An Overview of Reinforcement Learning Algorithms for Handover Management in 5G Ultra-Dense Small Cell Networks

The fifth generation (5G) wireless technology emerged with marvelous effort to state, design, deployment and standardize the upcoming wireless network generation. Artificial intelligence (AI) and machine learning (ML) techniques are well capable to support 5G latest technologies that are expected to deliver high data rate to upcoming use cases and services such as massive machine type communications (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable low latency communications (uRLLC). These services will surely help Gbps of data within the latency of few milliseconds in Internet of Things paradigm. This survey presented 5G mobility management in ultra-dense small cells networks using reinforcement learning techniques. First, we discussed existing surveys then we are focused on handover (HO) management in ultra-dense small cells (UDSC) scenario. Following, this study also discussed how machine learning algorithms can help in different HO scenarios. Nevertheless, future directions and challenges for 5G UDSC networks were concisely addressed.

IMPSO and Linear Programming-Based Energy-Efficient Cell Association Algorithm for Backhaul-Constrained Ultra-Dense Small-Cell Networks

This paper studies the energy efficiency optimization problem for coordinated multipoint (CoMP)-enabled and backhaul-constrained ultra-dense small-cell networks (UDNs). Energy efficiency is an eternal topic for future wireless communication networks; however, taking actual bottleneck of the backhaul link and the coordinated network architecture into consideration, it is difficult to find an effective way to improve the energy efficiency of the network. Aiming at this problem, we propose to combine cell association, subchannel allocation, backhaul resource allocation, and sleep/on of the cells together to develop an optimization algorithm for energy efficiency in UDN and then solve the formulated energy efficiency optimization problem by means of improved modified particle swarm optimization (IMPSO) and linear programming in mathematics. Simulation results indicate that nearly 13 % energy cost saving and 21 % energy efficiency improvement can be obtained by combining IMPSO with linear programming, and the backhaul link data rate can be improved by 30 % as the number of small cells increases. From the results, it can be found that by combining IMPSO with linear programming, the proposed algorithm can improve the network energy efficiency effectively at the expense of limited complexity.

3D-mapping of human lymph node and spleen reveals integrated neuronal, vascular, and ductal cell networks

As secondary lymphoid organs, the spleen and lymph node represent important hubs for both innate and adaptive immunity. Neuroanatomical and tracing data, largely derived from rodents, suggest that lymph nodes contain sensory and sympathetic innervation, whereas the spleen contains postganglionic sympathetic innervation, with conflicting views regarding the existence of cholinergic or vagal innervation. Herein, we map the neuronal, vascular, and sinus cell networks from human spleen and lymph node using highly multiplexed CODEX (CO-Detection by indEXing) and 3D light sheet microscopy of cleared tissues. These data demonstrate striking delineation of two distinct layers within the lymph node subcapsular sinus-the ceiling defined by Podoplanin expression and floor by LYVE1, which overlays the lymph node follicles. Within the lymph node interior, we observed a mesh-like vessel network innervated with GAP43 and beta3-tubulin. Dense perivascular innervation occurred in both tissues, including a subset of axonal processes expressing choline acetyl transferase (ChAT). Four neuronal markers (ChAT, PGP9.5, tyrosine hydroxylase, and beta3-tubulin) localized to the arterial tunica externa suggest expression in the nervi vasorum while GAP43 was expressed within the internal elastic membrane of arteries. These data represent highly novel 3D visualization of perivascular and periductal autonomic innervation within these two key human organs.

Single-cell Networks Reorganise to Facilitate Whole-brain Supercritical Dynamics During Epileptic Seizures

Excitation-inhibition (EI) balance may be required for the organisation of brain dynamics to a phase transition, criticality, which confers computational benefits. Brain pathology associated with EI imbalance may therefore occur due to a deviation from criticality. However, evidence linking critical dynamics with EI imbalance-induced pathology is lacking. Here, we studied the effect of EI imbalance-induced epileptic seizures on brain dynamics, using in vivo whole-brain 2-photon imaging of GCaMP6s larval zebrafish at single-neuron resolution. We demonstrate the importance of EI balance for criticality, with EI imbalance causing a loss of whole-brain critical statistics. Using network models we show that a reorganisation of network topology drives this loss of criticality. Seizure dynamics match theoretical predictions for networks driven away from a phase transition into disorder, with the emergence of chaos and a loss of network-mediated separation, dynamic range and metastability. These results demonstrate that EI imbalance drives a pathological deviation from criticality.