Task Offloading Scheme Based On Behavior Evaluation In Maritime Edge Computing

The rapid development of the Internet of Things and 5G has brought new opportunities to the marine wireless communication network.Meanwhile,with the large-scale deployment of intelligent terminal equipment,maritime wireless communication networks have put forward more stringent requirements for bandwidth,delay,and capacity.As a new computing mode,edge computing brings calculation and storage resources to the edge of the network,which effectively alleviates the bandwidth pressure brought by remote transmission and improve the efficiency of task processing.Maritime network deployment environment is complicated and has the characteristics of dynamicity and reliability,which makes the application of edge computing more complicated in the field of marine communications.How to achieve efficient and reliable mission unloading in complex environmental environment is the problem that needs to be solved urgently.Considering the complexity of the maritime environment,the task offloading scheme with multiobjective joint optimization of edge computing is further proposed to avoid packet loss,failure and node overload and to achieve reliable task offloading in the maritime wireless communication network.The main research work of this paper is as follows:Firstly,we construct an evaluation mechanism of offloading request behavior to evaluate the credibility of task offloading service requesters.By analyzing the characteristics of task authenticity and identifying the filtered false tasks,the delay overhead and resource waste caused by false task execution in edge network are reduced.The experimental results show that the model can not only identify and intercept the bad behavior of non-cooperative nodes effectively to ensure the reliability of task sources,but also improve the effective utilization of resources.Secondly,we construct a comprehensive evaluation mechanism of offloading cooperation to evaluate the credibility of resource providers with offloading cooperation trust.By analyzing the resource utilization rate of edge nodes and the offloading/execution of task,we can reward the trust behaviors and punish the bad behaviors of nodes,which encourage the integrity service of nodes.Then,the credible candidate node set is constructed to divide the edge nodes.The particle swarm optimization algorithm based on search discovery probability is designed to search the best cooperative node and realize the reliable offloading service of computing tasks.The results show that the model can effectively improve the success rate of task execution and reduce the time cost of task multiple offloading decisions.Finally,we construct the framework of Maritime Wireless Mesh Network(MWMN)considering the influence of ship mobility and cooperation on the communication of network nodes.A multi-objective joint optimization task offloading scheme is proposed to solve task offloading problems in MWMN.To be specific,the ship motion model is established to analyze its position change and network connectivity.And taking delay and energy consumption as constraints,an offloading path optimization algorithm is designed by considering the ability of network resources,channel transmission and node execution.Then,an improved chaotic ant colony optimization algorithm is used to find the best offloading path.The experimental results show that the proposed offloading scheme improves the success rate and offloading efficiency of task execution,and ensures the resource balance and stability of the network.