Channel Prediction Model Research Articles

Deep-Learning-Based Spatial–Temporal Channel Prediction for Smart High-Speed Railway Communication Networks

Intelligent channel prediction plays a key role in artificial intelligence (AI)-optimized or AI-native communication networks for smart high-speed railways (HSRs). This paper investigates the spatial-temporal prediction of channel state information (CSI) and channel statistical characteristics (CSCs) based on deep-learning (DL) for the future smart HSR communication network. A propagation-graph simulation method is used to generate datasets of CSI and CSCs for massive multiple-input multiple-output (mMIMO) channels in a HSR cutting scenario, and realistic channel measurements are used to validate the datasets. Then, single-step ahead and multi-step ahead prediction problems are formulated with the consideration of both spatial and temporal information hidden in the datasets. By exploiting the temporal and spatial correlations of the HSR mMIMO channel, a novel spatial-temporal channel prediction model that combines the convolutional neural network (CNN) and convolutional long short-term memory (CLSTM) is proposed and called as Conv-CLSTM. Moreover, the hyper-parameters of the Conv-CLSTM model are determined by autocorrelation and similarity analysis and cross-validation. Finally, the performance of the Conv-CLSTM model is evaluated in terms of prediction accuracy and space and time computational complexity, and is compared with classical DL models. The evaluation results show that the proposed model has high prediction accuracy but acceptable computational complexity.

DeepBAN: A Temporal Convolution-Based Communication Framework for Dynamic WBANs

Wireless body area network (WBAN) has become a promising technology, which can be widely applied in health monitoring, and so on. However, the performance of a practical WBAN may severely suffer from the degradation caused by dynamic nature of wireless channels with the movements of human body. Traditional communication frameworks cannot catch up with the channel variation of dynamic WBANs, which may severely degrade the performance, so an accurate channel prediction model is necessary for developing an efficient transmission strategy. In this paper, we propose a DeepBAN communication framework for dynamic WBANs. In our proposed framework, a temporal convolution network (TCN) based deep learning approach is adopted for channel prediction, the computationally intensive task of which is processed by mobile edge computing (MEC), to reduce the response time. Given the predicted channel conditions, we propose a joint power control, time-slot allocation, and relay selection algorithm to maximize the energy efficiency of the system, taking into account the transmission reliability and end-to-end latency requirements. We evaluate the performance of DeepBAN, and the results show that it can achieve energy-efficient, reliable, and low-latency data transmission in dynamic WBANs, which can improve the system energy efficiency by 15% compared with the stochastic scheduling scheme.

Measurement of Path Loss Characterization and Prediction Modeling for Swarm UAVs Air-to-Air Wireless Communication Systems

A challenge swarm unmanned aerial vehicles (swarm UAVs)-based wireless communication systems have been focused on channel modeling in various environments. In this paper, we present the characterized path loss air-to-air (A2A) channel modeling-based measurement and prediction model. The channel model was considered using A2A Two-Ray (A2AT-R) extended path loss modeling. The prediction model was considered using an artificial neural network (ANN) algorithm to train the measured dataset. To evaluate the measurement result, path loss models between the A2AT-R model and the prediction model are shown. We show that the prediction model using ANN is optimal to train the measured data for the A2A channel model. To discuss the result, the parametric prediction errors such as mean absolute error (MAE), root mean square error (RMSE), and R-square (R2), are performed.

A Real-Time Channel Prediction Model Based on Neural Networks for Dedicated Short-Range Communications.

Based on a multiple layer perceptron neural networks, this paper presents a real-time channel prediction model, which could predict channel parameters such as path loss (PL) and packet drop (PD), for dedicated short-range communications (DSRC). The dataset used for training, validating, and testing was extracted from experiments under several different road scenarios including highways, local areas, residential areas, state parks, and rural areas. The study shows that the proposed PL prediction model outperforms conventional empirical models. Meanwhile, the proposed PD prediction model achieves higher prediction accuracy than the statistical one. Moreover, the prediction model can operate in real-time, through updating its training set, to predict channel parameters. Such a model can be easily extended to the applications of autonomous driving, the Internet of Things (IoT), 5th generation cellular network technology (5G) and many others.

