prototype mobility robot combined with a wireless LAN system. The developed robot has functions to measure the throughput and receive signal strength indication and obtain self-status details such as location, direction, and odometry data. Prediction performance is evaluated in offline processing by using the dataset gathered in an indoor experiment. The experiments clarified that, in the 5.6 GHz band, link quality prediction using self-status of the robot forecasted the throughput several seconds into the future, and the prediction accuracies were investigated as dependent on time window size of the target throughput, bandwidth, and frequency gap.

Time series analysis to predict link quality of wireless community networks

Various smart connected devices are emerging like automated driving cars, autonomous robots, and remote-controlled construction vehicles. These devices have vision systems to conduct their operations without collision. Machine vision technology is becoming more accessible to perceive self-position and/or the surrounding environment thanks to the great advances in deep learning technologies. The accurate perception information of these smart connected devices makes it possible to predict wireless link quality (LQ). This paper proposes an LQ prediction scheme that applies machine learning to HD camera output to forecast the influence of surrounding mobile objects on LQ. The proposed scheme utilizes object detection based on deep learning and learns the relationship between the detected object position information and the LQ. Outdoor experiments show that LQ prediction proposal can well predict the throughput for around 1 s into the future in a 5.6-GHz wireless LAN channel.

Community networks have emerged under the mottos of “break the strings that are limiting you”, “don't buy the network, be the network” or “a free net for everyone is possible”. Such networks create a measurable social impact as they provide to the community the right and opportunity of communication. As any other network that mixes wired and wireless links, the routing protocol must face several challenges that arise from the unreliable nature of the wireless medium. Link quality tracking helps the routing layer to select links that maximize the delivery rate and minimize traffic congestion. Moreover, link quality prediction has proved to be a technique that surpasses link quality tracking by foreseeing which links are more likely to change its quality. In this work, we focus on link quality prediction by means of a time series analysis. We apply this prediction technique in the routing layer of large-scale, distributed and decentralized networks. We demonstrate that this type of prediction achieves about a success probability of about 98% in both the short and long term.

With the development of wireless communication systems, a variety of different systems have been studied for controlling mobile robots remotely from a cloud service, often called cloud robotics. In cloud robotics, the quality of wireless links in the wireless communication systems is important to control the mobile robots. Since the quality of wireless links changes for a variety of different reasons, such as moving and blockage, such changes may affect robot control. To operate the mobile robots safely with changing wireless link quality, we proposed a safe operation architecture. Our initial proposal realizes the monitoring of the wireless link status using the heartbeat. When the heartbeat detects the disconnection of the wireless link, the mobile robot automatically stops. However, for safer control of mobile robots, an adaptive control method for the safe operation architecture is required to follow the any change in the wireless link quality because the change is not only a disconnection level but also a gradual status. In this paper, we propose a method of discriminating the wireless link status for adaptive control of mobile robots with changes in the wireless link quality. Our method analyzed the trends in the RSSI to determine the wireless link quality, and the wireless link quality is classified into four statuses to judge the safe operation level of the mobile robot. The evaluation of the proposed method based on the experiments with 60 GHz mobile communication system is presented, and the result shows the usefulness of the method.

Accurate 5G wireless network link quality prediction can effectively improve the reliability of service transmission in 5G smart grid, where the emergence of machine learning brings innovation for link quality prediction. A link quality prediction method based on recurrent neural network(RNN) is proposed in this paper. Three parameters, RSSI, LQI and SNR, are selected to evaluate the link quality, and entropy method is introduced to calculate the weight of different parameters in the grade calculation. At the same time, because the link quality is affected by multiple feature attributes, the link quality level is divided by using the closeness analysis method to synthesize various feature attributes. On this basis, RNN is used to predict the link quality level. The parameter datasets collected at two different distances are used to train the model. The experimental results show that the proposed model has better prediction accuracy compared with the support vector machine(SVM) model.

In the application of wireless sensor networks (WSNs) to smart grid, real-time and accurate wireless link quality prediction (LQP) is important to determine which link is reliable enough to undertake the communication task. However, the existing LQP methods are neither suitable to describe the dynamic stochastic features of link quality nor to ensure the validity of prediction results. In this paper, a random-vector-functional-link-based LQP (RVFL-LQP) algorithm is proposed. The algorithm selects the signal-to-noise ratio (SNR) as the link quality metric and decomposes the raw SNR sequence into the time-varying sequence and the stochastic sequence according to the analysis of wireless link characteristics. Then, the RVFL network is used to establish the prediction model of the time-varying sequence and the variance of the stochastic sequence. Lastly, the probability-guaranteed interval boundary of SNR is predicted, and the validity and practicability of prediction results are evaluated by comparative experiments and real-world application, respectively.

Link quality is an important factor for nodes selecting communication links in wireless sensor networks. Effective link quality prediction helps to select high quality links for communication, so as to improve stability of communication. We propose the improved fuzzy C-means clustering algorithm (SUBXBFCM) and use it to adaptively divide the link quality grades according to the packet reception rate. The Pearson correlation coefficient is employed to analyse the correlation between the hardware parameters and packet reception rate. The averages of the received signal strength indicator, link quality indicator and the signal to noise ratio are selected as the inputs of the link quality estimation model based on the XGBoost (XGB_LQE). The XGB_LQE is constructed to estimate the current link quality grade, which takes the classification advantages of XGBoost. Based on the estimated results of the XGB_LQE, the link quality prediction model (XGB_LQP) is constructed by using the XGBoost regression algorithm, which can predict the link quality grade at the next moment with historical link quality information. Experiment results in single-hop scenarios of square, laboratory, and grove show that the SUBXBFCM algorithm is effective at dividing the link quality grades compared with the normal division methods. Compared with link quality prediction methods based on the Support Vector Regression and 4C, XGB_LQP makes better predictions in single-hop wireless sensor networks.

