Computation Offloading Scheme In Ultra-dense Networks Integrated With MEC

The popularity of smart terminals accelerates the development of the mobile communication industry.The development of mobile communication industry makes a variety of new applications continue to emerge.However,by the limit of the terminal resource,these intelligent terminals need a high-performance computing machine instead of them to completing some of the computing tasks in local devices.The emergence of Mobile Edge Computing(MEC)technology provides the possibility for the challenge.Mobile edge computing technology migrate the computing and storage of the cloud computing platform to the edge of radio access network.Deeply integrated of the traditional telecommunications cellular network and Internet services.By providing IT and cloud computing capability,traditional business services could be deployed in local area and close to the mobile devices.Even though,there are still some problems such as low density network coverage and excessive load on the central compute nodes in mobile edge computing.Based on the above problem,we proposed a strategy of combining mobile edge computing with Ultra-Dense Network(UDN)technology.Ultra-Dense Network(UDN)technology can improve the system throughput and reuse the frequency by increase the base station deployment density and further reduce users' access delay.Besides,we proposed a distributed computing offloading model to replace the center computing model.Distributed computing offloading can effiective reduce the pressure of center computing nodes,and enhance the reliability and stability of mobile edge computing systems.The mobile edge computing based on the ultra-dense network architecture provides more selectivity for users connecting and computing offloading.In this paper,we proposed a computation task offloading strategy,jointly considering fronthaul and backhaul link,and a distributed computing offloading scheme.The scheme aims to minimize the energy consumption under the users' delay constrain.The main innovations of this paper are summarized as follows:Firstly,we research and analyzed the status of mobile edge computing technology,and discussed the development of ultra-dense network based mobile edge computing technology.We summarized the measurement of energy consumption and delay cost in mobile edge computing.In this paper,we introduced the common mobile edge computing offloading strategy,and summarized the advantage and limitations of the related technology.Secondly,we proposed a computation task offloading strategy for ultra-dense network based mobile edge computing system under the delay constraint,and we jointly considering fronthaul and backhaul links.We apply artificial fish swarm algorithm(AFSA)to solve the proposed problem in a high efficiency.The simulation result shows that the algorithm could have a better performance.Besides,we also simulate the convergence of the algorithm.Thirdly,we proposed a distributed multi-device computation task offloading strategy.In the scenario of multi-device multi-base station,we use potential game model to minimize the computing offloading energy consumption under the delay constrain.From the simulation results we can see that the distributed computing offloading game can achieve Nash equipment and convergence to a point in the end.By comparing the simulation results with other computing offloading algorithm,we can conclude that the distributed computing offloading algorithm which designed in this paper can effectively save the energy cost.