Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in im...Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.展开更多
This paper focuses on the problem of multi-station multi-robot spot welding task assignment,and proposes a deep reinforcement learning(DRL)framework,which is made up of a public graph attention network and independent...This paper focuses on the problem of multi-station multi-robot spot welding task assignment,and proposes a deep reinforcement learning(DRL)framework,which is made up of a public graph attention network and independent policy networks.The graph of welding spots distribution is encoded using the graph attention network.Independent policy networks with attention mechanism as a decoder can handle the encoded graph and decide to assign robots to different tasks.The policy network is used to convert the large scale welding spots allocation problem to multiple small scale singlerobot welding path planning problems,and the path planning problem is quickly solved through existing methods.Then,the model is trained through reinforcement learning.In addition,the task balancing method is used to allocate tasks to multiple stations.The proposed algorithm is compared with classical algorithms,and the results show that the algorithm based on DRL can produce higher quality solutions.展开更多
The integration of technologies like artificial intelligence,6G,and vehicular ad-hoc networks holds great potential to meet the communication demands of the Internet of Vehicles and drive the advancement of vehicle ap...The integration of technologies like artificial intelligence,6G,and vehicular ad-hoc networks holds great potential to meet the communication demands of the Internet of Vehicles and drive the advancement of vehicle applications.However,these advancements also generate a surge in data processing requirements,necessitating the offloading of vehicular tasks to edge servers due to the limited computational capacity of vehicles.Despite recent advancements,the robustness and scalability of the existing approaches with respect to the number of vehicles and edge servers and their resources,as well as privacy,remain a concern.In this paper,a lightweight offloading strategy that leverages ubiquitous connectivity through the Space Air Ground Integrated Vehicular Network architecture while ensuring privacy preservation is proposed.The Internet of Vehicles(IoV)environment is first modeled as a graph,with vehicles and base stations as nodes,and their communication links as edges.Secondly,vehicular applications are offloaded to suitable servers based on latency using an attention-based heterogeneous graph neural network(HetGNN)algorithm.Subsequently,a differential privacy stochastic gradient descent trainingmechanism is employed for privacypreserving of vehicles and offloading inference.Finally,the simulation results demonstrated that the proposedHetGNN method shows good performance with 0.321 s of inference time,which is 42.68%,63.93%,30.22%,and 76.04% less than baseline methods such as Deep Deterministic Policy Gradient,Deep Q Learning,Deep Neural Network,and Genetic Algorithm,respectively.展开更多
