The use of unmanned aerial vehicles (UAVs) is a promising solution for collecting data from wireless Internet of Things (IoT) devices and offloading to mobile edge computing (MEC) server embedded access points (APs) equipped with powerful servers. This article presents a solution to optimize the energy efficiency of UAV relaying in the IoT system, which assists in programming the multiple UAV flight trajectories and bandwidth allocation schemes to scientifically and energy-efficiently transmit the data from IoT devices to MEC servers. Furthermore, in order to ensure the continuous and effective data relaying of the UAVs, we deploy a number of decentralized wireless charging stations (CSs) in the system to replenish the UAVs’ energy and enable them to provide long-term services. Specifically, we propose a deep reinforcement learning-based efficient IoT data relaying method, where we mainly apply deep deterministic policy gradient (DDPG) to solve this dynamic programming problem with large action spaces. Experimental results demonstrate that the DDPG-based method for UAV efficient data collection and offloading (DDPG-UCO) algorithm outperforms other five baseline methods in terms of the UAV energy efficiency, amount of data relayed and data interaction energy consumption rate while maintaining a high level of geographical fairness of the relaying service.

Multiaccess edge computing (MEC) is a new paradigm to meet the demand of resource-hungry and latency-sensitive services by enabling the placement of services and execution of computing tasks at the edge of radio access networks much closer to resource-constrained devices. However, how to serve more requests while reducing service latency by exploiting limited resources (storage capacities, CPU cycles, communication bandwidth) is still a critical issue in the multidevice MEC-assisted IoT networks, since the time-varying computing demands of devices and unavailability of future information make it difficult to determine where to handle computation tasks and which services to cache. In this article, we propose a twin-timescale framework to jointly optimize adaptive request scheduling (RS) and cooperative service caching (SC) in the multidevices and MEC-assisted networks, in order to explore request dynamic, MECs heterogeneity, service difference. To accommodate the unavailability of future information and unknown system dynamics, we, respectively, formulate RS and SC as partially observable Markov decision process (POMDP) problems. Then, we propose a deep reinforcement learning (DRL)-based online algorithm to improve the service latency reduction ratio and hit rate, which do not requirea prioriknowledge such as service popularity. Moreover, we give the optimal CPU cycles and communication bandwidth allocations in order to further minimize the average service latency. Extensive and trace-driven simulation results demonstrate the efficacy of the proposed approach.

Unmanned aerial vehicles (UAVs) have been considered as a promising approach for providing additional computation capability and extensive coverage to ground mobile devices (MDs), especially in the scenario where the communication infrastructure is unavailable. This article investigates a UAV-assisted multiaccess edge computing system, where a number of ground MDs are served by a flying UAV and a ground base station, both of them are equipped with computation resources. The system aims to minimize the weighted cost of time latency and energy consumption, subject to the constraints on offloading decisions and resource competition. Since this problem is NP-hard, and the MDs are autonomous, we propose a game theory-based scheme to find the optimal solution and prove the existence of the Nash equilibrium. Meanwhile, we propose another two schemes as the benchmark to evaluate the efficiency and effectiveness of the game-theoretic solution. The simulation results show that the game-theoretic scheme is able to achieve a near-optimal performance, and the convergence time is also stable when the number of MDs increases.

We consider a general multi-user mobile edge computing (MEC) system with multiple MEC servers. For each user, a MEC serves both as the network access point and a computation service provider, where users can offload part of their tasks. We formulate the sum cost of time delay and energy consumption for all mobile users as our optimization objective. This problem is NP-hard in general. In this paper, we jointly optimize the offloading decisions of all users tasks as well as the allocation of computation and communication resources, pursing the minimal sum cost for all users. We proposed an efficient two-stage algorithm comprising of one-dimensional search (ODS) and alternating optimization (AO). The first stage is responsible for obtaining the optimal offloading decision, and the second stage is in charge of computing a locally optimal solution for resource allocation. It is shown to give nearly optimal performance under a wide range of parameter settings. Through evaluating the performance of different combinations of the two stages of ODS-AO algorithm, we provide insights into their roles and contributions in the overall solution. Our simulation results show that the proposed scheme achieves significant reduction on the average delay and sum cost compared to other baselines.