This paper reviews task scheduling frameworks,methods,and evaluation metrics of central processing unit-graphics processing unit(CPU-GPU)heterogeneous clusters.Task scheduling of CPU-GPU heterogeneous clusters can be ...This paper reviews task scheduling frameworks,methods,and evaluation metrics of central processing unit-graphics processing unit(CPU-GPU)heterogeneous clusters.Task scheduling of CPU-GPU heterogeneous clusters can be carried out on the system level,nodelevel,and device level.Most task-scheduling technologies are heuristic based on the experts’experience,while some technologies are based on statistic methods using machine learning,deep learning,or reinforcement learning.Many metrics have been adopted to evaluate and compare different task scheduling technologies that try to optimize different goals of task scheduling.Although statistic task scheduling has reached fewer research achievements than heuristic task scheduling,the statistic task scheduling still has significant research potential.展开更多
The energy Internet operation platform provides market entities such as energy users,energy enterprises,suppliers,and governments with the ability to interact,transact,and manage various operations.Owing to the large ...The energy Internet operation platform provides market entities such as energy users,energy enterprises,suppliers,and governments with the ability to interact,transact,and manage various operations.Owing to the large number of platform users,complex businesses,and large amounts of data-mining tasks,it is necessary to solve the problems afflicting platform task scheduling and the provision of simultaneous access to a large number of users.This study examines the two core technologies of platform task scheduling and multiuser concurrent processing,proposing a distributed task-scheduling method and a technical implementation scheme based on the particle swarm optimization algorithm,and presents a systematic solution in concurrent processing for massive user numbers.Based on the results of this study,the energy internet operation platform can effectively deal with the concurrent access of tens of millions of users and complex task-scheduling problems.展开更多
Many Task Computing(MTC)is a new class of computing paradigm in which the aggregate number of tasks,quantity of computing,and volumes of data may be extremely large.With the advent of Cloud computing and big data era,...Many Task Computing(MTC)is a new class of computing paradigm in which the aggregate number of tasks,quantity of computing,and volumes of data may be extremely large.With the advent of Cloud computing and big data era,scheduling and executing large-scale computing tasks efficiently and allocating resources to tasks reasonably are becoming a quite challenging problem.To improve both task execution and resource utilization efficiency,we present a task scheduling algorithm with resource attribute selection,which can select the optimal node to execute a task according to its resource requirements and the fitness between the resource node and the task.Experiment results show that there is significant improvement in execution throughput and resource utilization compared with the other three algorithms and four scheduling frameworks.In the scheduling algorithm comparison,the throughput is 77%higher than Min-Min algorithm and the resource utilization can reach 91%.In the scheduling framework comparison,the throughput(with work-stealing)is at least 30%higher than the other frameworks and the resource utilization reaches 94%.The scheduling algorithm can make a good model for practical MTC applications.展开更多
An optimal algorithmic approach to task scheduling for, triplet based architecture（TriBA）, is proposed in this paper. TriBA is considered to be a high performance, distributed parallel computing architecture. TriBA ...An optimal algorithmic approach to task scheduling for, triplet based architecture（TriBA）, is proposed in this paper. TriBA is considered to be a high performance, distributed parallel computing architecture. TriBA consists of a 2D grid of small, programmable processing units, each physically connected to its three neighbors. In parallel or distributed environment an efficient assignment of tasks to the processing elements is imperative to achieve fast job turnaround time. Moreover, the sojourn time experienced by each individual job should be minimized. The arriving jobs are comprised of parallel applications, each consisting of multiple-independent tasks that must be instantaneously assigned to processor queues, as they arrive. The processors independently and concurrently service these tasks. The key scheduling issues is, when some queue backlogs are small, an incoming job should first spread its tasks to those lightly loaded queues in order to take advantage of the parallel processing gain. Our algorithmic approach achieves optimality in task scheduling by assigning consecutive tasks to a triplet of processors exploiting locality in tasks. The experimental results show that tasks allocation to triplets of processing elements is efficient and optimal. Comparison to well accepted interconnection strategy, 2D mesh, is shown to prove the effectiveness of our algorithmic approach for TriBA. Finally we conclude that TriBA can be an efficient interconnection strategy for computations intensive applications, if tasks assignment is carried out optimally using algorithmic approach.展开更多
