High-altitude base station cluster auxiliary edge calculation method for emergency communication

Abstract

The invention relates to a high-altitude base station cluster auxiliary edge calculation method for emergency communication, which adopts an AK-means method for accurately acquiring a K value to solve the number and position deployment of unmanned aerial vehicles, and comprehensively covers a moving target area; in order to prevent insufficient power supply of the unmanned aerial vehicles or other accidental weather conditions, a certain number of high-altitude balloon terminals equipped with MEC servers are deployed in the air to assist an unmanned aerial vehicle in providing communication and computing services for ground mobile user equipment, and a digital twin network is introduced to feed back information such as geographic positions and computing resources of the mobile user equipment, the unmanned aerial vehicle and the high-altitude balloon terminals in real time. An unloading decision of the mobile user equipment is solved by applying a DDQN algorithm in deep reinforcement learning, and a computing resource allocation strategy of the mobile user equipment, the unmanned aerial vehicle and the high-altitude balloon terminal is obtained by utilizing an RO algorithm, so that the energy consumption of the whole system is effectively reduced, and the service experience of the mobile user equipment is improved.

Description

technical field [0001] The invention relates to a high-altitude base station cluster-assisted edge computing method used in emergency communications, and belongs to the technical field of UAV-assisted edge computing. Background technique [0002] In recent years, extreme weather events have occurred frequently. In the face of unknown weather conditions, it is very important to build a communication platform in advance, which is not only the prevention of emergencies, but also the protection of human life; There are more and more studies on the construction of medium and high-altitude base station platforms. Due to the characteristics of high mobility, low cost and easy deployment of UAVs, UAV-assisted edge computing technology has developed rapidly and has been widely accepted by academia and industry. focus on. On the one hand, the commonly used methods for the deployment of UAVs include the DBSCAN algorithm and the K-means algorithm. Among them, the DBSCAN algorithm does ...

AI Technical Summary

Problems solved by technology

On the one hand, the commonly used methods for the deployment of UAVs include the DBSCAN algorithm and the K-means algorithm. Among them, the DBSCAN algorithm does not need to specify the number of clusters in advance, but needs to jointly adjust the distance threshold and the neighborhood sample number threshold. Generally, the determination of these two parameters needs to rely on empirical values. If the initial selection is not good, it will cause greater computational complexity.

When the traditional K-means algorithm solves the UAV deployment problem, the number of clusters K is the given number of drones, K The choice of value will also have a certain impact on the final clustering effect

On the other hand, most of the existing research on UAV-assisted edge computing assumes that UAVs can fly stably or hover at high altitudes to provide smooth communication and computing services for user equipment, and do not consider the extreme weather conditions. In the process, once the UAV cannot provide stable and continuous services for the user equipment, how to further ensure the communication experience of the user equipment

Images