With the rapid development of Internet technology and the emergence of more flexible applications, dynamic allocation of network resources is becoming more and more significant. Since bandwidth resource is limited, us...
详细信息
With the rapid development of Internet technology and the emergence of more flexible applications, dynamic allocation of network resources is becoming more and more significant. Since bandwidth resource is limited, users' dynamic allocation requests cannot always be granted. Therefore, scheduling the dynamic requests to achieve optimal bandwidth utilization or service rate is of great importance. However, this is difficult to achieve in current networks due to the lack of programming interface of network devices for effective and centralized control and management. In recent years, the emergence of software-defined networks (SDN) provides us an opportunity to realize the goal. Centralized control and programmability of SDN let network managers configure, manage and optimize network resources very easily and quickly. In this paper, a dynamic scheduling algorithm based on an optimization model for scheduling reservation-based bandwidth allocation requests is proposed to achieve optimal resource utilization. Simulation result shows that the scheduling algorithm proposed in this paper could achieve higher bandwidth utilization compared to another two scheduling algorithms.
Task scheduling problem in cloud computing environment is NP-hard problem, which is difficult to obtain exact optimal solution and is suitable for using intelligent optimization algorithms to approximate the optimal s...
详细信息
ISBN:
(纸本)9781479986477
Task scheduling problem in cloud computing environment is NP-hard problem, which is difficult to obtain exact optimal solution and is suitable for using intelligent optimization algorithms to approximate the optimal solution. Meanwhile, quality of service (QoS) is an important indicator to measure the performance of task scheduling. In this paper, a novel task scheduling algorithm MQoS-GAAC with multi-QoS constraints is proposed, considering the time-consuming, expenditure, security and reliability in the scheduling process. The algorithm integrates ant colony optimization algorithm (ACO) with genetic algorithm (GA). To generate the initial pheromone efficiently for ACO, GA is invoked. With the designed fitness function, 4-dimensional QoS objectives are evaluated. Then, ACO is utilized to seek out the optimum resource. The experiment indicates that the proposed algorithm has preferable performance both in balancing resources and guaranteeing QoS.
Real-time systems often involve time critical control tasks in which their correctness depends not only on the functionality but also on timeliness. In order to guarantee the timely-correctness, real-time scheduling h...
详细信息
Real-time systems often involve time critical control tasks in which their correctness depends not only on the functionality but also on timeliness. In order to guarantee the timely-correctness, real-time scheduling has been studied extensively. The main problem of multiprogramming scheduling on a single processor is that an optimum fixed priority scheduler has a least upper bound to processor utilization, which is around 70 percent for large tasksets, in contrast, full processor utilization can be achieved by dynamically assigning priorities. In this paper DynAmic Real-time Task scheduling (DARTS) algorithm is proposed, which is based on dynamic utilization and assigns higher priority to a task with the highest utilization with regard to its laxity. Eventually, this method is extended for multiprocessor systems and we demonstrate that not only does DARTS algorithm have better utilization than existing global EDF schedulability tests, but it also has significantly well outputs in total utilization less than 90 percent.
Cloud computing is a platform for hosting an immense number of applications and computing services that will continuously change due to a large number of jobs randomly submitted by the end user. Thus, scheduling becom...
详细信息
ISBN:
(纸本)9781509019342
Cloud computing is a platform for hosting an immense number of applications and computing services that will continuously change due to a large number of jobs randomly submitted by the end user. Thus, scheduling becomes strenuous in cloud computing because of an immense number of jobs submitted randomly. The ultimate intention of the proposed work is to minimize the makespan of the job, to improve the processor utilization irrespective with the cloud environment. Hence, this paper posits a novel approach called Adaptive Deadline Based Dependent Job scheduling (A2DJS) algorithm in cloud computing that comprises of three major components as job manager, data center and VM creation. Here, the job manager embeds with dependency resolver and task-prioritizer. The dependency resolver will determine the dependency among the tasks and task-prioritizer will prioritize the tasks to avoid starvation. Moreover, the data center embeds with job scheduler and host creation with VM allocation. The job scheduler schedules the job with the VM existing. The host creation with VM allocation allocates the jobs to the VM in a two-tier VM architecture. This contribution will mitigate the makespan of the job, evade starvation and improve the processor utilization. The results are simulated using cloudsim that shows the performance of the proposed A2DJS algorithm better when compared to the existing algorithms.
Despite distributed in computation and data storage, current data-parallel computing systems are centralized in task scheduling, which results in hierarchies that create single point of failure, limit scalability, and...
详细信息
Despite distributed in computation and data storage, current data-parallel computing systems are centralized in task scheduling, which results in hierarchies that create single point of failure, limit scalability, and increase administration costs. In this paper, we propose a fully decentralized scheduling algorithm for data-parallel computing systems on peer-to-peer (P2P) networks. Our scheduling algorithm eliminates the centralized scheduler by letting each node in the network make scheduling decisions. To achieve good performance, data locality, which stresses the efficiency of colocating tasks with their input data, and load-balancing, should be considered jointly, and in a decentralized fashion. By exploring a backpressure-based approach, the proposed task scheduling algorithm strikes the right balance between data locality and load-balancing with each node only knowing the status information of part of the nodes in the network, and proves to maximize the throughput.
