Edge computing based method and system for optimizing target tracking power consumption of unmanned aerial vehicle

Abstract

The invention discloses an edge computing based method and system for optimizing target tracking power consumption of an unmanned aerial vehicle. The method comprises the following steps: S1, settinga video processing mode in an unmanned aerial vehicle tracking process; and S2, computing task allocation: selecting proper transmitting power and service nodes for the unmanned aerial vehicle by considering the adjustment of the transmitting power of the unmanned aerial vehicle and a selection mechanism of the edge nodes at the same time, and minimizing the total overhead. Compared with a generalmethod of using the fixed maximum unmanned aerial vehicle transmitting power to perform data transmission, the algorithm provided by the invention considers the adjustment of the unmanned aerial vehicle transmitting power and the selection scheme of the edge nodes at the same time, so as to minimize the trade-off value between the energy consumption cost and the time cost, and the communication energy consumption of the unmanned aerial vehicle is reduced on the premise of ensuring normal tracking.

Description

technical field [0001] The invention belongs to the field of UAV target tracking, in particular to a method and system for optimizing power consumption of UAV target tracking based on edge computing. Background technique [0002] As a new computing model, edge computing pushes computing resources to the edge of the Internet close to end users to meet the growing demand for high computing power and low latency for applications such as the Internet of Things (IoT). Edge computing The model decomposes computing tasks and migrates them to edge nodes for processing, so as to reduce the computing load of cloud computing data centers and reduce transmission delays, thereby achieving the purpose of reducing energy consumption and improving service time of mobile devices. [0003] Unmanned Aerial Vehicle (UAV) is an important class of robots. With the development of Internet of Things technology and the continuous improvement of UAV performance, it has been widely used in various asp...

AI Technical Summary

Problems solved by technology

Moving target tracking is a complex and challenging problem. During the tracking process, UAVs continuously shoot videos to track suspicious targets. Due to the limited computing resources of UAVs, it is impossible to quickly process the continuously generated video streams. Usually, it is considered to The video processing task is offloaded from the UAV to the edge node / server collaborative processing; however, the process of UAV flight propulsion and the process of offloading tasks are accompanied by energy consumption. According to the UAV product data released by DJI official website, most Under ideal conditions, the maximum flight time of drones is about 31 minutes, and the working time is very limited. Because of the limitation of its battery capacity, the energy consumption of drones has always been a research hotspot.

Images