With the development of intelligent transportation, various computation intensive and delay sensitive applications are emerging in the Internet of Vehicles (IoV). The B5G/6G (Beyond 5th generation mobile communication technology/6th generation mobile communication technology) network has the characteristics of ultralow latency and ultra many connections. The deployment of the network in boxes (NIBs) supporting B5G/6G network in the vehicle can realize the real-time communication with the edge server (ES) and offload the task to the ES. However, the current multiaccess edge computing (MEC) lacks research on cooperative processing among multiple ESs, and the efficiency of data-intensive computation tasks is still insufficient. In this article, we investigate the cooperative offloading of multitype tasks among ESs in B5G/6G networks under a dynamic environment. In order to minimize the delay of task execution, we regard cooperative offloading as a Markov decision process (MDP), and improve the convergence speed and stability of traditional soft actor-critic (SAC) algorithm by the adaptive weight sampling mechanism. Finally, an offline centralized training distributed execution framework based on improved soft actor critical (OCTDE-ISAC) is proposed to optimize the cooperative offloading strategy. The experimental results show that the proposed algorithm is better than the existing algorithm in terms of latency.

Mobile management is a challenging technology in Mobile Edge Computing (MEC). When the device is moving, computation tasks need to be dynamically migrated between multiple edge servers to maintain service continuity. This paper proposes a migration optimization of distributed task in MEC by deep reinforcement learning solution to optimize delay. In Multi-agent Deep Reinforcement Learning (MADRL), we construct an adaptive weight deep deterministic policy gradient (AWDDPG) algorithm to optimize the migration cost and service delay, and adopt centralized training and distributed execution to solve the high-dimensional problem. Experiments show that our algorithm greatly reduces the service delay compared with the related algorithms.

In mobile edge computing(MEC), application partitioning can split the executions into local and edge server parts. Optimal partitioning will allow mobile devices to obtain the highest benefit from Mobile Edge Computing (MEC). In this paper, a new approach on task offloading scheduling for application of mobile edge computing is proposed. We divide the computing task into several subtasks. Then, we analyze the overhead of the system, and propose a fine-grained strategy for task scheduling and offloading in a multi-user MEC system. For reducing the energy consumption and delay, the computation offloading is considered as a constrained multi-objective optimization problem (CMOP), which can be solved by an improved NSGA-II algorithm. The experimental results show that the proposed algorithm can find a large number of optimal solutions to adjust the corresponding offloading decision according to the real-world situation.

This paper proposes and designs a new method of the best path selection algorithm with length priority to analyze and solve the optimal path planning problem of intelligent driving vehicles in practical applications. Through the understanding and learning of the reinforcement learning algorithm, we proposed a new method of the best path selection with length priority based on the prior knowledge applied reinforcement learning strategy, and improved the search direction setting of the shortest path in the program, simplified the process of shortest path search. This path optimization method can effectively help different types of intelligent driving vehicles to smoothly select the best path in the traffic network with limited height, width and weight, accident and traffic jam. Through simulation experiments and scene experiments, it is proved that the proposed algorithm has good stability, high efficiency and practicability.

As a hierarchical network architecture, the cluster architecture can improve the routing performance greatly for vehicular ad hoc networks (VANETs) by grouping the vehicle nodes. However, the existing clustering algorithms only consider the mobility of a vehicle when selecting the cluster head. The rapid mobility of vehicles makes the link between nodes less reliable in cluster. A slight change in the speed of cluster head nodes has a great influence on the cluster members and even causes the cluster head to switch frequently. These problems make the traditional clustering algorithms perform poorly in the stability and reliability of the VANET. A novel passive multi-hop clustering algorithm (PMC) is proposed to solve these problems in this paper. The PMC algorithm is based on the idea of a multi-hop clustering algorithm that ensures the coverage and stability of cluster. In the cluster head selection phase, a priority-based neighbor-following strategy is proposed to select the optimal neighbor nodes to join the same cluster. This strategy makes the inter-cluster nodes have high reliability and stability. By ensuring the stability of the cluster members and selecting the most stable node as the cluster head in the N-hop range, the stability of the clustering is greatly improved. In the cluster maintenance phase, by introducing the cluster merging mechanism, the reliability and robustness of the cluster are further improved. In order to validate the performance of the PMC algorithm, we do many detailed comparison experiments with the algorithms of N-HOP, VMaSC, and DMCNF in the NS2 environment.

Considered the wireless sensor network clustering structure, a new big data collecting method based on compressive sensing is proposed. The collection process is as follows: in the cluster, the sink node sets the corresponding seed vector based on the distribution of network, and then sends it to each cluster head. Cluster head can generate corresponding own random spacing sparse matrix based on its received seed vector, and collect data through compressive sensing technology; Among clusters, clusters forward measurement values to sink node along multi-hop routing tree which we built before. Performance analyzing and comparison of results show that this method is superior to other methods regardless of in a cluster or inter-cluster.

Since there is a competition between subcarriers of Internet of Things (IOT) because FBMC (Filter Bank Multicarrier) modulation technology does not need subcarriers to be orthogonal to each other, we consider the game method to optimize subcarrier allocation. Considering the height of secondary user and base station's antenna, the total data transmission rate limit, total power consumption constraint and power consumption constraint on a single subcarrier, a nonlinear fractional programming problem is established where maximum energy efficiency is the objective function, total data transmission rate limit, total power consumption constraint and power consumption constraint on a single subcarrier are constraint conditions. Through experimental simulation, EESA- EG proposed in this paper gives the most reasonable subcarrier allocation scheme, allocates more subcarriers for the subcarriers with better channel state and the energy efficiency in EESA-EG is optimal.