This paper presents an energy scheduling algorithm for a small-scale microgrid serving small to medium size commercial buildings (the Building Microgrid) that includes conventional and renewable distributed generation...
详细信息
This paper presents an energy scheduling algorithm for a small-scale microgrid serving small to medium size commercial buildings (the Building Microgrid) that includes conventional and renewable distributed generation resources, energy storage, and both linear and nonlinear loads. An essential study objective is to mitigate power quality issues through coordinating the operating schedules of sensitive devices in the Building Microgrid. The proposed energy scheduling algorithm is formulated as a mixed integer programming problem where power quality requirements are modeled in the constraints. The algorithm also involves validation with the harmonics and dynamic event simulations. Case studies have been performed with realistic model parameters to verify the performance of the algorithm. The study results demonstrate the effectiveness of the algorithm in managing voltage and frequency deviations, as well as harmonic distortions. In the transaction-based control framework, the proposed algorithm can be used to aggregate device transaction bids and facilitate the buildings-to-grid integration.
This paper proposes a novel Resource scheduling (RS) method by using Hybrid Broadcasting and Cellular Networks (HBCN). In this approach, the hot or common information is assigned with higher priority levels and is pre...
详细信息
This paper proposes a novel Resource scheduling (RS) method by using Hybrid Broadcasting and Cellular Networks (HBCN). In this approach, the hot or common information is assigned with higher priority levels and is preferentially scheduled. The Equivalent Throughput (ET) and fairness are redefined and discussed. Simulations show the ETs of the networks are improved by using the proposed algorithms, the hotter the information, the more efficient the network. Moreover, the simulations also show the more cells in the coverage of the terrestrial broadcasting network, the more efficient of the HBCN.
In this paper, a feedrate scheduling algorithm based on master axis is proposed to generate smooth five-axis tool center point (TCP) trajectory. The method first plans corner feedrate while respecting jerk continuity ...
详细信息
In this paper, a feedrate scheduling algorithm based on master axis is proposed to generate smooth five-axis tool center point (TCP) trajectory. The method first plans corner feedrate while respecting jerk continuity of three linear axes at block corner. The axis with the maximum movement among TCP and rotary axes is selected to be a master, and the ratios among the movements of the master and other axes are obtained. Five-axis feedrate regulation formulation (FFRF) is utilized to evaluate the velocity of the master axis. Feedrate command on TCP is adjusted with the constraints of jerks and movements of TCP and rotary axes. S-shape acceleration/ deceleration (ACC/DE C) method is us ed to achieve velocity smoothing and generate five-axis interpolation commands. Finally, the cutting experiments are performed to verify the efficiency of the proposed technology on a five-axis engraving machine.
A large class of Wireless Sensor Networks applications involved in monitoring environmental parameters in isolated urban areas covered with sensor nodes. Mobile sinks are mounted upon isolated urban areas with fixed t...
详细信息
A large class of Wireless Sensor Networks applications involved in monitoring environmental parameters in isolated urban areas covered with sensor nodes. Mobile sinks are mounted upon isolated urban areas with fixed trajectories to monitor environmental parameters. These MS provides ideal infrastructure for retrieving sensory data from isolated WSNfields. The existing approach uses the multi-hop technique for transfer of data from SNs lies within MS's range and network traffic can be balanced among sensor nodes. When sensor nodes run out of energy, the resulting loss of network connectivity and decreasing network life time. In this paper, an ant colony optimization (ACO) scheduling algorithm is exploredfor maximizing the network life, it can be done in three phases. In phase one, finds the initial active sensor nodes with fully coverage constraints. In second phase, it uses successor sensor set, for activating the sensor nodes for reaching constraint. In third phase, sensory data will be forwarded to MS through rendezvous nodes.
Long Term Evolution (LTE) a Third Generation Partnership Project (3GPP) is developed for multimedia applications on mobile user equipment with very high data rates of the order 75/300 Mbps and low latency of 10msec. T...
详细信息
Long Term Evolution (LTE) a Third Generation Partnership Project (3GPP) is developed for multimedia applications on mobile user equipment with very high data rates of the order 75/300 Mbps and low latency of 10msec. The high data rates are achieved by using SC-FDMA radio access mechanism for uplink communication and OFDM access mechanism for downlink. The performance can be further improved by scheduling the user data in an efficient manner considering channel characteristics as well as its QOS parameters, thereby allocating the resources to maximize the throughput. The Packet Scheduler helps in handling the LTE data traffic by allocating the resources both in time and frequency dimension. In this paper, we propose a novel scheduling algorithm that allocates maximum resources for the random users depending on their channel SNR condition with main focus on the data flow behavior. This is then compared with the two distinct algorithms that focus mainly on flow level dynamics- Fair Fixed Assignment (FFA) and Maximum added value (MAV) algorithms. It is shown that our algorithm outperforms the other two algorithms in terms of mean flow transfer time.
暂无评论