Smart Handover Scheme for a 5G-Enabled Ambulance

Abstract

Remote first-aid treatment on ambulances is a promising application of 5G. However, there still exist gaps between the capabilities of current 5G networks and the ultra-high requirements of remote emergency on ambulances. Therefore, we investigate a smart handover scheme to enhance the transmission capacity of the 5G wireless links for ambulances. First, we introduce the mobility and mmWave communication models of a 5G-enabled ambulance in an urban environment. Based on these models, we formulate the handover problem to maximize the expected transmission rate during a driving period of the 5G-enabled ambulance. Considering the randomness of system environments and the delay caused by the handover process, we apply a far-sighted Artificial Intelligence (AI) technology, i.e., Deep Q Network (DQN)-based algorithm, to solve this problem. For resolving the limitations of vanilla DQN, we adopt effective techniques including multi-step learning, double DQN, and NoisyNet to improve the performances of DQN and propose a Noisy Double DQN (NDDQN)-based handover algorithm. Simulation results verify the effectiveness and superiority of our NDDQN-based smart handover scheme compared with vanilla DQN and UCB-based handover algorithms.