Task scheduling in cloud computing environments is a multi-objective optimization problem, which is NP hard. It is also a challenging problem to find an appropriate trade-off among resource utilization, energy consump...Task scheduling in cloud computing environments is a multi-objective optimization problem, which is NP hard. It is also a challenging problem to find an appropriate trade-off among resource utilization, energy consumption and Quality of Service(QoS) requirements under the changing environment and diverse tasks. Considering both processing time and transmission time, a PSO-based Adaptive Multi-objective Task Scheduling(AMTS) Strategy is proposed in this paper. First, the task scheduling problem is formulated. Then, a task scheduling policy is advanced to get the optimal resource utilization, task completion time, average cost and average energy consumption. In order to maintain the particle diversity, the adaptive acceleration coefficient is adopted. Experimental results show that the improved PSO algorithm can obtain quasi-optimal solutions for the cloud task scheduling problem.展开更多
Collaborative cross-edge analytics is a new computing paradigm in which Internetof Things (IoT) data analytics is performed across multiple geographically dispersededge clouds. Existing work on collaborative cross-edg...Collaborative cross-edge analytics is a new computing paradigm in which Internetof Things (IoT) data analytics is performed across multiple geographically dispersededge clouds. Existing work on collaborative cross-edge analytics mostly focuses on reducingeither analytics response time or wide-area network (WAN) traffic volume. In thiswork, we empirically demonstrate that reducing either analytics response time or networktraffic volume does not necessarily minimize the WAN traffic cost, due to the price heterogeneityof WAN links. To explicitly leverage the price heterogeneity for WAN cost minimization,we propose to schedule analytic tasks based on both price and bandwidth heterogeneities.Unfortunately, the problem of WAN cost minimization underperformance constraintis shown non-deterministic polynomial (NP)-hard and thus computationally intractablefor large inputs. To address this challenge, we propose price- and performanceawaregeo-distributed analytics (PPGA) , an efficient task scheduling heuristic that improvesthe cost-efficiency of IoT data analytic jobs across edge datacenters. We implementPPGA based on Apache Spark and conduct extensive experiments on Amazon EC2to verify the efficacy of PPGA.展开更多
Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power sta...Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power stations).To solve the problem,we propose an energy harvesting based task scheduling and resource management framework to provide robust and low-cost edge computing services for smart grid.First,we formulate an energy consumption minimization problem with regard to task offloading,time switching,and resource allocation for mobile devices,which can be decoupled and transformed into a typical knapsack problem.Then,solutions are derived by two different algorithms.Furthermore,we deploy renewable energy and energy storage units at edge servers to tackle intermittency and instability problems.Finally,we design an energy management algorithm based on sampling average approximation for edge computing servers to derive the optimal charging/discharging strategies,number of energy storage units,and renewable energy utilization.The simulation results show the efficiency and superiority of our proposed framework.展开更多
By combining fault-tolerance with power management, this paper developed a new method for aperiodic task set for the problem of task scheduling and voltage allocation in embedded real-time systems. The scbedulability ...By combining fault-tolerance with power management, this paper developed a new method for aperiodic task set for the problem of task scheduling and voltage allocation in embedded real-time systems. The scbedulability of the system was analyzed through checkpointing and the energy saving was considered via dynamic voltage and frequency scaling. Simulation results showed that the proposed algorithm had better performance compared with the existing voltage allocation techniques. The proposed technique saves 51.5% energy over FT-Only and 19.9% over FT ＋ EC on average. Therefore, the proposed method was more appropriate for aperiodic tasks in embedded real-time systems.展开更多
基金supported by ZTE‑University‑Institute Fund Project under Grant No.IA20230629009.
