An SDN/ML-Based Adaptive Cell Selection Approach for HetNets: A Real-World Case Study in London, UK

Abstract

Heterogeneous networks (HetNets) are one of the key enabling technologies for nextgeneration networks. They aim to provide high capacity, low installation cost, and distributed traffic loads. The cell selection issue is an open research problem in HetNets, due to the different characteristics of base stations and the existence of a large number of them. In this paper, a novel software-defined networking (SDN)/machine learning (ML)-based adaptive algorithm is proposed, called adaptive two-tier, based on the K-nearest neighbor (A2T-KNN) algorithm. It is designed for millimeter wave (mmWave)based HetNets and it has the ability to adapt to the various movement features of moving vehicles, as well as the different characteristics of the base stations. A real-world case is considered in the center of London. Simulation results demonstrate that A2T-KNN achieves high prediction performance in association with different vehicle features and configuration information. It outperforms other related schemes in terms of average number of handovers by up to 45.83%. Moreover, it was found to enhance the average achievable downlink data rate and network energy efficiency achieved by vehicles by up to 17.18% and 16.86%, respectively.

A Comprehensive Review on Artificial Intelligence/Machine Learning Algorithms for Empowering the Future IoT Toward 6G Era

“…However, HetNets face resource management related issues, interference and system optimization. For instance, in [9], the study attempts to address the cell selection approach in HetNets. This operation needs to consider different cell sizes and high frequency reusability and issues such as high handover rates due to users' movement in small areas, which can affect the network performance as well as the user experience.…”

“…A central controller, for example, software defined network (SDN) controller, can utilize ML to perform effective cell selection operation in the communication systems for future IoT. However, it needs to be able to select the appropriate base station by taking into account the characteristics of the HetNets and user device mobility as well as minimization of handover rate [9], [11]. Mobile user device detection with Wi-Fi fingerprinting and crowdsourcing mechanisms can relieve the effort of surveying procedures.…”

“…Validation of the classifier performance with respect to PSO, decision tree, GA and hidden Markov model [90] Target tracking Validation of the model against K-means clustering and extended Kalman filter [91] Device authentication Verification of the model against ID spoofing attacks [92] Trust management mechanism Malicious device detection and device misjudgment probability reduction [93] Protection against DoS attacks Reduction of malicious node missing detection rate and false detection rate KNN [94] Spectrum auction Spectrum efficiency improvement with resistance against collusion [9] Cell selection Improved handover operation, throughput and network energy efficiency [95] CNN-based indoor localization with KNN for computing target location Low average localization error with respect to SAE and DNN [96] Indoor localization Analysis of the model in terms of localization error and computational complexity [97] Device fingerprinting with KNN, distance metric learning and online multitask metric learning Improvement of distance estimation with respect to ANN approaches [98] Fingerprint database construction for indoor localization Fingerprint database recovery with high accuracy with respect to SVT-MC, IALM-MC and PSFM-GRP [99] Indoor localization Performance comparison with Naïve Bayes in terms of accuracy, precision and computational complexity [18] Device clustering Improved system throughput against K-means clustering a: Applications:…”

“…Cell selection problem is an open issue in heterogeneous networks due to their presence in large numbers and difference in base station behaviors. A KNN based cell selection algorithm is presented in [9] for mmWave communication to choose optimum base stations from two-tier base stations. Indoor localization efforts based on received signal strength fingerprint techniques are affected by instability of the signal strength indicator and negligence of Wi-Fi signal distribution diversity and network traffic.…”

A2T-Boost: An Adaptive Cell Selection Approach for 5G/SDN-Based Vehicular Networks

“…The cell selection decision can be coordinated by using SDN solution [27], and the combination of SDN and ML creates a new network management approach [28], [29].…”