Prediction leakage channels of CO2 injection wells

During CO2 injection, a microannulus will be generated, leading to the transmission of gas through the cement behind the casing or before the formation when thermal stress exceeds bond strength. In this work, leakage channel prediction model was developed to predict the leakage channel of CO2 injection wells. The prediction results indicate that the thermal stresses first decreased and then increased with increasing well depth; decreased with increasing radial distance; and increased with increasing injection time. The cement sheath of a production casing is more likely to form a leakage channel than other cement sheaths during long-duration CO2 injection.

ARMA-Based Adaptive Coding Transmission Over Millimeter-Wave Channel for Integrated Satellite-Terrestrial Networks

The integrated satellite-terrestrial network can provide broadband wireless access in a wide coverage, efficient, and cost-effective manner, and is regarded as one of the most promising infrastructures for future heterogeneous network toward fifth generation. With the development of next generation of high throughput satellites (HTS), the application of the millimeter-wave (mmWave) band HTS is viewed as a vital role in the future integrated satellite-terrestrial network. Considering the rain attenuation is the dominant fading factor of the mmWave channel, we first propose a practical time-varying rain attenuation prediction model based on the autoregressive-moving-average (ARMA) model. Then, we develop an adaptive coding transmission (ACT) scheme based on the analog fountain codes combine the ARMA mmWave channel prediction model. The key parameters are selected based on a tradeoff between the decoding failure probability, block length, and overhead for our ARMA-based ACT scheme. Simulation results show that our proposed ACT scheme can effectively improve the throughput.

A Semi-Blind Channel Estimation Method Based on Improved Particle Filtering for HF Channel

To further improve the performance of channel estimation by particle filtering, an improved particle filtering method was proposed. The HF channel has multipath、fading and time-varying characteristics, and using the dynamic channel prediction model and the phased semi-blind estimation by improved particle filtering can obtain the tracking performance for the time varying channel. Based on stratified resampling of particle filtering, a criterion is set during the particle choosing process to ensure the valid of the chosen particles. Simulation result shows the effectiveness of the proposed method.

English

The propagation of radio signals is affected by several factors that contribute to the degradation of its quality and these are more significant on the propagation of wireless signals with low-power radios, typically used in Wireless Sensor Networks (WSNs). This makes radio links in WSNs to be unpredictable. This paper presents the development of an indoor channel prediction model of Wireless Sensor Network (WSN). A WSN testbed comprising of four TelosB sensor nodes was built at the corridor of first floor of Goddian Ezekwem building, faculty of Engineering, Nnamdi Azikiwe University, Awka. Three of the sensor nodes were placed at angles and the remaining one was attached to a laptop and used as the sink. Extensive measurements of RSSI were taken at distances of 1m to 7m at the interval of 1m. Channel prediction model of the environment was developed from the measured data using Linear Regression Analysis. The developed model was tested and the regression data analysis gives the R Square (R2) as 0.86, Multiple R as 0.93 and Adjusted R Square as 0.70.

Two-stage EWMA-based H.264 SVC bandwidth adaptation

Proposed is a new scalable video coding (SVC) bandwidth (BW) adaptation method over a WIFI. To cope with the variable channel condition, a new channel prediction model is proposed based on the modified two-stage exponentially weighted moving average (EWMA); also, to provide fine grain BW adaptation of H.264 SVC, the slice group (SG)-based layer switching method is proposed based on the channel prediction model. In the experiments conducted, the average gain was 2.14 dB in PSNR.

Particle filtering based autoregressive channel prediction model

A particle filtering based AutoRegressive (AR) channel prediction model is presented for cognitive radio systems. Firstly, this paper introduces the particle filtering and the system model. Secondly, the AR model of order p is used to approximate the flat Rayleigh fading channels; its stability is discussed, and an algorithm for solving the AR model parameters is also given. Finally, an AR channel prediction model based on particle filtering and second-order AR model is presented. Simulation results show that the performance of the proposed AR channel prediction model based on particle filtering is better than that of Kalman filtering.