知识图谱辅助的无人机群频谱资源优化算法

doi:10.19665/j.issn1001-2400.20240505

摘要/Abstract

摘要：

针对无人机群可用频谱资源紧缺及资源优化过程中面临的多目标优化难以求解、完整信道信息难以获取和实时性差等问题,提出了一种知识图谱辅助的无人机群频谱资源优化算法。首先构建一种基于多头注意力机制的关系感知图神经网络编码器,实现无人机群通信参数、性能参数和电磁环境信息的聚合,并根据节点的重要性为邻居信息分配不同的权重;然后构建一种改进型基于层注意力的InteractE模型,使用压缩-激励模块获取层注意力信息,从循环卷积结果中挖掘深层次交互信息,实现无人机群信道接入和发射功率预测。仿真结果表明,在公共数据集上,所提算法收敛速度快、链路预测性能好,并且具有较好的稳定性和鲁棒性;在无人机群频谱管控数据集上,所提算法可以在已知信道分布信息和部分环境信息的情况下,生成近似最优的无人机群频谱资源优化方案。

关键词: 无人机群, 资源分配, 知识图谱, 图神经网络

Abstract:

In response to the scarcity of available spectrum resources in UAV swarms and the difficulties in solving multi-objective optimization problems,as well as the challenges of obtaining complete channel information and poor real-time performance during the resource optimization process,a knowledge graph-assisted spectrum resource optimization algorithm for UAV swarms is proposed.Firstly,a relation-aware graph multi-head attention network(RGMAN) encoder is constructed to aggregate communication parameters,performance parameters,and electromagnetic environment information of the UAV swarm,and allocate different weights to neighbor information based on the importance of the nodes.Then,an improved layer-attention-based InteractE(SE-IE) model is developed to predict the channel access and transmit power for the UAVs,which utilizes a squeeze-and-excitation module to obtain layer attention information and extracts deep-level interactive information from the results of circular convolutions.The simulation results indicate that the proposed algorithm exhibits rapid convergence capability,excellent performance in link prediction,and notable stability and robustness on public datasets.Additionally,on the dataset for UAV swarm spectrum management,the proposed algorithm can generate an approximately optimal spectrum resource optimization scheme for UAV swarms,in the premise of channel distribution information and partial environmental information.

Key words: unmanned aerial vehicle swarm, resource allocation, knowledge graph, graph neural networks

中图分类号:

TN929.52

王雨来, 廖晓闽, 何海光, 叶国军. 知识图谱辅助的无人机群频谱资源优化算法[J]. 西安电子科技大学学报, 2024, 51(5): 58-70.

WANG Yulai, LIAO Xiaomin, HE Haiguang, YE Guojun. Knowledge graph assisted spectrum resource optimization algorithm for UAVs[J]. Journal of Xidian University, 2024, 51(5): 58-70.

