Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there m...Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there may be multiple servers and devices that can provide services to the same user simultaneously. This paper proposes a userside adaptive user service deployment algorithm ASD(Adaptive Service Deployment) based on reinforcement learning algorithms. Without relying on complex system information, it can master only a few tasks and users. In the case of attributes, perform effective service deployment decisions, analyze and redefine the key parameters of existing algorithms, and dynamically adjust strategies according to task types and available node types to optimize user experience delay. Experiments show that the ASD algorithm can implement user-side decision-making for service deployment. While effectively improving parameter settings in the traditional Multi-Armed Bandit algorithm,it can reduce user-perceived delay and enhance service quality compared with other strategies.展开更多
基金supported in part by the Industrial Internet Innovation and Development Project "Industrial robot external safety enhancement device"(TC200H030)the Cooperation project between Chongqing Municipal undergraduate universities and institutes affiliated to CAS (HZ2021015)
文摘Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there may be multiple servers and devices that can provide services to the same user simultaneously. This paper proposes a userside adaptive user service deployment algorithm ASD(Adaptive Service Deployment) based on reinforcement learning algorithms. Without relying on complex system information, it can master only a few tasks and users. In the case of attributes, perform effective service deployment decisions, analyze and redefine the key parameters of existing algorithms, and dynamically adjust strategies according to task types and available node types to optimize user experience delay. Experiments show that the ASD algorithm can implement user-side decision-making for service deployment. While effectively improving parameter settings in the traditional Multi-Armed Bandit algorithm,it can reduce user-perceived delay and enhance service quality compared with other strategies.
