Summary In mobile edge computing (MEC), due to the limited computing resources and power of mobile augmented reality (MAR) devices, cache identification results which can reduce power consumption and executing time of mobile devices are the solution to process MAR tasks. In this paper, we study an allocation cache problem in MAR systems. The allocation cache problem is formulated as maximizing the cache utility of cache hit ratio and user preference factor. To solve this problem, a cache resource allocation and cache space adjustment policy for edge computing systems is proposed. We also propose an improved double deep Q‐network (DDQN) algorithm to learn this policy. Simulation results show that the policy greatly improves the cache hit ratio compared with the traditional caching policy.

Recently, Unmanned Aerial Vehicles (UAVs) have attracted much attention due to their flexibility and low cost. However, there are limitations for multiple UAVs such as limited energy and collaborative coverage. To achieve a better coverage performance, each UAV needs to find the optimal position to cover many ground users while saving energy. However, there are trade-offs between coverage utility and energy consumption. In this paper, we study a multi-UAV communication scenario where multi-UAV array is deployed to provide wireless coverage for mobile ground users. Considering the number, 3D positions, and speeds of UAVs, we formulate a Coverage Utility and Energy Multi-objective Optimization Problem (CUEMOP) to simultaneously maximize the total coverage utility and minimize the total energy consumption of UAVs. Due to the complexity and NP-hardness of the formulated CUEMOP, we propose Improved Multi-objective Grey Wolf Optimizer (ImMOGWO) algorithm. In this algorithm, we design the Role Determination (RD) algorithm to cluster the ground users and prepare for initialization of UAV number and position. Hybrid solution initialization (HSI) algorithm is to initialize multi-dimensional variables and overcome algorithm inefficiency caused by random initialization. The Levy flight and Sin Cosine method based on the MOGWO algorithm (LSCMGA) is proposed to increase the diversity of solutions and ensure the convergence effect of the algorithm. Simulation results verify that proposed ImMOGWO algorithm has better performance than some other benchmark methods.

In recent years, multi-access edge computing (MEC) has become a hot topic. In this paper, we study a task offloading problem combined with bandwidth allocation in multi-access edge computing. Based on alliance game, we formulate bandwidth allocation to minimize the dissatisfaction of alliances. Then, we formulate the task offloading decision-making to minimize the delay. The delay consists of communication delay and execution delay. To solve the offloading problem, we convert the dissatisfaction of alliance into a vector, and obtain the Pareto optimal through multi-objective particle swarm algorithm. Then, we use Branch and Bound method to construct the propagation tree to facilitate decision-making. To evaluate the edge servers in the tree, we build an evaluation matrix and transform the matrix to a set of evaluation index which is used on task offloading decision-making. A large number of experimental results show that our algorithm is better than compared algorithm.

The rapid development of edge computing has an impact on the Internet of Vehicles (IoV). However, the high-speed mobility of vehicles makes the task offloading delay unstable and unreliable. Hence, this paper studies the task offloading problem to provide stable computing, communication and storage services for user vehicles in vehicle networks. The offloading problem is formulated to minimize cost consumption under the maximum delay constraint by jointly considering the positions, speeds and computation resources of vehicles. Due to the complexity of the problem, we propose the vehicle deep Q-network (V-DQN) algorithm. In V-DQN algorithm, we firstly propose a vehicle adaptive feedback (VAF) algorithm to obtain the priority setting of processing tasks for service vehicles. Then, the V-DQN algorithm is implemented based on the result of VAF to realize task offloading strategy. Specially, the interruption problem caused by the movement of the vehicle is formulated as a return function as part of evaluating the task offloading strategy. The simulation results show that our proposed scheme significantly reduces cost consumption and improves Quality of Service (QoS).