Grid Resource Scheduling Algorithms Research Articles

Energy Optimization Based on Grid Resource Scheduling Algorithm

Energy Optimization Based on Grid Resource Scheduling Algorithm

Imperfect Information Dynamic Stackelberg Game Based Resource Allocation Using Hidden Markov for Cloud Computing

Existing static grid resource scheduling algorithms, which are limited to minimizing the makespan, cannot meet the needs of resource scheduling required by cloud computing. Current cloud infrastructure solutions provide operational support at the level of resource infrastructure only. When hardware resources form the virtual resource pool, virtual machines are deployed for use transparently. Considering the competing characteristics of multi-tenant environments in cloud computing, this paper proposes a cloud resource allocation model based on an imperfect information Stackelberg game (CSAM-IISG) using a hidden Markov model (HMM) in a cloud computing environment. CSAM-IISG was shown to increase the profit of both the resource supplier and the applicant. Firstly, we used the HMM to predict the service provider's current bid using the historical resources based on demand. Through predicting the bid dynamically, an imperfect information Stackelberg game (IISG) was established. The IISG motivates service providers to choose the optimal bidding strategy according to the overall utility, achieving maximum profits. Based on the unit prices of different types of resources, a resource allocation model is proposed to guarantee optimal gains for the infrastructure supplier. The proposed resource allocation model can support synchronous allocation for both multi-service providers and various resources. The simulation results demonstrated that the predicted price was close to the actual transaction price, which was lower than the actual value in the game model. The proposed model was shown to increase the profits of service providers and infrastructure suppliers simultaneously.

Heuristic Grid Resource Scheduling Algorithm based on Group of Task and Secondary Distribution

Grid resource scheduling policies directly affect the performance of the grid, so the grid resource scheduling algorithm for grid research has become a hot spot. In this paper, based on grid heterogeneity to resource scheduling of load balancing, effective resource utilization and minimize task sets the span of time (Makespan) as the goal, propose a heuristic grid resource scheduling algorithm based on Group of Task and Secondary Distribution, the basic idea is dividing the set of tasks into two groups by using the standard deviation, the one is long tasks group, another is short tasks group .The longest task in long tasks group will be allocated to the worst performance to execute, the rest can be done in the same manner. Tasks in short tasks group will be executed by the Min-Min algorithm , and then through secondary dispatch ideas to make the grid system to quickly reach each resource load balancing , improving resource utilization efficiency and minimizing the task set time span. Finally, the simulation model benchmark Braun et al. demonstrates the effectiveness of the algorithm.

Job Scheduling Using Coupling in Grid

The grid computing main concern is to use the resources efficiently. For achieving this many grid resource scheduling algorithms are used for the efficient use of unused resources, especially CPU. The scheduling algorithms assign single complete job to a single resource. Instead, if these algorithms consider the degree of dependency among the modules of a job, they can be allocated parallel to the different resources. This reduces the completion time of the job and the resources can be utilized to its maximum extent. Towards this, the job scheduling using coupling algorithm is proposed. This algorithm puts forward the idea of considering the coupling degree while allocating the modules of a job parallel to different resources. In this algorithm, resource selection is done by using both its functional and non-functional properties. The algorithm works in 3 phases. It groups the interdependent modules of a job into different sets using coupling in the first phase. It checks the non-functional property i.e. availability of a resource using echo procedure in the second phase and in the third phase, the sets created in first phase, are allocated parallel to different available and matching resources. From the simulation results it is observed that job scheduling using coupling algorithm gives better performance in terms of reduced turnaround time as compared to First Come First Served, Largest Task First and Minimum Execution Time scheduling algorithms.

OPT-Min-Min Scheduling Algorithm of Grid Resources

As a newly emerged distributed computing platform, the Gird aims at the implementation of resources sharing and collaborative computing on the internet. Research on grid resource scheduling algorithm is one of the core problems of grid technology, as well as an essential part of grid resource management. Resource scheduling in grid environment refers to the application of tasks scheduling algorithm to assign the works in the grid to the right resources. During the allocation process, the computing performance of grid resource nodes, communication parameters and loading balance, etc., shall be put into consideration. Since they are all dynamic for both the grid resources and the grid resource nodes, requirements on grid resource scheduling algorithm are relatively higher if compared to those existing parallel resource scheduling algorithm. Based on the Min-Min scheduling algorithm, the OPT- Min-Min scheduling algorithm is presented to overcome the drawbacks. Upon the basis of applying Min-Min pre- scheduling into stage one, by adapting the strategy of two- rounds scheduling, the assignment on heavy load resources are rescheduled to balance the load. Actual cases are used to illustrate the superiority of OPT-Min-Min scheduling algorithm to the Min-Min scheduling algorithm. Simulation experiments were carried out to the batch grid resource scheduling algorithms including Min-Min, Max-Min, Min- mean and OPT-Min-Min. According to the ETC generation technique used in experimental benchmarks, ETC matrix was generated. By the comparing and analyzing the Min- Min, Max-Min and Min-mean scheduling algorithm, the validity of OPT-Min-Min scheduling algorithm is proved. Index Terms—Grid; Scheduling Strategy; OPT-Min-Min; resource scheduling algorithm; load balance

Joint QoS optimization for layered computational grid

Many existing grid resource allocation and scheduling algorithms mainly focus on isolated layers of the grid architecture. The inflexibility of the strict layering structure results in an inefficient utilization of the grid resources. This paper takes a system view of the computational grid and aims to jointly optimize global QoS by adopting cross-layer design. Cross-layer design is based on information exchange and joint optimization among multiple grid layers. Parameters from different layers are provided to a cross-layer optimizer, which selects the values of the layer specific parameters maximizing joint global QoS. The objective of the paper is to jointly optimize the parameters of all layers in a decentralized optimization problem and decompose joint QoS optimization into three sub problems at fabric layer, collective layer and application layer. In simulation part, we compare the performance of the global joint QoS optimization approach with application layer local optimization and resource layer local optimization approach, respectively.

An optimization approach for decentralized QoS‐based scheduling based on utility and pricing in Grid computing

AbstractThis paper presents an optimization approach for decentralized Quality of Service (QoS)‐based scheduling based on utility and pricing in Grid computing. The paper assumes that the quality dimensions can be easily formulated as utility functions to express quality preferences for each task agent. The utility values are calculated by the user‐supplied utility function that can be formulated with the task parameters. The QoS constraint Grid resource scheduling problem is formulated into a utility optimization problem. The QoS‐based Grid resource scheduling optimization is decomposed into two subproblems by applying the Lagrangian method. In the Grid, a Grid task agent acts as a consumer paying for the Grid resource and the resource providers receive profits from task agents. A pricing‐based QoS scheduling algorithm is used to perform optimally decentralized QoS‐based resource scheduling. The experiments investigate the effect of the QoS metrics on the global utility and compare the performance of the proposed algorithm with other economical Grid resource scheduling algorithms. Copyright © 2006 John Wiley & Sons, Ltd.