The applications of Unmanned Aerial Vehicles (UAVs) are rapidly growing in domains such as surveillance, logistics, and entertainment and require continuous connectivity with cellular networks to ensure their seamless operations. However, handover policies in current cellular networks are primarily designed for ground users, and thus are not appropriate for UAVs due to frequent fluctuations of signal strength in the air. This paper presents a novel handover decision scheme deploying Deep Reinforcement Learning (DRL) to prevent unnecessary handovers while maintaining stable connectivity. The proposed DRL framework takes the UAV state as an input for a proximal policy optimization algorithm and develops a Received Signal Strength Indicator (RSSI) based on a reward function for the online learning of UAV handover decisions. The proposed scheme is evaluated in a 3D-emulated UAV mobility environment where it reduces up to 76 and 73% of unnecessary handovers compared to greedy and Q-learning-based UAV handover decision schemes, respectively. Furthermore, this scheme ensures reliable communication with the UAV by maintaining the RSSI above −75 dBm more than 80% of the time.

Anomaly detection is essential to guarantee the correctness of sensory data collected from Internet of Things. The latest detection approaches only operate under one of the two general forms of short-term or long-term anomaly. In this article, we propose monotone split and conquer (MSC) scheme to tackle both anomaly forms. The proposed scheme exploits the spatial–temporal correlation between neighboring sensors to detect abnormal sensory data. MSC splits the collected data into monotonic subtrends in the training phase to establish the trend-based normal profiles for the online detection phase. To eradicate the overfitting phenomenon, we further develop a general formulation to estimate the square prediction error (SPE) control limit. Both monotone split and general formulation contribute to the advancement of MSC in terms of accuracy (ACC) and false positive rate (FPR) in the online detection phase. To evaluate the performance of MSC, we design a general anomaly model to generate artificial short-term and long-term anomalies. Numerical experiments with the Intel Berkeley Research Lab (IBRL) data set demonstrate that MSC obtains about 8% higher ACC and 5% lower FPR on average when compared to existing schemes. Remarkably, MSC requires only a few observations for anomaly detection as it is applicable to real-time systems.

Containers virtually package a piece of software and share the host Operating System (OS) upon deployment. This makes them notably light weight and suitable for dynamic service deployment at the network edge and Internet of Things (IoT) devices for reduced latency and energy consumption. Data collection, computation, and now intelligence is included in variety of IoT devices which have very tight latency and energy consumption conditions. Recent studies satisfy latency condition through containerized services deployment on IoT devices and gateways. They fail to account for the limited energy and computing resources of these devices which limit the scalability and concurrent services deployment. This paper aims to establish guidelines and identify critical factors for containerized services deployment on resource constrained IoT devices. For this purpose, two container orchestration tools (i.e., Docker Swarm and Kubernetes) are tested and compared on a baseline IoT gateways testbed. Experiments use Deep Learning driven data analytics and Intrusion Detection System services, and evaluate the time it takes to prepare and deploy a container (creation time), Central Processing Unit (CPU) utilization for concurrent containers deployment, memory usage under different traffic loads, and energy consumption. The results indicate that container creation time and memory usage are decisive factors for containerized micro service architecture.

Recent advances in big data technology collecting and analyzing large amounts of valuable data have attracted a lot of attention. When the information in non-reachable areas is required, IoT wireless sensor network technologies have to be applied. Sensors fundamentally have energy limitations, and it is almost impossible to replace energy-depleted sensors that have been deployed in an inaccessible region. Therefore, moving healthy sensors into the sensing hole will recover the faulty sensor area. In rough surfaces, hopping sensors would be more appropriate than wheel-driven mobile sensors. Sensor relocation algorithms to recover sensing holes have been researched variously in the past. However, the majority of studies to date have been inadequate in reality, since they are nothing but theoretical studies which assume that all the topology in the network is known and then computes the shortest path based on the nonrealistic backing up knowledge—The topology information. In this paper, we first propose a distributed hopping sensor relocation protocol. The possibility of movement of the hopping sensor is also considered to recover sensing holes and is not limited to applying the shortest path strategy. Finally, a performance analysis using OMNeT++ has demonstrated the solidification of the excellence of the proposed protocol.

Over the past few years, the use of wireless sensor networks in a range of Internet of Things (IoT) scenarios has grown in popularity. Since IoT sensor devices have restricted battery power, a proper IoT data aggregation approach is crucial to prolong the network lifetime. To this end, current approaches typically form a virtual aggregation backbone based on a connected dominating set or maximal independent set to utilize independent transmissions of dominators. However, they usually have a fairly long aggregation delay because the dominators become bottlenecks for receiving data from all dominatees. The problem of time-efficient data aggregation in multichannel duty-cycled IoT sensor networks is analyzed in this paper. We propose a novel aggregation approach, named LInk-delay-aware REinforcement (LIRE), leveraging active slots of sensors to explore a routing structure with pipeline links, then scheduling all transmissions in a bottom-up manner. The reinforcement schedule accelerates the aggregation by exploiting unused channels and time slots left off at every scheduling round. LIRE is evaluated in a variety of simulation scenarios through theoretical analysis and performance comparisons with a state-of-the-art scheme. The simulation results show that LIRE reduces more than 80% aggregation delay compared to the existing scheme.

Importance of user mobility has rapidly increased in 5G due to reduced cell sizes, management of Multi-access Edge Computing (MEC), and ultra-low latency services. Reactive nature of existing management systems is a bottleneck, and it can be solved by building proactive systems that exploit temporal characteristics of time-series mobility data to predict long-term user movement (i.e.path). However, user mobile path prediction with useable accuracy is a challenging task, particularly for lengthy target trajectories. This paper adopts general approaches to propose two models for predicting mobile path with high accuracy. Step Forward Iteration (SFI) model is based on recursive approach, whereas Encoder-Decoder (ED) model follows multi-output approach, and both the models use Long-Short Term Memory (LSTM) as the learning unit. Training and testing of these models is done on mobility datasets from the wireless network of Pangyo ICT Research Center, Korea and one of the Korean mobile operators. The experiment results show viability of the proposed models for leveraging mobile network management, as they outperform state-of-the-art GRU with attention (GRU-ATTN) and Transformer Network (TN) models. The highest prediction accuracies achieved for 3, 5, and 7 steps of target sequences (i.e.predicted mobile path) in the campus dataset are 96%, 90%, and 87%, respectively.