图/表 11

图1

图2

图3

图4

表1

图5

表2

表3

图6

表4

图7

参考文献 29

[1]	ZHAO N, LU W, SHENG M, et al. UAV-Assisted Emergency Networks in Disasters[J]. IEEE Wireless Communications, 2019, 26(1):45-51. doi: 10.1109/MWC.2018.1800160
[2]	ZHANG S, ZHANG H, HE Q, et al. Joint Trajectory and Power Optimization for UAV Relay Networks[J]. IEEE Communications Letters, 2018, 22(1):161-164.
[3]	王莉, 魏青, 徐连明, 等. 面向通信-导航-感知一体化的应急无人机网络低能耗部署研究[J]. 通信学报, 2022, 43(7):1-20. doi: 10.11959/j.issn.1000-436x.2022138
	WANG Li, WEI Qing, XU Lianming, et al. Research on Low-Energy Deployment of Emergency Unmanned Aerial Vehicles Network Integrated with Communication,Navigation,and Perception[J]. Journal of Communications, 2022, 43(7):1-20.
[4]	陈新颖, 盛敏, 李博, 等. 面向6G的无人机通信综述[J]. 电子与信息学报, 2022, 44(3):781-789.
	CHEN Xinying, SHENG Min, LI Bo, et al. Overview of Drone Communication for 6G[J]. Journal of Electronics & Information Technology, 2022, 44(3):781-789.
[5]	吴义豪, 齐彦丽, 周一青, 等. 通感算协同的无人机群轨迹规划与功率分配[J]. 西安电子科技大学学报, 2023, 50(3):61-74.
	WU Yihao, QI Yanli, ZHOU Yiqing, et al. UAVs Trajectory Planning and Power Allocation Based on the Convergence of Communication,Sensing and Computing[J]. Journal of Xidian University, 2023, 50(3):61-74.
[6]	徐子蒙, 王博文, 云霄, 等. 灾后无人机不确定偏好序下稳定中继选择方法[J]. 西安电子科技大学学报, 2022, 49(6):32-41.
	XU Zimeng, WANG Bowen, YUN Xiao, et al. Stable Relay Selection Method Under an Uncertain Preference Oordinal for UAV in Post-Disaster[J]. Journal of Xidian University, 2022, 49(6):32-41.
[7]	LI Y, ZHANG H, LONG K, et al. Joint Resource Allocation and Trajectory Optimization with QoS in UAV-Based NOMA Wireless Networks[J]. IEEE Transactions on Wireless Communications, 2021, 20(10):6343-6355.
[8]	QI X, YUAN M, ZHANG Q, et al. Joint Power-Trajectory-Scheduling Optimization in a Mobile UAV-Enabled Network via Alternating Iteration[J]. China Communications, 2022, 19(1):136-152.
[9]	WU Q, ZENG Y, ZHANG R. Joint Trajectory and Communication Design for Multi-UAV Enabled Wireless Networks[J]. IEEE Transactions on Wireless Communications, 2018, 17(3):2109-2121.
[10]	YOU W, DONG C, WU Q, et al. Joint Task Scheduling, Resource Allocation,and UAV Trajectory under Clustering for FANETs[J]. China Communications, 2022, 19(1):104-118.
[11]	ZHOU L, DONG Y, HONG M, et al. Joint Channel Assignment and Power Allocation for Multi-UAVs Communication Systems[C]// 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).Piscataway:IEEE, 2020:1-5.
[12]	CHEN R, CHEN J, WANG H, et al. Joint Channel Access and Power Control Optimization in Large-Scale UAV Networks:A Hierarchical Mean Field Game Approach[J]. IEEE Transactions on Vehicular Technology, 2023, 72(2):1982-1996.
[13]	XU W, LEI H, SHANG J. Joint Topology Construction and Power Adjustment for UAV Networks:A Deep Reinforcement Learning Based Approach[J]. China Communications, 2021, 18(7):265-283.
[14]	LU Q, LI C, YANG J, et al. Radio Regulatory Knowledge Graph Framework and Its Application[C]// 2020 IEEE 3rd International Conference on Electronics and Communication Engineering (ICECE).Piscataway:IEEE, 2020:61-65.
[15]	孙佳琛, 王金龙, 丁国如, 等. 频谱知识图谱:面向未来频谱管理的智能引擎[J]. 通信学报, 2021, 42(5):1-12. doi: 10.11959/j.issn.1000-436x.2021084
	SUN Jiachen, WANG Jinlong, DING Guoru, et al. Spectrum Knowledge Graph:An Intelligent Engine for Future Spectrum Management[J]. Journal of Communications, 2021, 42(5):1-12.
[16]	HE S, OU Y, WANG L, et al. Representation Learning of Knowledge Graph for Wireless Communication Networks[C]// GLOBECOM 2022-2022 IEEE Global Communications Conference.Piscataway:IEEE, 2022:1338-1343.
[17]	JI S, PAN S, CAMBRIA E, et al. A Survey on Knowledge Graphs:Representation, Acquisition,and Applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2):494-514.
[18]	LIANG S, SHAO J, ZHANG D, et al. DRGI:Deep Relational Graph Infomax for Knowledge Graph Completion[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(3):2486-2499.
[19]	ZHAO Y, ZHOU H, ZHANG A, et al. Connecting Embeddings Based on Multiplex Relational Graph Attention Networks for Knowledge Graph Entity Typing[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(5):4608-4620.
[20]	FANG Q, ZHANG X, HU J, et al. Contrastive Multi-Modal Knowledge Graph Representation Learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(9):8983-8996.
[21]	BORDES A, USUNIER N, GARCIA-DURáN A, et al. Translating Embeddings for Modeling Multi-Relational Data[C]// 6th International Conference on Neural Information Processing Systems. San Diego: NIPS, 2013:2787-2795.
[22]	SONG D, ZHANG F, LU M, et al. DTransE:Distributed Translating Embedding for Knowledge Graph[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(10):2509-2523.
[23]	YANG B, YIH W, HE X, et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014)[J/OL].[2014-12-20]. https://arxiv.org/abs/1412.6575.
[24]	LI Z, PETEGROSSO R, SMITH S, et al. Scalable Label Propagation for Multi-Relational Learning on the Tensor Product of Graphs[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(12):5964-5978.
[25]	LIU X, TAN H, CHEN Q, et al. RAGAT:Relation Aware Graph Attention Network for Knowledge Ggraph Completion[J]. IEEE Access, 2021, 9:20840-20849.
[26]	VASHISHTH S, SANYAL S, NITIN V, et al. Composition-Based Multi-Relational Graph Convolutional Networks(2019)[J/OL].[2019-11-08]. https://arxiv.org/abs/1911.03082.
[27]	VASHISHTH S, SANYAL S, NITIN V. InteractE:Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020:3009-3016.
[28]	MAMAGHANI M T, HONG Y. Terahertz Meets Untrusted UAV-Relaying:Minimum Secrecy Energy Efficiency Maximization via Trajectory and Communication Co-Design[J]. IEEE Transactions on Vehicular Technology, 2022, 71(5):4991-5006.
[29]	MATAR A S, SHEN X. Joint Subchannel Allocation and Power Control in Licensed and Unlicensed Spectrum for Multi-Cell UAV-Cellular Network[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(11):3542-3554.

