Ultra-dense heterogeneous networks (HetNets) are deployment scenarios in the advent of fifth generation (5G) and beyond network generations. A massive number of small base stations (SBSs) and connected devices have been exponentially increasing. This has subsequently led to a rise of several mobility management issues which require optimization techniques to avoid performance degradation. Machine learning (ML) is a promising approach for future mobile communication networks (5G and beyond). It has the ability of improving the efficiency of complicated heterogeneous and decentralized networks. ML has proven to be significant in the mobility management field since it optimizes handover control parameters (HCPs) over various dynamic environments. To the best of the authors’ knowledge, no comprehensive survey deeply discussing a state-of-the-art ML algorithms in mobility robustness optimization (MRO) functions. However, each summarized algorithm in this study includes deployment scenario, ML type, methodology used, criteria, HCPs, key performance indicators (KPIs), simulators, and achievements which can assist researchers for future investigations in MRO functions. In addition, this study serves as a guide in the selection of proper optimization algorithms according to the outcomes of each algorithm. Furthermore, this study presented the common types of ML and the techniques used from each type to optimize the HCPs of the MRO functions. Moreover, high-mobility-aware and network topologies are presented in MRO function for further system enhancements. Besides, the survey further highlights several potential problems for upcoming research and provides future directions to address the issues of next generation wireless networks.

Recent studies on indoor positioning using Wi-Fi fingerprinting are motivated by the ubiquity of Wi-Fi networks and their promising positioning accuracy. Machine learning algorithms are commonly leveraged in indoor positioning works. The performance of machine learning based solutions are dependent on the availability, volume, quality, and diversity of related data. Several public datasets have been published in order to foster advancements in Wi-Fi based fingerprinting indoor positioning solutions. These datasets, however, lack dual-band Wi-Fi data within symmetric indoor environments. To fill this gap, this research work presents the UTMInDualSymFi dataset, as a source of dual-band Wi-Fi data, acquired within multiple residential buildings with symmetric deployment of access points. UTMInDualSymFi comprises the recorded dual-band raw data, training and test datasets, radio maps and supporting metadata. Additionally, a statistical radio map construction algorithm is presented. Benchmark performance was evaluated by implementing a machine-learning-based positioning algorithm on the dataset. In general, higher accuracy was observed, on the 5 GHz data scenarios. This systematically collected dataset enables the development and validation of future comprehensive solutions, inclusive of novel preprocessing, radio map construction, and positioning algorithms.

This paper presents the propagation path loss channel models, developed from real-field measurement in Universiti Teknologi Malaysia (UTM) Kuala Lumpur, Malaysia. The purpose of the study is to characterize the channel at 28 GHz for 5G communications system in line-of-sight corridors environment. Measurement campaigns were conducted to measure the wireless signal of received signal strength at three different construction of straight corridors, narrow, wide, and open corridors. The large-scale path loss models are developed using the closed-in reference distance and floating–intercept modeling approaches. Besides contributing path loss models at 28 GHz for different corridors dimension, the result found in this work discovered the breakpoint distance of radio propagation is seen varies differently at those corridors.