A Machine Learning Approach for 5G SINR Prediction

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.

Medium Access-Based Scheduling Scheme for Cyber Physical Systems in 5G Networks

The development of the 5G mobile communication standard attempts to meet the future needs of data users. The impact of Cyber Physical Systems (CPS) is crucial in Internet of Things (IoT) and other emerging technologies. The design of medium access mechanisms for CPS such as radio resource scheduling schemes has a significant effect on network performance. Recent literature shows that limited work is available on uplink scheduling schemes, particularly in the 5G domain. Planning a network that can address the modern needs of users entails efficient CPS scheduling mechanisms such that resources are amicably distributed between users of contrasting priorities. The prime focus of this work is to design and develop an uplink radio resource scheduling framework for CPS-based future networks such as 5G. In the designed framework, scarce radio resources are sought to be distributed efficiently according to the service-based needs of users. The proposed scheduling scheme is a service aware (SA) scheduler designed for CPS in accordance with the 5G network peculiarities, intended to achieve higher throughput and reduced latency. The proposed SA scheduler supports multi-bearer traffic and is capable of providing resources in adverse channel conditions in an efficient manner. The SA scheduling mechanism’s performance is evaluated and compared with renowned scheduling algorithms such as blind equal throughput (BET), maximum throughput (MT), and proportional fair (PF) scheduling schemes. The simulation results obtained in a cellular environment demonstrate that the SA scheduler achieves acceptable cell throughput and end-to-end delay results in all scenarios and out-performs other contemporary scheduling schemes.

Intelligent Radio Resource Scheduling for LTE-Advanced using Wavelet Neural Network

This paper presents a novel technique for the efficient resource scheduling for Long Term Evaluation Advanced downlink transmission using wavelet neural network. The dynamism and the uncertainty in the resource scheduling due to the large scale of the network has been taken care through wavelet neural network. The proposed neural network based approach is trained to provide the best scheduling rule at every transmission time interval. Due to the superior estimation capability and better dynamic characteristics than conventional neural network, wavelet neural network offers a better radio resource scheduling. The objective of the proposed scheme is to enhance the system throughput, spectral efficiency and the system capacity. The simulation analysis is performed to verify the effectiveness of the theoretical development.