文摘This paper reviews task scheduling frameworks,methods,and evaluation metrics of central processing unit-graphics processing unit(CPU-GPU)heterogeneous clusters.Task scheduling of CPU-GPU heterogeneous clusters can be carried out on the system level,nodelevel,and device level.Most task-scheduling technologies are heuristic based on the experts’experience,while some technologies are based on statistic methods using machine learning,deep learning,or reinforcement learning.Many metrics have been adopted to evaluate and compare different task scheduling technologies that try to optimize different goals of task scheduling.Although statistic task scheduling has reached fewer research achievements than heuristic task scheduling,the statistic task scheduling still has significant research potential.
基金supported by the Science and Technology Project of State Grid Corporation“Research and Application of Internet Operation Platform for Ubiquitous Power Internet of Things”(5700-201955462A-0-0-00).
文摘The energy Internet operation platform provides market entities such as energy users,energy enterprises,suppliers,and governments with the ability to interact,transact,and manage various operations.Owing to the large number of platform users,complex businesses,and large amounts of data-mining tasks,it is necessary to solve the problems afflicting platform task scheduling and the provision of simultaneous access to a large number of users.This study examines the two core technologies of platform task scheduling and multiuser concurrent processing,proposing a distributed task-scheduling method and a technical implementation scheme based on the particle swarm optimization algorithm,and presents a systematic solution in concurrent processing for massive user numbers.Based on the results of this study,the energy internet operation platform can effectively deal with the concurrent access of tens of millions of users and complex task-scheduling problems.
基金ACKNOWLEDGEMENTS The authors would like to thank the reviewers for their detailed reviews and constructive comments, which have helped improve the quality of this paper. The research has been partly supported by National Natural Science Foundation of China No. 61272528 and No. 61034005, and the Central University Fund （ID-ZYGX2013J073）.
文摘Many Task Computing(MTC)is a new class of computing paradigm in which the aggregate number of tasks,quantity of computing,and volumes of data may be extremely large.With the advent of Cloud computing and big data era,scheduling and executing large-scale computing tasks efficiently and allocating resources to tasks reasonably are becoming a quite challenging problem.To improve both task execution and resource utilization efficiency,we present a task scheduling algorithm with resource attribute selection,which can select the optimal node to execute a task according to its resource requirements and the fitness between the resource node and the task.Experiment results show that there is significant improvement in execution throughput and resource utilization compared with the other three algorithms and four scheduling frameworks.In the scheduling algorithm comparison,the throughput is 77%higher than Min-Min algorithm and the resource utilization can reach 91%.In the scheduling framework comparison,the throughput(with work-stealing)is at least 30%higher than the other frameworks and the resource utilization reaches 94%.The scheduling algorithm can make a good model for practical MTC applications.
文摘An optimal algorithmic approach to task scheduling for, triplet based architecture（TriBA）, is proposed in this paper. TriBA is considered to be a high performance, distributed parallel computing architecture. TriBA consists of a 2D grid of small, programmable processing units, each physically connected to its three neighbors. In parallel or distributed environment an efficient assignment of tasks to the processing elements is imperative to achieve fast job turnaround time. Moreover, the sojourn time experienced by each individual job should be minimized. The arriving jobs are comprised of parallel applications, each consisting of multiple-independent tasks that must be instantaneously assigned to processor queues, as they arrive. The processors independently and concurrently service these tasks. The key scheduling issues is, when some queue backlogs are small, an incoming job should first spread its tasks to those lightly loaded queues in order to take advantage of the parallel processing gain. Our algorithmic approach achieves optimality in task scheduling by assigning consecutive tasks to a triplet of processors exploiting locality in tasks. The experimental results show that tasks allocation to triplets of processing elements is efficient and optimal. Comparison to well accepted interconnection strategy, 2D mesh, is shown to prove the effectiveness of our algorithmic approach for TriBA. Finally we conclude that TriBA can be an efficient interconnection strategy for computations intensive applications, if tasks assignment is carried out optimally using algorithmic approach.