参数	取值
总迭代次数	300
批处理大小	128
初始学习率	0.01
初始嵌入维度	100
编码器输出嵌入维度	200
图神经网络隐藏神经元个数	200
图神经网络层数	1
多头注意力机制“头”数	2
整形矩阵维度	20×10
卷积核数量	200
卷积核大小	9

算法	FB15k-237					WN18RR
算法	MRR	MR	Hit@1	Hit@3	Hit@10	MRR	MR	Hit@1	Hit@3	Hit@10
RAGAT	0.353 7	227.26	0.263 71	0.388 94	0.533 10	0.312 22	3 584.6	0.214 26	0.384 33	0.476 55
KGC-SROA	0.354 7	227.55	0.264 85	0.390 28	0.532 52	0.316 40	3 526.6	0.217 93	0.388 96	0.480 54

参数	取值
无人机总数/个	100/150/200
信道数量/个	3
最大发射功率/W	3
最大初始能量/J	200
飞行高度/m	300
载波中心频率/GHz	2
载波带宽/MHz	10
服务区域面积/km²	10×10/15×10/20×10
莱斯分布归一化因子	1
瑞利分布归一化因子	20
LoS信道衰落/dB	1
NLoS信道衰落/dB	20
信噪比阈值/dB	1
背景噪声功率谱密度/(dBm·Hz^-1)	-149
定向天线天线半波束角度/(°)	60
直视角度阈值/(°)	15
总迭代次数	500
批处理大小	128
初始学习率	0.01
优化器动量	0.9
初始嵌入维度	100
编码器输出嵌入维度	200
图神经网络隐藏神经元个数	200
图神经网络层数	1
多头注意力机制“头”数	2
整形矩阵维度	20×10
卷积核数量	200
卷积核大小	9

算法	M=100	M=150	M=200
KGC-SROA	0.195	0.287	0.350
HMFGA	5 698.16	7 856.14	10 560.03
BSDBA	276.51	431.92	530.72
MCGSBA	386.67	568.15	754.61