| With the development of the fifth generation(5G)mobile communication systems,a large number of emerging network applications have spilled out,such as industrial automation,augmented reality,and autonomous driving.The explosive growth of these applications has provided a lot of convenience to human life,but also put forward requirements of higher performance indicators to 5G mobile communication systems.First of all,these emerging network applications are usually computationally intensively and have strict requirements on latency.The computing resources carried by ordinary mobile terminals such as mobile phones and devices in the Internet of things(Io T)are limited,and it is difficult to meet the demands of these applications.Second,the development of emerging applications has led to a substantial increment in mobile data traffic,and the demands of those applications have gradually shown diversification.The situations mentioned above have brought unprecedented challenges to the network.Mobile edge computing(MEC)is considered to be one of the key technologies in 5G.MEC refers to the provision of the Internet service environment and cloud computing capabilities at the edge of the mobile network,by sinking network services to the radio access network side closer to mobile users.MEC can reduce latency,offer efficient network management and control,and support service distribution functions.Task offloading is a key technology in MEC,the user terminal sends computing tasks to the MEC network for assisting task processing,mainly to solve the equipment’s deficiencies in resource caching,computing performance,and energy consumption.With the goal of jointly optimizing latency and energy consumption,this thesis conducts research on the task offloading method in MEC,and mainly carries out the following work:In view of the current situation that the communications,computing,and caching are separate in edge networks,the integration of multiple technologies in the mobile edge is explored,and proposed a technology that integrates mobile edge communications,computing,and caching(MEC3).In the MEC3 technology,communication,computing,and caching resources assist each other to jointly improve the efficiency of task processing.Subsequently,in the edge network based on the MEC3 technology,an improved Hungarian algorithm is proposed for the task offloading problem in Io T scenarios.When each task is offloading,the task execution latency,execution cost,and the available resources of edge nodes are considered in a balanced manner,and the energy consumption and latency of task processing are optimized.Then this thesis explored how to set appropriate caching resources for MEC base stations under relatively stable traffic to avoid waste of resources.The simulation results show that the improved hungary algorithm proposed in this thesis can effectively reduce the latency and energy consumption of task offloading.The optimal response offloading algorithm is introduced into the edge network based on MEC3,and simulations verify that the algorithm can effectively combine with MEC3 technology to reduce the latency and energy consumption of task processing.Further,the algorithm is extended to the maritime area communication environment,the objective function is adjusted according to the needs of the maritime area,and the computing capacity,communication capacity and caching capacity of the node are comprehensively considered when allocating resources for each user.The simulation results show that based on MEC3 technology,the optimal response offloading algorithm can effectively reduce the total cost of maritime area communication services.The research work in this thesis can provide theoretical and methodological support for the applications of the MEC technology in 5G.At the same time,it can provide an effective solution for task offloading in MEC. |
