Mobility Management for Blockchain-Based Ultra-Dense Edge Computing: A Deep Reinforcement Learning Approach

Abstract

Ultra-dense edge computing is expected to provide delay-sensitive and computational-intensive services for mobile devices. Due to the complexity and unpredictability of the network environment, it is challenging to ensure the continuity and security of computing offloading services in the process of user movement. Most existing works consider the decisions of communication handover and computational offloading simultaneously while ignoring the security on offloading tasks. In light of this, we propose a secure mobility management framework for blockchain-based ultra-dense edge computing, where blockchain reduces duplicate authentication between edge servers. We jointly optimize the wireless handover and service migration decisions between base stations, which is translated into a multi-objective dynamic optimization problem using the Lyapunov optimization. The optimization problem is solved by deep reinforcement learning approach based on the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Actor</i> – <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Critic</i> method. Finally, we use simulation studies to evaluate the performance of the proposed scheme. The results show that, compared with other existing schemes, the proposed scheme can reduce the average delay of computing tasks, the rate of tasks failure and the rate of handover.