A Resource Allocation Algorithm Based On Mobile Edge Computing

Recently,with the rapid development of the mobile internet and Internet of Things(IoT),various intelligent terminals are rapidly spreading,and the data traffic in mobile networks is exponentially growing.Mobile networks are facing huge challenges such as higher transmission rates,broad network bandwidth,and lower transmission delay.At the same time,the application programs on intelligent terminals need more computing resources and communication resources,resulting in a heavy burden on communication networks.The emergence of mobile cloud computing provides a new way to solve these problems.However,traditional mobile cloud computing technology has problems such as long transmission delay and low reliability,which cannot meet the requirement of low latency and high reliability of 5G networks.In this context,Mobile Edge Computing(MEC)technology with low latency and high reliability has attracted wide attentions from scholars and has become one of the key technologies for 5G networks.In the MEC system,the communication resources of the wireless network and the computing resources of the MEC server are limited.In addition,different applications have different requirements on performance indexes such as energy consumption and delay.Therefore,in order to meet the performance requirements of different applications and improve the system resource utilization,the MEC system needs to allocate communication resources and computing resources reasonably in the process of computation offloading to ensure the quality of service(QoS)of the users.This paper is devoted to studying the resource allocation algorithm of communication resources and computing resources in the MEC system.By taking into account factors such as system cost,network channel status and user's QoS requirements,the problem of resource allocation and computation offloading decision in MEC system is solved to reduce system cost,extend battery life and improve user's QoS.The main research contents of this paper included(1)a resource allocation algorithm based on the monetary cost model in the cooperative scenario and(2)a joint optimization algorithm for computation offloading and resource allocation based on energy harvesting technology.The main contributions are as follows.Firstly,from the perspective of reducing system economic costs,this paper studies how to allocate system communication resources and computing resources to minimize the system currency cost.In this paper,a resource allocation algorithm based on Lyapunov optimization theory is proposed.The algorithm takes into account factors such as task delay requirement,network channel state and system cost.In the case of ensuring long-term stable operation of the system,the computing resources of the mobile terminal and the MEC server and the communication resources of the wireless network are jointly allocated to minimize the system currency cost.In addition,the algorithm only needs the current system state information with a lower complexity.Simulation results show that the algorithm can meet the delay requirements of computing tasks,ensure the long-term stable operation of the system,and effectively reduce the monetary cost of the system.Secondly,from the perspective of extending battery life and reducing task execution consumption,this paper studies how mobile devices with energy harvesting(EH)function perform computation offloading and resource allocation to reduce the task execution cost.In this paper,a joint optimization algorithm for computation offloading and resource allocation based on Lyapunov optimization theory is proposed.First of all,the system model of the MEC system with energy harvesting function is given,and then the task execution energy consumption and execution delay are weighted and summed to establish the model of minimizing the task execution cost.Finally,the Lyapunov optimization theory is used to derive the energy harvesting decision and the optimal solution of resource allocation.The computation offloading strategy is obtained by comparing the task execution cost in the local execution mode and the MEC execution mode.Simulation results show that the algorithm can effectively reduce the task execution cost of the system when compared with the traditional algorithm,and adjust the control parameters to achieve the trade-off between system energy consumption and execution delay.