基于强化学习的智能电网多接入边缘计算的位置隐私保护

Location Privacy Protection of Smart Grid MEC Based on Reinforcement Learning

文章以智能电网多接入边缘计算(multi-accessedgecomputing,MEC)中的移动终端电动汽车为主要研究对象,提出了一种既能满足系统能耗的计算卸载,又能实现对用户的位置隐私进行保护的方案。该方案以强化学习Q-learning算法为基础,根据MEC部署模式建立MEC计算卸载位置隐私保护模型,用户可根据隐私保护需求设置隐私保护强度,选择较远的MEC服务器进行计算卸载,在保证较低的系统能耗的情况下能够对自己的位置隐私进行保护。实验结果表明,所提出的地理位置隐私保护方案对保护用户的位置隐私具有良好的效果,并且用户可以根据个人的位置隐私保护需求调整保护程度达到不同的保护目的。

In this paper,taking the mobile terminal of electric vehicle in the smart grid multi-access edge computing(MEC)as the main research object,this paper proposes a scheme that can not only meet the computation offloading of system energy consumption,but also realize the protection of the user’s location privacy.The scheme is based on the Q-learning algorithm,according to the MEC deployment mode to establish MEC computing offload location privacy protection model,users can set the privacy protection intensity according to privacy protection needs,select a distant MEC server for computation offloading,in the case of ensuring low system energy consumption and can protect their own location privacy.Experimental results show that the geographical location privacy protection scheme proposed in this paper has a good effect on protecting the user’s location privacy,and the user can adjust the degree of protection according to the personal location privacy protection needs to achieve different protection purposes.