Research on Information Freshness of UAV-assisted IoT Networks Based on DDQN
Jin Xu, Xiangdong Jia, Zhenchao Hao · 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · 2022
In time-sensitive Internet of Things (IoT) systems which is assisted by Unmanned Aerial Vehicle (UA V), most of the existing researches focus on maximizing the system throughput or minimizing the delay, but these researches has ignored the timeliness of the information at the receiver. This paper proposes a UAV-assisted IoT fresh information collection system model, and studies the information collection process and information freshness in the system. In this system, the base station sends the UAV to fly to the sensor node and collect the data in the sensor node. In the process of data collection, the energy of the UAV must be kept in the surplus state. Once the energy of the UAV is lower than the energy threshold, the UAV immediately flies to the destination. The data collected from the sensor node is stored in the buffer and follows the proposed queuing policy which replace old packets with new packets. In this paper, the problem is modeled as a Markov Decision Process and the state space, action space and reward function of the problem are defined. The system average age of information is minimized by jointly optimizing the flight trajectory of UAV and the transmission scheduling sequence of sensors. In order to overcome the disaster of dimension, this paper proposes a node data collection algorithm based on Double Deep Q Learing(DDQN). A large number of simulation experiments show that the proposed DDQN algorithm can reduce the system average age of information effectively compared with other baseline algorithms.