Research On Maximum Network Lifetime Of UAV Emergency Communication Network

With science and technology promoting people's life and informatization promoting social development,the existing wired communication can no longer meet the needs of specific scenarios,especially in some public sectors including natural disaster rescue,environmental field monitoring,military exercises,or scenes of major communication accidents.At present,due to extremely limited resources and high cost,the common wireless satellite communication method can only be used in the command system,which is difficult to meet the communication needs of a large number of users on the scene of emergency.Due to the low cost of construction and use,strong mobility and small safety risk factor,UAVs are increasingly used in emergency communication systems.This paper studies the key technology of UAV-based wireless router self-organizing emergency communication network.Then aiming at the rapid replacement and flexible organization of the wireless router self-organizing work on the emergency scene,a kind of wireless emergency communication network architecture with UAV as the relay node for the emergency situation is built to meet the demand of emergency command and dispatching on site and try to restore the user communication.Furthermore,the life of the new architecture in the complex geographical environment of the emergency scene is deeply studied.The SARSA algorithm is introduced to discuss the movement mechanism of the UAV under the architecture.Deploying wireless routers on the ground and unmanned aerial vehicles(UAVs)in the air is believed to be a fast and efficient approach to providing the emergency communication service to disaster areas.The network lifetime is restricted to the lifetime of mesh networks of routers that are scattered across a complex disaster environment.We consider the problem of multi-UAVs relaying and moving with the goal of maximizing the network lifetime.UAVs must learn where to move in order to relay messages from the routers efficiently.However,under the dynamics of the router traffic,that is,the uncertainty of the environment,it is challenging for UAVs to find a movement mechanism that maximizes the network lifetime.By embracing the on-policy reinforcement learning algorithm SARSA,we are able to demonstrate a greedy movement policy.Specifically,we study the trajectory planning of multiple UAVs in a dense wireless router mesh networks(WMNs)on the ground.UAVs can learn the unknown environment by a little movement of UAVs in each step,in which communication connections between routers with UAVs are retained.A Q-table of movement actions and environment states is formed after multiple attempts of movements.Simulation results show the proposal effectiveness comparing with other methods.The following two aspects can fully summarize the main research contents and results of this paper:(1)the demand for emergency on-site emergency communications support are analyzed,and then a network architecture about UAV-based wireless router self-organizing emergency communication network is proposed.In addition,a drone-based wireless router self-organizing network architecture suitable for emergency field communication support is formed.(2)this paper analyzes related algorithms for reinforcement learning,proposes the SARSA-based UAV motion trajectory algorithm,so as to enhance the life of the emergency communication network on the emergency.Simulation results show that the SARSA algorithm can improve the life of the whole network and reduce the waste of resources in a more effective way compared with the static network.