Service migration in MEC: an Approach Based on Deep Reinforcement Learning and Fuzzy Logic

Abstract

As a new computing paradigm, Mobile Edge Computing (MEC) sinks resources to the network edge to support real-time responses of services. Facing the demand for migrating services caused by the frequent movement of the mobile device, it is a great challenge to reduce the operation costs of migrating services with user requirements satisfied, especially for the continuous optimization of services deployed in hot spot areas. In order to address the above challenge, we propose the mechanism of dynamically migrating and optimally deploying services, which optimizes the latency and energy consumption of the service migration. Firstly, we introduce Markov Decision Process (MDP) to model changes of deployment locations of the single-user service, and devise the approach to determine whether to migrate a service at the current network status based on the dueling Deep Q-Network (DQN). Secondly, we propose the service pre-migration decision approach to determine where to migrate a service by combining the Long Short-Term Memory (LSTM) network and the attention mechanism, so as to determine the future moving area of the user and perform the migration decision in advance with the impact of migration service on service quality considered. Finally, we devise the distance-weighted matching algorithm based on the fuzzy logic to further optimize the selection of the most appropriate services to migrate in hotspot areas and the corresponding service migration regions, thus, the load pressure of the edge computing node caused by the imbalanced deployment density of service among multiple regions. Simulation results show that the proposed mechanism has significant improvements in overall operating costs compared with the cur-rent state of the art.