No abstract

No abstract

In order to efficiently utilize available grid resources and promptly complete tasks assigned to the grid, providing a suitable job scheduling strategy for the grid computing is necessary. Lots of grid scheduling algorithms have already been developed, and some of them are used to schedule independent coarse-grained tasks. Those algorithms don't adapt very well to the grid tasks that are submitted continuously and randomly. Besides, they mostly need a prediction system to provide the prediction information about the processor utilization and the task workloads. This paper proposes an adaptive grid scheduling system for high-throughput applications. Firstly, a grid scheduling model is adopted to represent the performance of processors, the task workloads, and the schedules. Then we develop a scheduling algorithm that doesn't need any prediction information and can adapt to the grid environment. Finally, the scheduling system combines the proposed algorithm with the best of scheduling algorithms that need the prediction information. According to the accuracy of the prediction system in the grid, the system selects the proper strategy to schedule tasks. A prototype of this model is developed and tested with several experiments. The experimental results of the simulation show that the proposed scheduling system is able to perform scheduling well in the grid environment.

Due to the rapid growth of the hardware technology, personal computers and workstations are more powerful than before. Instead of using the expensive supercomputer, many personal computers can be connected by a high speed network to form a distributed computing system, so as to decrease the cost of building a high performance computing system.To link all of the dispersed nodes to a cluster, it is very important to setup an agent for achieving the load balancing of the cluster. A Grey Dynamic model-based Load Balancing Mechanism (GMLBM) has been proposed in this paper. It will produce grey prediction for the load data according to the grey theory By applying a few data to get the load model for assigning new tasks according to the load in the predicted group for avoiding the overloading or vacancy of some nodes, so as to eliminate the system bottleneck and improve the system performance. The GMLBM is installed at the agent. The agent detects records and predicts the load of each node in a local group, and selects the node with the lowest load predicted as the node for executing the next task. A simulation has been made to evaluate the performance of the proposed system. By comparing with other load balancing methods, the experimental results show that the method of GMLBM can achieve a better performance than that of round robin and linear extrapolation.

The decision of call admission becomes an important work owing to the scarce wireless spectrum for wireless cellular networks. If there exists adequate information for call admission control (CAC) schemes, the terms of quality of service (QoS), such as call dropping probability (CDP), call blocking probability (CBP), and system utilization, will be kept in a certain acceptable level. Therefore, a prediction system which can predict most information, such as system utilization and CDP, in advance with a novel data mining technique and a distributed CAC scheme is presented in this paper. Based on the prediction results and the bandwidth consumption of adjacent cells, the proposed CAC scheme is able to decide to admit a new call. The throttle flag that can indicate the usage of current cell is proposed to prevent the newly admitted call request from being blocked in adjacent cells if handoff is needed. The simulation results show that the proposed CAC scheme can maintain the CDP below a predefined threshold, and the CBP is also lower than the cluster prediction and traditional guard channel policies.