Bandit Learning-based Service Placement and Resource Allocation for Mobile Edge Computing

Abstract

Service placement is a significant issue in mobile edge computing (MEC) system. Many works have proposed efficient offline approaches for service placement problems in MEC system. However, because of the randomness and uncertainty of mobile networks, it is impractical for these approaches to be implemented. Facing these uncertainty, we propose an online service placement scheme for MEC system without knowing service demand and network states in advance. In order to maximize the long-term accumulated reward obtained by service placement with limited resource constraint, we analyse this problem by a combinatorial multi-armed bandit (MAB) framework. In addition, because we simultaneously consider the service placement and resource allocation among services, it can be formulated as a multiple choice knapsack problem (MCKP) in each time slot. To solve this long-term reward maximization problem, we first propose a combinatorial upper bound confidence(CUCB)-based online service placement and resource allocation scheme. Then, we analyse the performance of this algorithm theoretically. Finally, simulation results show the efficiency of the algorithm.