scholarly journals A Machine Learning Approach for 5G SINR Prediction

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1660
Author(s):  
Ruzat Ullah ◽  
Safdar Nawaz Khan Marwat ◽  
Arbab Masood Ahmad ◽  
Salman Ahmed ◽  
Abdul Hafeez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mobile Networks ◽  
Radio Resource Management ◽  
Radio Resource ◽  
Machine Learning Approach ◽  
Channel Conditions ◽  
Radio Resources ◽  
Auto Regressive ◽  
Artificial Neural Network Ann ◽  
Radio Resource Scheduling

Artificial Intelligence (AI) and Machine Learning (ML) are envisaged to play key roles in 5G networks. Efficient radio resource management is of paramount importance for network operators. With the advent of newer technologies, infrastructure, and plans, spending significant radio resources on estimating channel conditions in mobile networks poses a challenge. Automating the process of predicting channel conditions can efficiently utilize resources. To this point, we propose an ML-based technique, i.e., an Artificial Neural Network (ANN) for predicting SINR (Signal-to-Interference-and-Noise-Ratio) in order to mitigate the radio resource usage in mobile networks. Radio resource scheduling is generally achieved on the basis of estimated channel conditions, i.e., SINR with the help of Sounding Reference Signals (SRS). The proposed Non-Linear Auto Regressive External/Exogenous (NARX)-based ANN aims to minimize the rate of sending SRS and achieves an accuracy of R = 0.87. This can lead to vacating up to 4% of the spectrum, improving bandwidth efficiency and decreasing uplink power consumption.

scholarly journals Machine Learning for Disseminating Cooperative Awareness Messages in Cellular V2V Communications

2021 ◽  
Author(s):  
Luca Lusvarghi ◽  
Maria Luisa Merani
Keyword(s):  
Machine Learning ◽  
Resource Assignment ◽  
Radio Resource ◽  
Vehicle To Vehicle ◽  
Generation Times ◽  
Radio Resources ◽  
V2v Communications ◽  
Message Broadcasting ◽  
Cooperative Awareness Messages ◽  
Cooperative Awareness

<div>This paper develops a novel Machine Learning (ML)-based strategy to distribute aperiodic Cooperative Awareness Messages (CAMs) through cellular Vehicle-to-Vehicle (V2V) communications. According to it, an ML algorithm is employed by each vehicle to forecast its future CAM generation times; then, the vehicle autonomously selects the radio resources for message broadcasting on the basis of the forecast provided by the algorithm. This action is combined with a wise analysis of the radio resources available for transmission, that identifies subchannels where collisions might occur, to avoid selecting them.</div><div>Extensive simulations show that the accuracy in the prediction of the CAMs’ temporal pattern is excellent. Exploiting this knowledge in the strategy for radio resource assignment, and carefully identifying idle resources, allows to outperform the legacy LTE-V2X Mode 4 in all respects.</div>

scholarly journals A Deep Learning Based Transmission Algorithm for Mobile Device-to-Device Networks

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1361 ◽  
Author(s):  
Tae-Won Ban ◽  
Woongsup Lee
Keyword(s):  
Deep Learning ◽  
Mobile Networks ◽  
Spectral Efficiency ◽  
Radio Resource Management ◽  
Cellular Communications ◽  
D2d Communications ◽  
Radio Resource ◽  
Next Generation Mobile Networks ◽  
Device To Device ◽  
Mobile Caching

Recently, device-to-device (D2D) communications have been attracting substantial attention because they can greatly improve coverage, spectral efficiency, and energy efficiency, compared to conventional cellular communications. They are also indispensable for the mobile caching network, which is an emerging technology for next-generation mobile networks. We investigate a cellular overlay D2D network where a dedicated radio resource is allocated for D2D communications to remove cross-interference with cellular communications and all D2D devices share the dedicated radio resource to improve the spectral efficiency. More specifically, we study a problem of radio resource management for D2D networks, which is one of the most challenging problems in D2D networks, and we also propose a new transmission algorithm for D2D networks based on deep learning with a convolutional neural network (CNN). A CNN is formulated to yield a binary vector indicating whether to allow each D2D pair to transmit data. In order to train the CNN and verify the trained CNN, we obtain data samples from a suboptimal algorithm. Our numerical results show that the accuracies of the proposed deep learning based transmission algorithm reach about 85%∼95% in spite of its simple structure due to the limitation in computing power.

