Adjustable Multi-Objective Deep Reinforcement Learning-Based Edge User Allocation

Multi-Access Edge Computing (MEC) is a popular and promising paradigm that allows service providers to serve their users from nearby servers. In order to fully leverage the advantages of MEC, the mapping between users and edge servers is of utmost importance for service providers. The Edge User Allocation (EUA) problem has been widely studied from the perspective of service providers with different objectives, e.g., maximizing the number of allocated users, respecting the latency threshold, minimizing overall system cost, etc. However, service providers tend to have dynamic priorities for different objectives over time. In certain situations, a service provider may opt to prioritize the minimization of their system cost at the expense of not meeting all their users expectations, or vice-versa, throughout a range of priority degrees. In this paper, we present a Deep Reinforcement Learning (DRL) approach for allocating users to edge servers according to dynamic priorities. We consider the online EUA problem where users arrive and depart dynamically, and propose a distributed solution that does not require full observation of all the servers to make allocation decisions. We offer a solution for both user-satisfaction and cost-effectiveness, while allowing the service provider to adjust their priority for each objective. A series of experiments have been conducted to evaluate the performance of our approach, under different priority degrees, against other baseline approaches. The results show the potential benefits of the proposed scheme in providing an adjustable multi-option solution for service providers.