Multi-unmanned aerial vehicle cluster dynamic task scheduling model based on adaptive network

Abstract

The invention provides an adaptive network architecture dynamic scheduling model (DSM-FNA) oriented to unmanned aerial vehicle cluster tasks for solving the problem of emergencies confronted in the unmanned aerial vehicle cluster task scheduling process due to failure nodes encountered in the current network architecture in the unmanned aerial vehicle task scheduling process and incapability of dynamically providing capability requirements in real time, and aims at solving the problem of the emergencies confronted in the unmanned aerial vehicle cluster task scheduling process. The model is organized and calculated by referring to the'mosaic battle 'adaptation thought of DARPA, applying a super network theoretical method and combining the management theory of a flexible network and an elastic network, capability values are weighted and layered by adopting a linear transformation function according to capability requirements required by tasks, then an adaptive network architecture dynamic scheduling algorithm (FDSA) is provided, a substitute strategy is designed for a failure point, dynamic self-adaption of the capability and the task is effectively realized, and finally, through experimental comparative analysis with a classical Max-Min algorithm, it is verified that the FDSA algorithm can quickly make dynamic adjustment for quick response in comparison with the classical scheduling algorithm when an unmanned aerial vehicle cluster is faced with an emergency.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a multi-unmanned aerial vehicle cluster dynamic task scheduling model based on an adaptive network. Background technique [0002] The rapid development of economic information globalization, the deepening of the application concept of unmanned and intelligent combat, the rapid progress of AI / ML technology, the application of unmanned platforms in various fields of land, sea and air, and the adaptive mission structure of UAV clusters The research has become a research hotspot, but most of the existing research ignores the failure of a certain node or a certain subgroup during the mission execution process. , lack of detail and authenticity, how to consider the emergency and autonomous response to emergencies in the process of mission execution is the difficulty of research on UAV swarm adaptive mission architecture. [0003] Keus's Netforce reference model, her m...

AI Technical Summary

Problems solved by technology

[0009] However, most of the existing research does not consider the adaptability of the cluster architecture. When the task is executed, the assigned task of the UAV is known. During the execution of the task, the real-time changes of the situation and environment cannot be determined It is foreseeable that the task of a certain drone or a certain subgroup cannot be executed, and the nodes or subnetworks in the cluster architecture fail. How the unmanned cluster architecture can dynamically adapt to changes in the environment will be a big problem.

Images