With the rapid development of vehicular edge computing (VEC) and artificial intelligence (AI), the emergence of vehicle edge intelligence meets the need for real-time vehicle intelligence applications. But the execution of deep neural networks (DNNs) requires a large amount of data input, which results in a large amount of computing resources required for the execution of DNN tasks. This also brings a certain burden to the deployment of DNN tasks and the resource allocation of edge servers. In addition, due to the high mobility of vehicles in the VEC, the backhaul delay of vehicle edge intelligent task results increases, affecting the vehicle’s quality of experience (QoE). We propose a joint optimization strategy for service migration and resource allocation aimed at minimizing the average task completion delay. This strategy comprehensively considers service migration actions and edge server resource allocation, which is proved to be a mixed integer nonlinear programming (MINLP) problem, and hence we formulate it as an Markov decision process (MDP). To solve this problem, we propose a service migration algorithm based on the self-attention mechanism-based double deep Q-network and deep deterministic policy gradient algorithm (SA-DDQN-DDPG) to solve it to obtain the optimal system service migration strategy. The experimental results show that the proposed SA-DDQN-DDPG algorithm has good performance in reducing latency. The average migration latency is reduced by 40.41%, 20.7%, and 14.50% compared with always, DQN and DDQN, respectively.

How to reduce energy consumption, improve resource utilization and put forward efficient resource management model so as to improve the media cloud performance and mobile users’ quality of service (QoS) is the problem needed to be addressed. Our proposed media cloud distributed scheduling model aims to maximize the utility of media cloud. The media cloud distributed scheduling policy for resource-intensive mobile application includes media service provisioning and cloud resource scheduling among media cloud datacenter. The media cloud service scheduling optimization algorithms include two sub-algorithms. The practical example of video streaming service for mobile users is also given. The experiments study the performance of media cloud distributed scheduling algorithm and related algorithms. The experiment results show that proposed algorithm has better performance than related algorithms.

The paper presents a hybrid cloud service provisioning and selection optimization scheme, and proposes a hybrid cloud model which consists of hybrid cloud users, private cloud and public cloud. This scheme aims to effectively provide cloud service and allocate cloud resources, such that the system utility can be maximized subject to public cloud resource constraints and hybrid cloud users constraints. The paper makes use of a utility-driven approach to solve interaction among private cloud user, hybrid cloud service provider and public cloud provider in hybrid cloud environment. The paper presents hybrid cloud service provisioning and selection algorithm in hybrid cloud. The hybrid cloud market consists of hybrid cloud user agent, hybrid cloud service agent and hybrid cloud agent, which represent the interests of different roles. The experiments are designed to compare the performance of proposed algorithm with the other related work.