A mobile edge computing-oriented virtual machine deployment method

Abstract

The invention relates to a mobile edge computing-oriented virtual machine deployment method, which comprises the following steps: constructing a mobile edge computing environment, defining an energy consumption model, a virtual machine set VM and an edge server queue S of each edge server, carrying out virtual machine deployment by introducing a bat model of a second-order oscillation factor, deploying m virtual machines to n edge servers, training an improved LSTM learning model by using historical data deployed by the virtual machine, and performing virtual machine deployment based on the learning model. Second-order oscillation is introduced into the Bat algorithm, the problem of a local optimal solution is solved, an order transfer mechanism is used when searching is close to the optimal solution, the optimal solution continues to be searched, and finally an improved LSTM model is trained by using historical deployment data obtained by the algorithm. According to the invention, the historical data of the edge nodes can be fully utilized, the problems of limited resources, decentration and the like of the edge ends are considered, the energy consumption problem and the time delay problem are comprehensively considered, and the purposes of low energy consumption and low time delay are achieved.

Description

technical field [0001] The technical field of electrical digital data processing involved in the present invention, in particular, relates to a virtual machine deployment method for mobile edge computing. Background technique [0002] With the development of intelligent applications in virtual reality, autonomous driving and user equipment, the requirements for high computing power and low latency of servers are getting higher and higher; because cloud data centers are generally far away from the user side, they cannot handle computing-intensive and data-intensive applications in a timely manner Mobile edge computing emerges as the times require, which improves service quality and reduces latency by offloading computing tasks to edge servers. [0003] However, when the edge server receives a large number of storage tasks, it will cause huge energy consumption, and processing a large number of tasks at the same time will also increase the time delay. Therefore, the purpose of...

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the problems in the prior art of not comprehensively considering multiple indicators, ignoring the particularity of the edge computing environment, and not making full use of historical data, the present invention proposes a virtual machine deployment method for mobile edge computing, which can make full use of historical data , and according to the characteristics of weak resources and decentralization in the edge environment, a corresponding solution is proposed to achieve the goal of reducing energy consumption and delay, and then it is applied in the mobile edge computing environment

Images