Multiple DAGs scheduling strategy is a critical factor affecting resource utilization and operating cost in the cloud computing. To solve the problem that multiple DAG scheduling cannot meet the resource utilization a...Multiple DAGs scheduling strategy is a critical factor affecting resource utilization and operating cost in the cloud computing. To solve the problem that multiple DAG scheduling cannot meet the resource utilization and reliability when multiple DAGs arrive at different time, the multiple DAGs scheduling problem can be transformed into a single DAG scheduling problem with limited resource available time period through multiple DAGs scheduling model based on backfill. On the basis of discussing the available time period description of resources and the sorting of task scheduling when the available time period is limited, the multiple DAGs scheduling strategy is proposed based on backfill. The experimental analysis shows that this strategy can effectively shorten the makespan and improve the resources utilization when multiple DAGs arrive at different time.展开更多
随着用户对延迟敏感的应用程序的需求不断增长,边缘计算环境中的高效任务调度对于及时满足用户需求变得至关重要。边缘计算环境下有向无环图(directed acyclic graph,DAG)调度的静态任务调度方法,旨在研究最小化任务完成时间并及时响应...随着用户对延迟敏感的应用程序的需求不断增长,边缘计算环境中的高效任务调度对于及时满足用户需求变得至关重要。边缘计算环境下有向无环图(directed acyclic graph,DAG)调度的静态任务调度方法,旨在研究最小化任务完成时间并及时响应用户需求。为了模拟边缘计算场景,本文采用Kubernetes(K8s)集群,通过构造基于深度优先搜索的异构最早完成时间(heterogeneous earliest finish time based on depth-first search,D-HEFT)调度算法优化了高效率任务调度。该算法使用深度优先搜索算法来优化异构最早完成时间(heterogeneous earliest finish time,HEFT)算法。实验结果表明,D-HEFT算法在任务调度效率和任务完成时间方面优于HEFT、具有复制的异构最早完成时间(heterogeneous earliest finish time with duplication,HEFT_D)、HEFT_U和处理器上的关键路径(critical path on the processor,CPOP)四种任务调度方法。展开更多
近日,山东大学网络空间安全学院魏普文教授团队在区块链领域的研究成果“Security-Performance Tradeoff in DAGBased Proof-of-Work Blockchain Protocols”被国际安全会议Network and Distributed System Security Symposium 2024(ND...近日,山东大学网络空间安全学院魏普文教授团队在区块链领域的研究成果“Security-Performance Tradeoff in DAGBased Proof-of-Work Blockchain Protocols”被国际安全会议Network and Distributed System Security Symposium 2024(NDSS)录用。山东大学是该论文的第一作者和通讯作者单位。展开更多
Peer-to-peer(P2P)spectrum sharing and energy trading are promising solutions to locally satisfy spectrum and energy demands in power Internet of Things(IoT).However,implementation of largescale P2P spectrum sharing an...Peer-to-peer(P2P)spectrum sharing and energy trading are promising solutions to locally satisfy spectrum and energy demands in power Internet of Things(IoT).However,implementation of largescale P2P spectrum sharing and energy trading confronts security and privacy challenges.In this paper,we exploit consortium blockchain and Directed Acyclic Graph(DAG)to propose a new secure and distributed spectrum sharing and energy trading framework in power IoT,named spectrum-energy chain,where a set of local aggregators(LAGs)cooperatively confirm the identity of the power devices by utilizing consortium blockchain,so as to form a main chain.Then,the local power devices verify spectrum and energy micro-transactions simultaneously but asynchronously to form local spectrum tangle and local energy tangle,respectively.Moreover,an iterative double auction based micro transactions scheme is designed to solve the spectrum and energy pricing and the amount of shared spectrum and energy among power devices.Security analysis and numerical results illustrate that the developed spectrum-energy chain and the designed iterative double auction based microtransactions scheme are secure and efficient for spectrum sharing and energy trading in power IoT.展开更多
Background:The purpose of the study was to investigatethe active ingredients and potential biochemicalmechanisms of Simiao Wan(SMW)in obesity-associated insulin resistance.Methods:An integrated network pharmacology me...Background:The purpose of the study was to investigatethe active ingredients and potential biochemicalmechanisms of Simiao Wan(SMW)in obesity-associated insulin resistance.Methods:An integrated network pharmacology method to screen the active compoundsand candidate targets,construct the protein-protein-interaction network,and ingredients-targets-pathways network was constructed for topological analysis to identify core targets and main ingredients.To find the possible signaling pathways,enrichment analysis was performed.Further,a model of insulin resistance in HL-7702 cells was established to verify the impact of SMW and the regulatory processes.Results:An overall of 63 active components and 151 candidate targets were obtained,in which flavonoids were the main ingredients.Enrichment analysis indicated that the PI3K-Akt signaling pathway was the potential pathway regulated by SMW in obesity-associated insulin resistance treatment.The result showed that SMW could significantly ameliorate insulin sensitivity,increase glucose synthesis and glucose utilization and reduce intracellular lipids accumulation in hepatocytes.Also,SMW inhibited diacylglycerols accumulation-induced PKCεactivity and decreased its translocation to the membrane.Conclusion:SMW ameliorated obesity-associated insulin resistance through PKCε/IRS-1/PI3K/Akt signaling axis in hepatocytes,providing a new strategy for metabolic disease treatment.展开更多
文摘Multiple DAGs scheduling strategy is a critical factor affecting resource utilization and operating cost in the cloud computing. To solve the problem that multiple DAG scheduling cannot meet the resource utilization and reliability when multiple DAGs arrive at different time, the multiple DAGs scheduling problem can be transformed into a single DAG scheduling problem with limited resource available time period through multiple DAGs scheduling model based on backfill. On the basis of discussing the available time period description of resources and the sorting of task scheduling when the available time period is limited, the multiple DAGs scheduling strategy is proposed based on backfill. The experimental analysis shows that this strategy can effectively shorten the makespan and improve the resources utilization when multiple DAGs arrive at different time.
