Research on the Deployment Strategy of UAV Location for Forest Fire Monitoring
The deployment of unmanned aerial vehicles(UAVs)in the complex environment of forest fires faces problems such as high energy consumption and low offloading efficiency.Therefore,an air to ground assisted edge computing framework is proposed.In this framework,UAVs collect data and provide edge computing services at the fire scene,while the command center provides edge computing services with more computing power.In order to improve the efficiency of the computing service,first,the impact of fire severity and distance on UAV deployment is considered comprehensively,and the fire spread speed and distance are used to determine the area where UAVs are needed to provide computing services;then,the UAV deployment problem is modeled as a system cost problem that minimizes the task computation latency and the energy consumption of the UAVs;and finally,an autonomous deployment strategy based on multi-agent reinforcement learning for minimal system cost was designed to obtain the optimal position of the UAV in the specified mission area.Simulation results demonstrate that the proposed scheme can effectively reduce the total cost of UAV deployment.
NETL
NSTL
万方数据