Hardware/software（HW/SW） partitioning is one of the key processes in an embedded system.It is used to determine which system components are assigned to hardware and which are processed by software.In contrast with p...Hardware/software（HW/SW） partitioning is one of the key processes in an embedded system.It is used to determine which system components are assigned to hardware and which are processed by software.In contrast with previous research that focuses on developing efficient heuristic,we focus on the pre-process of the task graph before the HW/SW partitioning in this paper,that is,enumerating all the sub-graphs that meet the requirements.Experimental results showed that the original graph can be reduced to 67% in the worst-case scenario and 58% in the best-case scenario.In conclusion,the reduced task graph saved hardware area while improving partitioning speed and accuracy.展开更多
以旅游大数据为基础,考虑长时间范围内的滞后效应以及不同搜索强度指数(Search Intensity Index,SII)之间的多任务影响,提出一种基于大数据的多任务旅游信息分析(Multi-tasking Tourism Information Analysis Based on Big Data,MTIABD...以旅游大数据为基础,考虑长时间范围内的滞后效应以及不同搜索强度指数(Search Intensity Index,SII)之间的多任务影响,提出一种基于大数据的多任务旅游信息分析(Multi-tasking Tourism Information Analysis Based on Big Data,MTIABD)框架。使用融合信息重排序技术预测旅游需求,具体根据图引导结构模拟历史变量对未来变量的滞后影响。每个变量通过时间维度上的卷积神经网络(Convolutional Neural Network,CNN)进行独立编码,利用二分图动态建模滞后效应,通过图聚合进行挖掘,实现对旅游需求的精准预测。基于上述技术,构建旅游需求预测系统,旅游者能够根据需求检索不同景点的信息。在真实数据集上进行大量实验,结果表明所提出的MTIABD框架在一步和多步预测方面均优于现有方法。在平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)指标下,相较于基于实例的多变量时间序列图预测框架(Instance-wise Graph-rased Framework for Multivariate Time Series Forecasting,IGMTF),MTIABD在HK-2021数据集上的性能提高了16.75%,在MO-2021数据集上的性能提高了19.79%。展开更多
图对比学习因其可有效缓解数据稀疏问题被广泛应用在推荐系统中.然而,目前大多数基于图对比学习的推荐算法均采用单一视角进行学习,这极大地限制了模型的泛化能力,且图卷积网络本身存在的过度平滑问题也影响着模型的稳定性.基于此,提出...图对比学习因其可有效缓解数据稀疏问题被广泛应用在推荐系统中.然而,目前大多数基于图对比学习的推荐算法均采用单一视角进行学习,这极大地限制了模型的泛化能力,且图卷积网络本身存在的过度平滑问题也影响着模型的稳定性.基于此,提出一种融合层注意力机制的多视角图对比学习推荐方法.一方面,该方法提出2种不同视角下的3种对比学习,在视图级视角下,通过对原始图添加随机噪声构建扰动增强视图,利用奇异值分解(singular value decomposition)重组构建SVD增强视图,对这2个增强视图进行视图级对比学习;在节点视角下,利用节点间的语义信息分别进行候选节点和候选结构邻居对比学习,并将3种对比学习辅助任务和推荐任务进行多任务学习优化,以提高节点嵌入的质量,从而提升模型的泛化能力.另一方面,在图卷积网络学习用户和项目的节点嵌入时,采用层注意力机制的方式聚合最终的节点嵌入,提高模型的高阶连通性,以缓解过度平滑问题.在4个公开数据集LastFM,Gowalla,Ifashion,Yelp上与10个经典模型进行对比,结果表明该方法在Recall,Precision,NDCG这3个指标上分别平均提升3.12%,3.22%,4.06%,这说明所提方法是有效的.展开更多
基金supported by the Talent Fund of Beijing Jiaotong University(No.2023XKRC028)CCFLenovo Blue Ocean Research Fund and Beijing Natural Science Foundation under Grant(No.L221003).
文摘Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.
基金National Key Research and Development Program of China,Grant/Award Number:2021YFB1714700Postdoctoral Research Foundation of China,Grant/Award Number:2024M752364Postdoctoral Fellowship Program of CPSF,Grant/Award Number:GZB20240525。
文摘This paper focuses on the problem of multi-station multi-robot spot welding task assignment,and proposes a deep reinforcement learning(DRL)framework,which is made up of a public graph attention network and independent policy networks.The graph of welding spots distribution is encoded using the graph attention network.Independent policy networks with attention mechanism as a decoder can handle the encoded graph and decide to assign robots to different tasks.The policy network is used to convert the large scale welding spots allocation problem to multiple small scale singlerobot welding path planning problems,and the path planning problem is quickly solved through existing methods.Then,the model is trained through reinforcement learning.In addition,the task balancing method is used to allocate tasks to multiple stations.The proposed algorithm is compared with classical algorithms,and the results show that the algorithm based on DRL can produce higher quality solutions.