It is a big challenge to realize accurate security detection of blast furnace bearing at the same time so as to guarantee the security of equipment. To end this problem, this paper proposed a computer vision technology based on sensor data and hybrid deep learning method for the solution. We use Variational Mode Decomposition (VMD) algorithm which is a new time-frequency analysis method, which can decompose multi-component signals into multiple single-component amplitude-modulated signals at one time to decompose and deal with the sensor data of bearing fault, so as to realize the effective stripping of fault components and original components from sensor data. Using the artificial intelligence mentioned above, the features can be quickly and accurately extracted. By combining the advantages of deep learning, we improve the coupling mechanism and implement a hybrid deep learning-based computer vision method which greatly improves the calculation speed and accuracy of bearing fault diagnosis. It can be fully connected with the feature extraction algorithm VMD, which overcomes the problem that the bearing feature component is easy to be submerged and difficult to extract under the condition of high temperature and strong noise. The results show that the optimal selection of parameters of computer vision technology based on sensor data and hybrid deep learning can be realized through training the sensor data obtained from the experiment. The optimized hybrid deep learning-based computer vision algorithm can achieve 97.4% bearing fault diagnosis hit rate, which is an advanced application of deep learning algorithm in the engineering field.

This study aims to get the best performance of cellular communication based on variations in empirical radio propagation models and the number of base stations (BTS) in urban areas. The model is designed and simulated by using programming software. The observed performance parameters are the quality of the radio link and drop call. Simulation results found that the increase in base stations and mobile stations (MS) antennas height resulted quality increment of the radio link and decrement of drop call rate for all empirical models. Likewise, an increase in the number of BTSs to four in system, exerted quality improvement of radio links and decrement on drop call rate. It was also found that each increase in antenna height for the Hata radio link model produces zero dropped call as the quality of the Hata radio link is above the threshold, even when the antenna height is at the lowest.

One of the main methods for link quality prediction is to predict the physical layer parameters first, and then evaluate the link quality based on the mapping models between such parameters and packet reception ratio (PRR). However, existing methods often ignore the temporal correlations of physical layer parameter series and rarely consider the influence of link fluctuations, which lead to more errors under moderate and sudden changed links with larger fluctuations. In view of these problems, this paper proposes a more effective link quality prediction method RNN-LQI, which adopts Recurrent Neural Network (RNN) to predict the Link Quality Indicator (LQI) series, and then evaluates the link quality according to the fitting model of LQI and PRR. This method accurately mines the inner relationship among LQI series with the help of short-term memory characteristics of RNN and effectively deals with link fluctuations by taking advantage of the higher resolution of LQI in the transitional region. Compared with similar methods, RNN-LQI proves to be better under different link qualities. Especially under moderate and sudden changed links with larger fluctuations, the prediction error reduces at least by 14.51% and 13.37%, respectively. Therefore, the proposed method is more suitable for low power wireless links with more fluctuations.

A core factor to consider when designing wireless sensor networks is the reliable and efficient transmission of massive data from source to destination. In practical situations, data transmission is often disrupted by link interference and interruption resulting in the data losses. Link quality prediction is an important approach to solve this problem. By estimating the link quality based on the past knowledge and information, link quality prediction is essential for routing decisions of future data transmission. Traditional link quality prediction algorithms are simply based on the statistical information of the links in the wireless sensor network. By introducing complex network theory and machine learning techniques, we propose a neighborhood-based nonnegative matrix factorization model to predict link quality in wireless sensor networks. Our model learns latent features of the nodes from the information of past data transmissions combing with local neighborhood structures of the underlying network topology and then estimates the link quality depending on the common latent features of the two nodes between the link. Extensive experiments on both real-world networks and simulation networks demonstrate the effectiveness and efficiency of our proposed model.

Link quality prediction is a fundamental component of the wireless network protocols and is essential for routing protocols in wireless sensor networks (WSNs). Effective link quality prediction can select high-quality links for communication and improve the reliability of data transmission. In order to improve the accuracy of the link quality prediction model and reduce the model complexity, the link quality prediction model based on the light gradient boosting machine (LightGBM-LQP) is proposed in this paper. Specifically, agglomerative hierarchical clustering and manual division are combined to grade the link quality and obtain the labels of samples. Then, light gradient boosting machine (LightGBM) classification algorithm and Focal Loss are used to estimate the link quality grades. In order to reduce the impact of data imbalance, Borderline-SMOTE is employed to oversample the minority link quality samples. Finally, LightGBM-LQP predicts link quality grade at the next moment with historical link quality information. The experimental results on data collected from a real-world WSNs show that the proposed model has better prediction accuracy and shorter predicting time compared to related models.

In the applications of multi-hop wireless sensor networks, the effective evaluation of wireless link quality which can improve the network reliability is a crucial problem in the design of network protocols. The lossy and dynamic nature of the radio channel, however, makes link quality estimation a great challenge. First, we use data-driven modeling and statistical inference methods to model the burstiness of wireless link packet loss, which reflects the reliability of packet retransmission in the data link layer. Then, from a multidimensional view of characterizing the wireless link quality, we present the fuzzy logic based link quality indicator (FLI), which is a comprehensive reflection of single hop reliability of packet delivery, link volatility, and packet loss burst. Finally, we implement a wireless link quality estimator based on FLI in the collection tree protocol (CTP). Through the experimental comparison with the original link quality estimator in the CTP, the network performance with the new link quality estimator guarantees high end to end delivery reliability, while the average routing depth of the nodes and the dynamic changes of network topology are reduced.