Unmanned aerial vehicles (UAVs) can be deployed in the air to provide high probabilities of line of sight (LoS) transmission, thus UAVs bring much gain for wireless communication systems. In this paper, we study a UAVs-aided self-organized device-to-device (D2D) network. Relay deployment, channel allocation and relay assignment are jointly optimized, aiming to maximize the capacity of the relay network. On account of the coupled relationship between the three optimization variables, an alternating optimization approach is proposed to solve this problem. The original problem is divided into two sub-problems. The first one is that of optimizing the channel allocation and relay assignment with fixed relay deployment. Considering without central controller, a reinforcement learning algorithm is proposed to solve this sub-problem. The second sub-problem is that of optimizing the relay deployment with fixed channel allocation and relay assignment. Assuming no knowledge of channel model and exact positions of the communication nodes, an online learning algorithm based on real-time capacity is proposed to solve this sub-problem. By solving the two sub-problems alternately and iteratively, the original problem is finally solved. Simulation results show that the UAVs-aided D2D network can achieve a high capacity via the joint optimization of relay deployment, channel allocation, and relay assignment.

With the advantages of high mobility, high maneuverability and high probability of line of sight (LoS) transmission, unmanned aerial vehicles (UAVs) have attracted much interest in assisting wireless communication systems. This paper considers a set of ground users cannot receive service from the base station because of a sudden malfunction of the base station, a UAV is deployed in the air to work as a relay to establish communication links between unable users and the neighboring base station. We are going to optimize the UAV relay deployment, aiming to maximize the capacity of the relay network. Considering the channel model and exact positions of ground users are priori unknown, the problem of deployment optimization can't be solved directly because of lacking parameters. Thus, considering multiple detecting UAVs are available and only one is available, model-free online deployment approaches are respectively proposed to solve this challenging problem. The optimal relay deployment is acquired via online learning and iteration without the knowledge of channel model and exact positions of the users but with the real-time measurement of relay capacity, thus the proposed model-free deployment approaches can be adaptive to the practical communication environment compared to the model-based optimization. Simulation results show that with the proposed model-free deployment approaches, relay network capacities are close to the optimum.

The development of edge computing based autonomous and connected vehicles (CAVs) provides a very promising solution for the construction of intelligent transportation system. Unfortunately, the existing methods are difficult to predict traffic flow accurately in such case due to not only the dynamic nature of the CAVs but also the considerable amount of missing traffic flow data. Based on this, we propose an online rolling traffic flow prediction method to provide support for the CAVs can be seen into practice. The new matrix factorization techniques proposed can learn the low-dimensional embeddings in the online setting and impute missing ones simultaneously. Moreover, instead of directly predicting the high-dimensional traffic flow data, a standard vector autoregressive (VAR) process is employed on low-dimensional embeddings to predict future values. Further, a multidimensional Cadzow method is proposed to solve the coefficient matrices of VAR efficiently even if there is noise. The simulation results on two real datasets show the applicability of the proposed method to online traffic flow prediction for edge computing-enhanced CAVs.

Supporting simultaneous access of machine-type devices is a critical challenge in machine-to-machine (M2M) communications. In this paper, we propose an optimal scheme to dynamically adjust the Access Class Barring (ACB) factor and the number of random access channel (RACH) resources for clustered machine-to-machine (M2M) communications, in which Delay-Sensitive (DS) devices coexist with Delay-Tolerant (DT) ones. In M2M communications, since delay-sensitive devices share random access resources with delay-tolerant devices, reducing the resources consumed by delay-sensitive devices means that there will be more resources available to delay-tolerant ones. Our goal is to optimize the random access scheme, which can not only satisfy the requirements of delay-sensitive devices, but also take the communication quality of delay-tolerant ones into consideration. We discuss this problem from the perspective of delay-sensitive services by adjusting the resource allocation and ACB scheme for these devices dynamically. Simulation results show that our proposed scheme realizes good performance in satisfying the delay-sensitive services as well as increasing the utilization rate of the random access resources allocated to them.

Except for the unmanned aerial vehicles (UAVs) providing specialized communication service, there may be many other UAVs executing various missions in the air. These UAVs may be idle in communication and thus are considered to work as opportunistic relays to enhance the ground device-to-device (D2D) network. On account of the dynamic behaviors and uncontrollable trajectories of the opportunistic UAVs, real-time relay assignment and channel allocation are two main factors that determine the network capacity. Thus, real-time relay assignment and channel allocation are optimized in this paper, aiming to maximize the long-term average capacity of this dynamic network. In order to implement relay assignment via the decentralized approach and resist the dynamic network characteristic, a mood-driven online learning relay selection approach is proposed for the D2D pairs, which not only utilizes the immediate transmission rate but also the variation tendency of the transmission rate. That is, the pairs with low transmission rate or with the tendency of rate decreasing will have a high probability to explore a better relay. The pairs with high transmission rate or with the tendency of rate increasing will have a high probability to continue to select the current relay. As a result, the dynamic network always has a tendency to increase its capacity. For the reason that the characteristic of channel selection in the dynamic network is similar to relay selection, a mood-driven approach that similar to the one used for relay selection is proposed for channel selection. And then, a time slot model is designed for joint relay selection and channel selection. Simulation results show that the opportunistic UAVs can significantly enhance the network capacity and the proposed mood-driven approach can adapt to the dynamic characteristic of the network.

Due to the high maneuverability of unmanned aerial vehicle (UAV), a cluster of UAVs are considered used to collect sensing data from the sensors that distributed randomly in an area without the terrestrial infrastructure. The cluster members work as relays to forward the sensing data from sensors to the cluster head. For the reason that the relay deployment impacts the transmission rate and coverage area directly, we are going to optimize the deployment of the UAV relays, aiming to maximize the total capacity of the network. The problem of multi-relay deployment is intractable for two reasons. On one hand, because of the interactional and coupled relationship among the UAV relays, when the deployment of any given relay changes, the deployment optimization of other relays will be affected. On the other hand, on account of that the exact positions of the sensors are unknown, the deployment optimization of the UAV relays cannot be completed directly because of lacking parameters. In order to tackle the coupled relationship among the UAV relays, the problem of multi-relay deployment is modeled as a local interaction game. We prove that the multi-relay deployment game is an exact potential game that has at least one Nash equilibrium (NE) point. Then, the better reply-based relay deployment approach, which is an online learning approach that does not demand the information of the exact positions of sensors, is proposed to search the NE point. The simulation results show that the network capacity is significantly enhanced with the proposed relays deployment approach.