基金partially been sponsored by the National Science Foundation of China(No.61572355,61272093,610172063)Tianjin Research Program of Application Foundation and Advanced Technology under grant No.15JCYBJC15700
文摘Task scheduling in cloud computing environments is a multi-objective optimization problem, which is NP hard. It is also a challenging problem to find an appropriate trade-off among resource utilization, energy consumption and Quality of Service(QoS) requirements under the changing environment and diverse tasks. Considering both processing time and transmission time, a PSO-based Adaptive Multi-objective Task Scheduling(AMTS) Strategy is proposed in this paper. First, the task scheduling problem is formulated. Then, a task scheduling policy is advanced to get the optimal resource utilization, task completion time, average cost and average energy consumption. In order to maintain the particle diversity, the adaptive acceleration coefficient is adopted. Experimental results show that the improved PSO algorithm can obtain quasi-optimal solutions for the cloud task scheduling problem.
基金This work was supported in part by the National Natural Science Foundation of China under Grant No.61802449the Guangdong Natural Science Funds under Grant No.2021A1515011912.
文摘Collaborative cross-edge analytics is a new computing paradigm in which Internetof Things (IoT) data analytics is performed across multiple geographically dispersededge clouds. Existing work on collaborative cross-edge analytics mostly focuses on reducingeither analytics response time or wide-area network (WAN) traffic volume. In thiswork, we empirically demonstrate that reducing either analytics response time or networktraffic volume does not necessarily minimize the WAN traffic cost, due to the price heterogeneityof WAN links. To explicitly leverage the price heterogeneity for WAN cost minimization,we propose to schedule analytic tasks based on both price and bandwidth heterogeneities.Unfortunately, the problem of WAN cost minimization underperformance constraintis shown non-deterministic polynomial (NP)-hard and thus computationally intractablefor large inputs. To address this challenge, we propose price- and performanceawaregeo-distributed analytics (PPGA) , an efficient task scheduling heuristic that improvesthe cost-efficiency of IoT data analytic jobs across edge datacenters. We implementPPGA based on Apache Spark and conduct extensive experiments on Amazon EC2to verify the efficacy of PPGA.
基金supported in part by the National Natural Science Foundation of China under Grant No.61473066in part by the Natural Science Foundation of Hebei Province under Grant No.F2021501020+2 种基金in part by the S&T Program of Qinhuangdao under Grant No.202401A195in part by the Science Research Project of Hebei Education Department under Grant No.QN2025008in part by the Innovation Capability Improvement Plan Project of Hebei Province under Grant No.22567637H
文摘Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power stations).To solve the problem,we propose an energy harvesting based task scheduling and resource management framework to provide robust and low-cost edge computing services for smart grid.First,we formulate an energy consumption minimization problem with regard to task offloading,time switching,and resource allocation for mobile devices,which can be decoupled and transformed into a typical knapsack problem.Then,solutions are derived by two different algorithms.Furthermore,we deploy renewable energy and energy storage units at edge servers to tackle intermittency and instability problems.Finally,we design an energy management algorithm based on sampling average approximation for edge computing servers to derive the optimal charging/discharging strategies,number of energy storage units,and renewable energy utilization.The simulation results show the efficiency and superiority of our proposed framework.
基金The National Natural Science Foundationof China(No.60873030 )the National High-Tech Research and Development Plan of China(863 Program)(No.2007AA01Z309)
文摘By combining fault-tolerance with power management, this paper developed a new method for aperiodic task set for the problem of task scheduling and voltage allocation in embedded real-time systems. The scbedulability of the system was analyzed through checkpointing and the energy saving was considered via dynamic voltage and frequency scaling. Simulation results showed that the proposed algorithm had better performance compared with the existing voltage allocation techniques. The proposed technique saves 51.5% energy over FT-Only and 19.9% over FT ＋ EC on average. Therefore, the proposed method was more appropriate for aperiodic tasks in embedded real-time systems.
