Edge Service Placement Optimization for Location-Based Service

Location-based service (LBS) is necessary and useful for several applications including navigation and games. These real-time applications require high accuracy and low delay. In general, the complexity of indoor localization algorithms used in LBS depends on the size of fingerprint data. This can lead to long delays when operating in large-scale areas. In this paper, we propose a novel optimization framework for edge service placement, aiming at minimizing the overall cost of edge computing deployment and service response time. Our placement strategy is used to solve the formulated edge node placement problems. The simulated annealing approach is then used in solution space exploration to discover the optimal solution efficiently. The results show that our proposed framework can outperform the existing work with a 27.58% improvement in the service response time on the simulated data, and a 41.94% improvement in the service response time on the real-world large-scale data.