Channel stability prediction to optimize signaling overhead in 5G networks using machine learning

Bakri, Sihem; Bouaziz, Maha; Frangoudis, Pantelis A.; Ksentini, Adlen

doi:10.1109/icc40277.2020.9149048

Cited by 7 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [40], 5G channel stability prediction, in connection with throughput and data loss, was investigated using neural network (NN) and support vector machines (SVM) methods. The authors recorded 96.43% and 92.86% prediction accuracies.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning-Based GPR with LBFGS Kernel Parameters Selection for Optimal Throughput Mining in 5G Wireless Networks

Isabona

Imoize

Ojo³

et al. 2023

Sustainability

View full text Add to dashboard Cite

Considering the ever-growing demand for an efficient method of deductive mining and extrapolative analysis of large-scale dimensional datasets, it is very critical to explore advanced machine learning models and algorithms that can reliably meet the demands of modern cellular networks, satisfying computational efficiency and high precision requirements. One non-parametric supervised machine learning model that finds useful applications in cellular networks is the Gaussian process regression (GPR). The GPR model holds a key controlling kernel function whose hyperparameters can be tuned to enhance its supervised predictive learning and adaptive modeling capabilities. In this paper, the limited-memory Broyden–Fletcher–Goldfarb–Shanno (LBFGS) with kernel parameters selection (KPS) algorithm is employed to tune the GPR model kernel hyperparameters rather than using the standard Bayesian optimization (BOP), which is computationally expensive and does not guarantee substantive precision accuracy in the extrapolative analysis of a large-scale dimensional dataset. In particular, the hybrid GPR–LBFGS is exploited for adaptive optimal extrapolative learning and estimation of throughput data obtained from an operational 5G new radio network. The extrapolative learning accuracy of the proposed GPR–LBFGS with the KPS algorithm was analyzed and compared using standard performance metrics such as the mean absolute error, mean percentage error, root mean square error and correlation coefficient. Generally, results revealed that the GPR model combined with the LBFGS kernel hyperparameter selection is superior to the Bayesian hyperparameter selection method. Specifically, at a 25 m distance, the proposed GPR–LBFGS with the KPS method attained 0.16 MAE accuracy in throughput data prediction. In contrast, the other methods attained 46.06 and 53.68 MAE accuracies. Similarly, at 50 m, 75 m, 100 m, and 160 m measurement distances, the proposed method attained 0.24, 0.18, 0.25, and 0.11 MAE accuracies, respectively, in throughput data prediction, while the two standard methods attained 47.46, 49.93, 29.80, 53.92 and 47.61, 52.54, 53.43, 54.97, respectively. Overall, the GPR–LBFGS with the KPS method would find valuable applications in 5G and beyond 5 G wireless communication systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Machine Learning-Based GPR with LBFGS Kernel Parameters Selection for Optimal Throughput Mining in 5G Wireless Networks

Isabona

Imoize

Ojo³

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…

…”

mentioning

confidence: 99%

Prediction of Channel Stability to Optimize Signalling Overhead in 5G Networks using ML Algorithm

Fathima¹

2023

IJSREM

View full text Add to dashboard Cite

As we are leaving in 5G era which promises us to give high throughput rate, better efficiency rate, and high bandwidth etc as its feature make headlines to give advanced and enhanced services in various sector whether it could be IOT, infrastructure, agriculture, and health care [1]. Giving well-grounded communication technology possesses a fundamental challenge for 5G system in both Core network and Radio Access Network (RAN) levels [2]. To get a better credibility at RAN level, base station (EnodeB or gNodeB in 4G and 5G respectively) should allocate proper amount of resource as per UE and select appropriate Modulation and scheme (MCS) to give better user experience. The amount of Physical Resource Blocks is directly proportional to channel condition at the User Equipment (UE) end [5]. The Base Station would generally know the real time channel strength of each UE, which then later provides accordingly resource to the UE, as UE would be sending periodically CQI to Base station. However, the periodic transmission of CQI would lead to signaling overhead which hampers the performance of RAN. Henceforth its foremost thing to average it or to optimize the CQI value to give a better user experience. Therefore, will be exploring four such machine learning algorithms (ANN, reinforcement learning, KNN and SVM) to optimize the CQI and would be analyzing which Algorithm will give better performance. Key Words: CQI, Machine Algorithm, RAN, Offloading, Handover, Base Station

show abstract

Signaling Overhead Reduction Techniques in Device-to-Device Communications: Paradigm for 5G and Beyond

et al. 2021

View full text Add to dashboard Cite

Channel stability prediction to optimize signaling overhead in 5G networks using machine learning

Cited by 7 publications

References 14 publications

Machine Learning-Based GPR with LBFGS Kernel Parameters Selection for Optimal Throughput Mining in 5G Wireless Networks

Machine Learning-Based GPR with LBFGS Kernel Parameters Selection for Optimal Throughput Mining in 5G Wireless Networks

Prediction of Channel Stability to Optimize Signalling Overhead in 5G Networks using ML Algorithm

Signaling Overhead Reduction Techniques in Device-to-Device Communications: Paradigm for 5G and Beyond

Contact Info

Product

Resources

About