文摘随着用户对延迟敏感的应用程序的需求不断增长,边缘计算环境中的高效任务调度对于及时满足用户需求变得至关重要。边缘计算环境下有向无环图(directed acyclic graph,DAG)调度的静态任务调度方法,旨在研究最小化任务完成时间并及时响应用户需求。为了模拟边缘计算场景,本文采用Kubernetes(K8s)集群,通过构造基于深度优先搜索的异构最早完成时间(heterogeneous earliest finish time based on depth-first search,D-HEFT)调度算法优化了高效率任务调度。该算法使用深度优先搜索算法来优化异构最早完成时间(heterogeneous earliest finish time,HEFT)算法。实验结果表明,D-HEFT算法在任务调度效率和任务完成时间方面优于HEFT、具有复制的异构最早完成时间(heterogeneous earliest finish time with duplication,HEFT_D)、HEFT_U和处理器上的关键路径(critical path on the processor,CPOP)四种任务调度方法。
文摘近日,山东大学网络空间安全学院魏普文教授团队在区块链领域的研究成果“Security-Performance Tradeoff in DAGBased Proof-of-Work Blockchain Protocols”被国际安全会议Network and Distributed System Security Symposium 2024(NDSS)录用。山东大学是该论文的第一作者和通讯作者单位。
文摘随着机器人操作系统(robot operating system, ROS)的日益普及,系统也变得更加复杂,这类系统的计算平台正逐渐转变为多核心平台.在ROS中,任务执行的顺序取决于底层任务调度策略和分配给任务的优先级,而最大限度地缩短所有任务的执行时间是并行系统任务调度的一个重要目标.受强化学习在解决各种组合优化问题的最新研究成果的启发,在考虑ROS2多线程执行器的调度机制和执行约束的前提下,提出了一种基于强化学习的任务优先级分配方法,该方法提取了基于有向无环图形式表示的任务集的时间和结构特征,通过策略梯度和蒙特卡洛树搜索(Monte Carlo tree search, MCTS)方法有效地学习ROS2调度策略并给出合理的优先级设置方案,最终达到最小化并行任务的最大完工时间的目的.通过模拟平台环境下随机生成的任务图以评估所提方法,结果表明所提方法明显优于基准方法.作为一种离线分析方法,所提方法可以很容易地扩展到复杂的ROS中,在可接受的时间内找到接近最优的解决方案.
基金supported by the National Key R&D Program of China(2020YFB1807801,2020YFB1807800)in part by Project Supported by Engineering Research Center of Mobile Communications,Ministry of Education(cqupt-mct-202003)+2 种基金in part by Key Lab of Information Network Security,Ministry of Public Security under Grant C19603in part by National Natural Science Foundation of China(Grant No.61901067 and 61901013)in part by Chongqing Municipal Natural Science Foundation(Grant No.cstc2020jcyj-msxmX0339).
文摘Peer-to-peer(P2P)spectrum sharing and energy trading are promising solutions to locally satisfy spectrum and energy demands in power Internet of Things(IoT).However,implementation of largescale P2P spectrum sharing and energy trading confronts security and privacy challenges.In this paper,we exploit consortium blockchain and Directed Acyclic Graph(DAG)to propose a new secure and distributed spectrum sharing and energy trading framework in power IoT,named spectrum-energy chain,where a set of local aggregators(LAGs)cooperatively confirm the identity of the power devices by utilizing consortium blockchain,so as to form a main chain.Then,the local power devices verify spectrum and energy micro-transactions simultaneously but asynchronously to form local spectrum tangle and local energy tangle,respectively.Moreover,an iterative double auction based micro transactions scheme is designed to solve the spectrum and energy pricing and the amount of shared spectrum and energy among power devices.Security analysis and numerical results illustrate that the developed spectrum-energy chain and the designed iterative double auction based microtransactions scheme are secure and efficient for spectrum sharing and energy trading in power IoT.
基金supported by the National Natural Science Foundation of China(81903871)Natural Science Foundation of Jiangsu Province(BK20190565)+1 种基金Fundamental Research Funds for the Central Universities(2632021ZD16)Zhenjiang City 2022 Science and Technology Innovation Fund(SH2022084).
文摘Background:The purpose of the study was to investigatethe active ingredients and potential biochemicalmechanisms of Simiao Wan(SMW)in obesity-associated insulin resistance.Methods:An integrated network pharmacology method to screen the active compoundsand candidate targets,construct the protein-protein-interaction network,and ingredients-targets-pathways network was constructed for topological analysis to identify core targets and main ingredients.To find the possible signaling pathways,enrichment analysis was performed.Further,a model of insulin resistance in HL-7702 cells was established to verify the impact of SMW and the regulatory processes.Results:An overall of 63 active components and 151 candidate targets were obtained,in which flavonoids were the main ingredients.Enrichment analysis indicated that the PI3K-Akt signaling pathway was the potential pathway regulated by SMW in obesity-associated insulin resistance treatment.The result showed that SMW could significantly ameliorate insulin sensitivity,increase glucose synthesis and glucose utilization and reduce intracellular lipids accumulation in hepatocytes.Also,SMW inhibited diacylglycerols accumulation-induced PKCεactivity and decreased its translocation to the membrane.Conclusion:SMW ameliorated obesity-associated insulin resistance through PKCε/IRS-1/PI3K/Akt signaling axis in hepatocytes,providing a new strategy for metabolic disease treatment.
