Mobile-edge computing (MEC) has emerged as a promising computing paradigm in the 5G architecture, which can empower user equipments (UEs) with computation and energy resources offered by migrating workloads from UEs to the nearby MEC servers. Although the issues of computation offloading and resource allocation in MEC have been studied with different optimization objectives, they mainly focus on facilitating the performance in the quasistatic system, and seldomly consider time-varying system conditions in the time domain. In this article, we investigate the joint optimization of computation offloading and resource allocation in a dynamic multiuser MEC system. Our objective is to minimize the energy consumption of the entire MEC system, by considering the delay constraint as well as the uncertain resource requirements of heterogeneous computation tasks. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem, and propose a value iteration-based reinforcement learning (RL) method, named $Q$ -Learning, to determine the joint policy of computation offloading and resource allocation. To avoid the curse of dimensionality, we further propose a double deep $Q$ network (DDQN)-based method, which can efficiently approximate the value function of $Q$ -learning. The simulation results demonstrate that the proposed methods significantly outperform other baseline methods in different scenarios, except the exhaustion method. Especially, the proposed DDQN-based method achieves very close performance with the exhaustion method, and can significantly reduce the average of 20%, 35%, and 53% energy consumption compared with offloading decision, local first method, and offloading first method, respectively, when the number of UEs is 5.

Reconfigurable Intelligent Surface (RIS) has grown rapidly due to its performance improvement for wireless networks, and the integration of unmanned aerial vehicle (UAV) and RIS has obtained widespread attention. In this paper, the downlink of non-orthogonal multiple access (NOMA) UAV networks equipped with RIS is considered. The objective is to optimize the UAV trajectory with RIS phase shift to maximize the system capacity under the UAV energy consumption constraint. By deep reinforcement learning, a capacity maximization scheme under energy consumption constraints based on double deep Q-Network (DDQN) is proposed. The joint optimization of UAV trajectory with RIS phase shift design is achieved by DDQN algorithm. From the numerical results, the proposed optimization scheme can increase the system capacity of the RIS-UAV-assisted NOMA networks.

With the continuous expansion of the power Internet of Things and the number of Smart Devices (SDs), the data generated by SDs has exponentially increased. The traditional cloud-based smart grid cannot meet the low latency and high reliability requirements of emerging applications. By moving computing, data, and services from the centralized cloud to Edge Servers (ESs), edge computing exhibits excellent performance in communication delay and traffic reduction. Simultaneously, service caching also shows attractive advantages in handling the surge in data traffic. This paper considers the joint optimization of computing offloading and service caching in edge computing-based smart grid, and formulates the problem as a Mixed-Integer Non-Linear Program, aiming to minimize the task cost of the system. The original problem is decomposed into an equivalent master problem and sub-problem, and a Collaborative Computing Offloading and Resource Allocation Method (CCORAM) is proposed to solve the problem, which includes two low-complexity algorithms. Specifically, a gradient descent allocation algorithm is first proposed to determine the computing resource allocation strategy, and then a game theory-based algorithm is proposed to determine the computing strategy. Simulation results show that CCORAM with low-complexity is very close to the optimal method, and performs much better than other benchmark methods.

This paper considers computation offloading and service caching in a three-tier mobile cloud-edge computing structure, in which Mobile Users (MUs) have subscribed to the Cloud Service Center (CSC) for computation offloading services and paid related fees monthly or yearly, and the CSC provides computation services to subscribed MUs and charges service fees. Long transmission distance and communication resource shortage caused by the increasing number of offloaded MUs may make the CSC unable to satisfy the delay requirements of MUs. Hence, the CSC can purchase some computation and communication resources from Edge Servers (ESs) with limited caching capacities and computation resources to assist MUs in computation offloading. However, from the perspective of the CSC, it remains open to jointly optimize the strategies of computation offloading, service caching, and resource allocation to meet the delay requirements of MUs while reducing the cost of the CSC. Therefore, a novel Deep Reinforcement Learning-based Computation Offloading and Service Caching Mechanism, named DRLCOSCM is proposed to jointly optimize the offloading decision, service caching, and resource allocation strategies, so as to minimize the cost of the CSC while ensuring the delay requirements of MUs. In DRLCOSCM, the optimization problem is formulated as a Mixed Integer Non-Linear Programming (MINLP) problem, and an Asynchronous Advantage Actor-Critic-based (A3C-based) algorithm is proposed to solve the problem. The simulation results show that DRLCOSCM significantly outperforms the other baseline methods in different scenarios.

Recently, due to the increasing popularity of enjoying various multimedia services on mobile devices (e.g., smartphones, ipads and electronic tablets), the generated mobile data traffic has been explosively growing and has become a serve burden on mobile network operators. To address such a serious challenge in mobile networks, an effective approach is to manage data traffic by using complementary technologies (e.g., small cell network, WiFi network, and so on) to achieve mobile data offloading. In this paper, we discuss the recent advances in the techniques of mobile data offloading. Particularly, based on the initiator diversity of data offloading, we classify the existing mobile data offloading technologies into four categories, i.e., data offloading through small cell networks, data offloading through WiFi networks, data offloading through opportunistic mobile networks and data offloading through heterogeneous networks. Besides, we show a detailed taxonomy of the related mobile data offloading technologies by discussing the pros and cons for various offloading technologies for different problems in mobile networks. Finally, we outline some opening research issues and challenges, which can provide guidelines for future research work.

Mobile edge computing (MEC) is becoming popular in many civilian applications. However, due to the broadcast nature of wireless connections, traditional MEC is open to eavesdropping attacks that endanger mobile users’ information confidentiality. Friendly jamming (FJ), as one of the physical layer security techniques, can efficiently protect users from such threats by degrading attackers’ wiretap channel capacities. In this paper, we propose an FJ-based physical layer security (PLS) mechanism to safeguard the confidentiality of data uploading in MEC services. We design a comprehensive security scheme that uses FJ from both base station (BS) and nearby mobile users to cover upload transmission. Accordingly, the eavesdropping risk zone (ERZ) is formulated as an area under high secrecy outage probability (SOP). To promote FJ from users, we further introduce Device-to-device (D2D) communication-based FJ, which is inspired by non-orthogonal multiple access (NOMA) techniques. Then, we formulate, simplify, and solve the problem by optimizing the MEC secrecy performance under the required risk, with efficiencies in data uploading, energy consumption, and incentive delivery. Furthermore, we tackle the challenge of efficient incentive design under information asymmetry by introducing Contract Theory and providing differentiated rewards. By simulations, we evaluate the mechanism in terms of secrecy performance and incentive efficiency under information asymmetry, and the results accordingly show the effectiveness of the proposed security mechanism.