Detection of Abnormal Activity to Alert the Nearby Persons via M-DNN Based Surveillance System

2021 ◽  
Vol 16 ◽  
pp. 668-685
Author(s):  
Shankargoud Patil ◽  
Kappargaon S. Prabhushetty
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Support Vector ◽  
Learning Approach ◽  
Normal Behavior ◽  
Machine Learning Approach ◽  
Artificial Neural Network Ann ◽  
Static Conditions ◽  
Advanced System

In today's environment, video surveillance is critical. When artificial intelligence, machine learning, and deep learning were introduced into the system, the technology had progressed much too far. Different methods are in place using the above combinations to help distinguish various wary activities from the live tracking of footages. Human behavior is the most unpredictable, and determining whether it is suspicious or normal is quite tough. In a theoretical setting, a deep learning approach is utilized to detect suspicious or normal behavior and sends an alarm to the nearby people if suspicious activity is predicted. In this paper, data fusion technique is used for feature extraction which gives an accurate outcome. Moreover, the classes are classified by the well effective machine learning approach of modified deep neural network (M-DNN), that predicts the classes very well. The proposed method gains 95% accuracy, as well the advanced system is contrast with previous methods like artificial neural network (ANN), random forest (RF) and support vector machine (SVM). This approach is well fitted for dynamic and static conditions.

A Survey of Radio Resource Management in Cognitive Radio Networks

2013 ◽  
pp. 264-289
Author(s):  
Chengshi Zhao ◽  
Wenping Li ◽  
Jing Li ◽  
Zheng Zhou ◽  
Kyungsup Kwak
Keyword(s):  
Cognitive Radio ◽  
Resource Management ◽  
Dynamic Spectrum Access ◽  
Radio Resource Management ◽  
Radio Spectrum ◽  
Radio Resource ◽  
Green Communications ◽  
Radio Resources ◽  
Adaptive Power

The framework of “green communications” has been proposed as a promising approach to address the issue of improving resource-efficiency and the energy-efficiency during the utilization of the radio spectrum. Cognitive Radio (CR), which performs radio resource sensing and adaptation, is an emerging technology that is up to the requests of green communications. However, CR networks impose serious challenges due to the fluctuating nature of the available radio resources corresponding to the diverse quality-of-service requirements of various applications. This chapter provides an overview of radio resource management in CR networks from several aspects, namely dynamic spectrum access, adaptive power control, time slot, and code scheduling. More specifically, the discussion focuses on the deployment of CR networks that do not require modification to existing networks. A brief overview of the radio resources in CR networks is provided. Then, three challenges to radio resource management are discussed.

scholarly journals Survey on TYDER Based Algorithm for Radio Resource Allocation in 5G Heterogeneous Scenarios

2020 ◽  
Author(s):  
Premi A ◽  
Rajakumar S
Keyword(s):  
Resource Allocation ◽  
Cellular Networks ◽  
Mobile Networks ◽  
Base Station ◽  
Radio Resource ◽  
Machine To Machine ◽  
Generation Network ◽  
Radio Resources ◽  
Massive Number

The rapid growth of machine-to-machine communications in cellular networks poses the challenge of meeting the various Quality-of-Service requirements of massive number of machine to machine communications devices with limited radio resources. In this study, we discuss the minimum resource allocation problem for M2M communications through 5G and beyond the cellular networks. Then, in 5G mobile networks we propose a TYDER based algorithm for allocation the radio resource. The next-generation network environment, associated with heterogeneous performance, is expected to include the networks of diverse types. This paper introduces the network Traffic Type-based Differentiated Reputation (TYDER) solution, which differentiates the data delivery process according to its type.This approach however requires creativity in the reduction of hardware and cost decrease in the plan of little cell base station.

Sign in / Sign up

Export Citation Format

Share Document