As a mode of processing task request, edge computing paradigm can reduce task delay and effectively alleviate network congestion caused by the proliferation of Internet of things(IoT) devices compared with cloud computing. However, in the actual construction of the network, there are various edge autonomous subnets in the adjacent areas, which leads to the possibility of unbalance of server load among autonomous subnets during the peak period of task request. In this paper, a deep reinforcement learning algorithm is proposed to solve the complex computation offloading problem for the heterogeneous Edge Computing Server(ECS) collaborative computing. The problem is solved based on the real-time state of the network and the attributes of the task, which adopts Actor Critic and Policy Gradient’s Deep Deterministic Policy Gradient(DDPG) to make optimized decisions of computation offloading. Considering multi-task, the heterogeneity of edge subnet and mobility of edge devices, the proposed algorithm can learn the network environment and generate the computation offloading decision to minimize the task delay.The simulation results show that the proposed DDPG-based algorithm is competitive compared with the Deep Q Network(DQN) algorithm and Asynchronous Advantage Actor-Critic(A3C) algorithm. Moreover, the optimal solutions are leveraged to analyze the influence of edge network parameters on task delay.

As a novel computing technology closer to business ends, edge computing has become an effective solution for delay sensitive business of power Internet of Things (IoT), and promotes the application and development of Internet of Things technology in smart grids. However, the inherent characteristics of a single edge node with limited resources may fail to meet the delay requirements for access ubiquitous IoT businesses of massive access. Multiple edge nodes are needed to cooperate with each other to optimize workload allocation to provide lower delay services. To this end, this paper proposes a workload allocation mechanism, orienting edge computing-based power IoT, which minimizes service delay. The workload optimization allocation model is established, and the optimal workload allocation oriented on delay among multiple edge nodes is further realized on the basis of computing resource optimization within single edge node. The BRT (Balanced initialization, Resource allocation, and Task allocation) algorithm is proposed. Based on balanced initialization of workload within edge nodes, the particle swarm algorithm modified by pheromone strategy is used to solve the problem of the computing resources allocation inside edge nodes. Finally, the task allocation among multiple edge servers is converted into a semi-definite programming problem. The simulation results show that the proposed BRT algorithm reduces the service delay by 9.1%, 16.9%, and 26.4%, and the service delay growth rate by 24.6%, 34.5%, and 38.7%, respectively, compared with SAA (Simulated Annealing Algorithm), LAB (LoAd Balancing) and LEAD (Latency-awarE workloAd offloaDing) algorithms.

This paper presents a novel approach for providing a mobile battery swapping service for electric vehicles (EVs) that is provided by a mobile battery swapping van. This battery swapping van can carry many fully charged batteries and drive up to an EV to swap a battery within a few minutes. First, a reasonable EV battery swapping architecture based on a battery swapping van is established in this paper. The function and role of each participant and the relationships between each participant are determined, especially their changes compared with the battery charging service. Second, the battery swapping service is described, including the service request priority and service request queuing model. To provide the battery swapping service efficiently and effectively, the battery swapping service request scheduling is analyzed well, and a minimum waiting time based on priority and satisfaction scheduling strategy (MWT-PS) is proposed. Finally, the battery swapping service is simulated, and the performance of MWT-PS is evaluated in simulation scenarios. The simulation results show that this novel approach can be used as a reference for a future system that provides reasonable and satisfying battery swapping service for EVs.

As a novel computing technology closer to business ends, edge computing has become an effective solution for delay sensitive business of power Internet of Things (IoT). However, the uneven spatial and temporal distribution of business requests in edge network leads to a significant difference in business busyness between edge nodes. Due to the natural lightweight and portability, container migration has become a critical technology for load balancing, thereby optimizing the resource utilization of edge nodes. To this end, this paper proposes a container migration-based decision-making (CMDM) mechanism in power IoT. First, a load differentiation matrix model between edge nodes is constructed to determine the timing of container migration. Then, a container migration model of load balancing joint migration cost (LBJC) is established to minimize the impact of container migration while balancing the load of edge network. Finally, the migration priority of containers is determined from the perspective of resource correlation and business relevance, and by introducing a pseudo-random ratio rule and combining the local pheromone evaporation with global pheromone update at the same time, a migration algorithm based on modified Ant Colony System (MACS) is designed to utilize the LBJC model and thus guiding the choice of possible migration actions. The simulation results show that compared with genetic algorithm (GA) and Space Aware Best Fit Decreasing (SABFD) algorithm, the comprehensive performance of CMDM in load balancing joint migration cost is improved by 7.3% and 12.5% respectively.

With the development of wireless local area networks and intelligent transportation technologies, the Internet of Vehicles is considered to be an effective method to alleviate the severe situation of the current transportation system. The vehicles in the Internet of Vehicles system build the Vehicular Ad Hoc Networks through wireless communication technology and dynamically provide different services through the real-time driving information broadcast by the vehicles. Vehicle drivers can control the distance, planning the driving route, between vehicles according to the current traffic environment, which improves the overall safety and efficiency of the traffic system. Due to the particularity of the Internet of Vehicles system service, vehicles need to broadcast their location information frequently. Attackers can collect and analyze vehicle broadcast information to steal privacy and even directionally track the owner through the driving trajectory, bringing serious security risks. This paper proposes a blockchain-based privacy protection system for the Internet of Vehicles. The system combines the blockchain with the Internet of Vehicles system to design a safe and efficient two-way authentication and key agreement algorithm through encryption and signature algorithm, which also solves the central dependency problem of the traditional Internet of Vehicles system.

With the development of Internet of things (IoT) technology and smart grid infrastructure, edge computing has become an effective solution to meet the delay requirements of the electric power IoT. Due to the limitation of battery capacity and data transmission mode of IoT terminals, the business collaboration computing must consider the energy consumption of the terminals. Since delay and energy consumption are the optimization goals of two co-directional changes, it is difficult to find a business collaboration computing mechanism that simultaneously minimizes delay and energy consumption. This paper takes the unmanned aerial vehicle (UAV) inspection business scenario in the electric power IoT based on edge computing as the representative, and proposes a two-stage business collaboration computing mechanism including resources allocation and task allocation to optimize the business delay and energy consumption of UAV by decoupling the complex correlation between resource allocation and task allocation. A steepest descent resource allocation algorithm is proposed. On the basis of resource allocation, an improved multiobjective evolutionary algorithm based on decomposition by dynamically adjusting the size of neighborhood and the cross distribution index is proposed as a task allocation algorithm to minimize energy consumption and business delay. Simulation results show that our algorithms can respectively reduce the business delay and energy consumption by more than 6.4% and 9.5% compared with other algorithms.