Graph neural network-based scheduling for multi-UAV-enabled communications in D2D networks

In this paper,we jointly design the power control and position dispatch for Multi-Unmanned Aerial Vehicle(UAV)-enabled communication in Device-to-Device(D2D)networks.Our objective is to maximize the total transmission rate of Downlink Users(DUs).Meanwhile,the Quality of Service(QoS)of all D2D users must be satisfied.We comprehensively considered the interference among D2D communications and downlink transmissions.The original problem is strongly non-convex,which requires high computational complexity for traditional optimization methods.And to make matters worse,the results are not necessarily globally optimal.In this paper,we propose a novel Graph Neural Networks(GNN)based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.Particularly,we first construct a GNN-based model for the proposed network,in which the transmission links and interference links are formulated as vertexes and edges,respectively.Then,by taking the channel state information and the coordinates of ground users as the inputs,as well as the location of UAVs and the transmission power of all transmitters as outputs,we obtain the mapping from inputs to outputs through training the parameters of GNN.Simulation results verified that the way to maximize the total transmission rate of DUs can be extracted effectively via the training on samples.Moreover,it also shows that the performance of proposed GNN-based method is better than that of traditional means.

Efficient Deployment of Multiple UAVs for IoT Communication in Dynamic Environment

The application of unmanned aerial vehicle(UAV)-mounted base stations is emerging as an effective solution to provide wireless communication service for a target region containing some smart objects(SOs)in internet of things(IoT).This paper investigates the efficient deployment problem of multiple UAVs for IoT communication in dynamic environment.We first define a measurement of communication performance of UAVto-SO in the target region which is regarded as the optimization objective.The state of one SO is active when it needs to transmit or receive the data;otherwise,silent.The switch of two different states is implemented with a certain probability that results in a dynamic communication environment.In the dynamic environment,the active states of SOs cannot be known by UAVs in advance and only neighbouring UAVs can communicate with each other.To overcome these challenges in the deployment,we leverage a game-theoretic learning approach to solve the position-selected problem.This problem is modeled a stochastic game,which is proven that it is an exact potential game and exists the best Nash equilibria(NE).Furthermore,a distributed position optimization algorithm is proposed,which can converge to a pure-strategy NE.Numerical results demonstrate the excellent performance of our proposed algorithm.

Debris flow susceptibility mapping in mountainous area based on multi-source data fusion and CNN model-taking Nujiang Prefecture,China as an example

Efforts to evaluate the susceptibility of debris flows in large areas,especially in mountainous regions,are often hampered by the alpine and canyon terrain.This paper proposes a convolution neural network(CNN)model named dense residual shuffle net(DRSNet).It is successfully applied to Nujiang Prefecture in Yunnan Province of China,a typical alpine area with frequent debris flows.DRSNet uses digital elevation model,remote sensing,lithology,soil type and precipitation data as input.First,dense connection and residual structure were used to extract the shallow features of various data.Next,channel shuffle,fuse block and fully connection were applied to strengthen the correlation between different shallow features and give inner danger scores.Finally,precipitation as the activation factor was introduced giving the valleys susceptibility.To verify the feasibility of DRSNet,comparative tests were conducted on 7 CNN models and 3 other machine learning(ML)methods.Experimental results show that DRSNet can achieve 78.6%accuracy in debris flow valley classification,which is at least 7.4%higher than common CNN models and 15.2%higher than other ML methods.This article provides new ideas for debris flow susceptibility evaluation.

New hydrous phases in the Al_(2)O_(3)-SiO_(2)-H_(2)O system under the mantle transition zone conditions

Hydrous minerals in the subducting slabs are potential water carriers into the deep mantle,and thus the synthesis of new hydrous phases is significant in our understanding of water circulation throughout the Earth’s interior.In this study,we report the two new hydrous phases,Al_(2)SiO_(6)H_(2)and Al_(5.5)Si_(4)O_(18)H_(3.5)(hereafter referred to simply as phases Psi and Phi,respectively),which are synthesized in the Al_(2)O_(3)-SiO_(2)-H_(2)O system at 15.5 GPa,1400℃and 17.5 GPa,1600℃ by using Sakura2500-ton multi-anvil apparatus.The luminescence spectra of Cr3+show the phase Psi has characteristic peaks at 687,693 and705 nm,while phase Phi has characteristic peaks at 691,696 and 708 nm.Single-crystal X-ray diffraction (SCXRD) refinements yield a monoclinic structure of both phases (space group P2_(1)) with ideal chemical formulae of Al_(2)SiO6H2and Al5.5Si4O18H3.5respectively.The determined lattice parameters for phase Psi are a=9.4168±0.0016Å,b=4.3441±0.0007Å,c=9.4360±0.002Åand β=119.726±0.005°at ambient pressure and 300 K,while the phase Phi has a=7.2549±0.0018Å,b=4.3144±0.001Å,c=8.0520±0.002Å,and β=101.740±0.009°at ambient pressure and 250 K.Electron microprobe analyses (EPMA) show the chemical compositions of phases Psi and Phi to be Al_(1.99)Si_(0.85)O_(6)H_(2.62)and Al_(5.58)Si_(2.81)O_(18)H_(8.03),respectively,which slightly deviate from the ideal formulae inferred from SCXRD measurements.This may result from the disorder or substitution of Al and Si by H in the crystal structures under our synthesis conditions.Our study suggests that phases Psi and Phi are the two potential water carriers at the upper part of the mantle transitions zone,providing new insights into how deep water is stored in this region.

Optimal transmit beamforming for near-field integrated sensing and wireless power transfer systems

The integrated sensing and wireless power transfer(ISWPT)technology,in which the radar sensing and wireless power transfer functionalities are implemented using the same hardware platform,has been recently proposed.In this paper,we consider a near-field ISWPT system where one hybrid transmitter deploys extremely large-scale antenna arrays,and multiple energy receivers are located in the near-field region of the transmitter.Under such a new scenario,we study radar sensing and wireless power transfer performance trade-offs by optimizing the transmit beamforming vectors.In particular,we consider the transmit beampattern matching and max-min beampattern gain design metrics.For each radar performance metric,we aim to achieve the best performance of radar sensing,while guaranteeing the requirement of wireless power transfer.The corresponding beamforming design problems are non-convex,and the semi-definite relaxation(SDR)approach is applied to solve them globally optimally.Finally,numerical results verify the effectiveness of our proposed solutions.