文摘The integration of technologies like artificial intelligence,6G,and vehicular ad-hoc networks holds great potential to meet the communication demands of the Internet of Vehicles and drive the advancement of vehicle applications.However,these advancements also generate a surge in data processing requirements,necessitating the offloading of vehicular tasks to edge servers due to the limited computational capacity of vehicles.Despite recent advancements,the robustness and scalability of the existing approaches with respect to the number of vehicles and edge servers and their resources,as well as privacy,remain a concern.In this paper,a lightweight offloading strategy that leverages ubiquitous connectivity through the Space Air Ground Integrated Vehicular Network architecture while ensuring privacy preservation is proposed.The Internet of Vehicles(IoV)environment is first modeled as a graph,with vehicles and base stations as nodes,and their communication links as edges.Secondly,vehicular applications are offloaded to suitable servers based on latency using an attention-based heterogeneous graph neural network(HetGNN)algorithm.Subsequently,a differential privacy stochastic gradient descent trainingmechanism is employed for privacypreserving of vehicles and offloading inference.Finally,the simulation results demonstrated that the proposedHetGNN method shows good performance with 0.321 s of inference time,which is 42.68%,63.93%,30.22%,and 76.04% less than baseline methods such as Deep Deterministic Policy Gradient,Deep Q Learning,Deep Neural Network,and Genetic Algorithm,respectively.
基金Supported by the National Natural Science Foundation of China (60970016,61173032)
文摘Hardware/software（HW/SW） partitioning is one of the key processes in an embedded system.It is used to determine which system components are assigned to hardware and which are processed by software.In contrast with previous research that focuses on developing efficient heuristic,we focus on the pre-process of the task graph before the HW/SW partitioning in this paper,that is,enumerating all the sub-graphs that meet the requirements.Experimental results showed that the original graph can be reduced to 67% in the worst-case scenario and 58% in the best-case scenario.In conclusion,the reduced task graph saved hardware area while improving partitioning speed and accuracy.
文摘以旅游大数据为基础,考虑长时间范围内的滞后效应以及不同搜索强度指数(Search Intensity Index,SII)之间的多任务影响,提出一种基于大数据的多任务旅游信息分析(Multi-tasking Tourism Information Analysis Based on Big Data,MTIABD)框架。使用融合信息重排序技术预测旅游需求,具体根据图引导结构模拟历史变量对未来变量的滞后影响。每个变量通过时间维度上的卷积神经网络(Convolutional Neural Network,CNN)进行独立编码,利用二分图动态建模滞后效应,通过图聚合进行挖掘,实现对旅游需求的精准预测。基于上述技术,构建旅游需求预测系统,旅游者能够根据需求检索不同景点的信息。在真实数据集上进行大量实验,结果表明所提出的MTIABD框架在一步和多步预测方面均优于现有方法。在平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)指标下,相较于基于实例的多变量时间序列图预测框架(Instance-wise Graph-rased Framework for Multivariate Time Series Forecasting,IGMTF),MTIABD在HK-2021数据集上的性能提高了16.75%,在MO-2021数据集上的性能提高了19.79%。
文摘图对比学习因其可有效缓解数据稀疏问题被广泛应用在推荐系统中.然而,目前大多数基于图对比学习的推荐算法均采用单一视角进行学习,这极大地限制了模型的泛化能力,且图卷积网络本身存在的过度平滑问题也影响着模型的稳定性.基于此,提出一种融合层注意力机制的多视角图对比学习推荐方法.一方面,该方法提出2种不同视角下的3种对比学习,在视图级视角下,通过对原始图添加随机噪声构建扰动增强视图,利用奇异值分解(singular value decomposition)重组构建SVD增强视图,对这2个增强视图进行视图级对比学习;在节点视角下,利用节点间的语义信息分别进行候选节点和候选结构邻居对比学习,并将3种对比学习辅助任务和推荐任务进行多任务学习优化,以提高节点嵌入的质量,从而提升模型的泛化能力.另一方面,在图卷积网络学习用户和项目的节点嵌入时,采用层注意力机制的方式聚合最终的节点嵌入,提高模型的高阶连通性,以缓解过度平滑问题.在4个公开数据集LastFM,Gowalla,Ifashion,Yelp上与10个经典模型进行对比,结果表明该方法在Recall,Precision,NDCG这3个指标上分别平均提升3.12%,3.22%,4.06%,这说明所提方法是有效的.
