A Novel Algorithm for Task Scheduling in Grid Computing Based on Game Theory

Yao, Lina; Dai, Guanzhong; Zhang, Huixiang; Ren, Shuai; Niu, Yun

doi:10.1109/hpcc.2008.74

Cited by 6 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is obvious that the trend of HMM prediction bids approximates the actual bids most of the time. However, the mean value prediction [2] bids fluctuate without any connection with the actual bids. Thus, we can conclude from the results that the prediction model based on HMM can approximate the actual bids better than the prediction method adopted by [2].…”

Section: Resultsmentioning

confidence: 99%

“…(9), the results are shown in Figure.2. The ESPSA algorithm performs better than the algorithm in [2] in approximating the actual value. Figure.3 depicts the victorious probability results of random bidding, mean value prediction bidding and ESPSA prediction bidding strategies.…”

Section: Equilibrium Analysismentioning

confidence: 93%

“…Game theoretic methods have been adopted in settings of cloud and grid computing. In the first place, from the grid computing perspective, Lei Yao and Guanzhong Dai (2008) [2] focus on resource-rich environment. They propose a method, namely GVP, which could guarantee resources' victorious probabilities.…”

Section: Related Workmentioning

confidence: 99%

“…Resource utilization rate and execution time. By increasing the user brokers that take part in the GVP [2] and ESPSA game, the recorded resource utilization rate of the two algorithms are illustrated as Figure 5. It is worth to note that each data in Figure 5 is abtained through 200 rounds of auctions.…”

Section: )mentioning

confidence: 99%

“…Reference [2] utilized a mean value prediction method. Specifically, a player calculates his rival's bid in the current round of auction by Eq.…”

Section: Equilibrium Analysismentioning

confidence: 99%

See 4 more Smart Citations

A Game Theoretic Resource Allocation Model Based on Extended Second Price Sealed Auction in Grid Computing

Sun¹,

Xia²,

Xu³

et al. 2012

JCP

View full text Add to dashboard Cite

In resource-limited environment, grid users compete for limited resources, and how to guarantee tasks’ victorious probabilities is one of the most primary issues that a resource scheduling model cares. In order to guarantee higher task’s victorious probabilities in grid resources scheduling situations, a novel model, namely ESPSA (Extended Second Price Sealed Auction), is proposed. The ESPSA model introduces an analyst entity, and designs analyst’s prediction algorithm based on Hidden Markov Model (HMM). In ESPSA model, grid resources are sold through second price sealed auction. Moreover, to achieve high victorious probabilities, the user brokers who are qualified to participate in the auctions will predict other players’ bids and then carry out the most beneficial bids. The ESPSA model is simulated based on GridSim toolkit. Simulation results show that the ESPSA model assures a higher victorious probability and superior to other traditional algorithms. Moreover, we analyze the existence of Nash equilibrium based on simulation results, thus, any participant who changes its strategy unilaterally could not make the results better

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Equilibrium Analysismentioning

confidence: 93%

Section: Related Workmentioning

confidence: 99%

Section: )mentioning

confidence: 99%

“…Reference [2] utilized a mean value prediction method. Specifically, a player calculates his rival's bid in the current round of auction by Eq.…”

Section: Equilibrium Analysismentioning

confidence: 99%

See 3 more Smart Citations

A Game Theoretic Resource Allocation Model Based on Extended Second Price Sealed Auction in Grid Computing

Sun¹,

Xia²,

Xu³

et al. 2012

JCP

View full text Add to dashboard Cite

show abstract

Dynamic task assignment and resource management in cloud services by using bargaining solution

Shin

Park

Jung

2013

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYCloud computing provides infrastructure, platform and software as services to customers. For the purpose of providing reliable and truthful service, a fair and elastic resource allocation strategy is essential from the standpoint of service customers. In this paper, we propose a game theoretic mechanism for dynamic cloud service management, including task assignment and resource allocation to provide reliable and truthful cloud services. A user utility function is first devised considering the dynamic characteristics of cloud computing. The elementary stepwise system is then applied to efficiently assign tasks to cloud servers. A resource allocation mechanism based on bargaining game solution is also adopted for fair resource allocation in terms of quality of service of requested tasks. Through numerical experiments, it is shown that the proposed mechanism guarantees better system performance than several existing methods. The experimental results show that the mechanism completes the requested tasks earlier with relatively higher utility while providing a significant level of fairness compared with existing ones. The proposed mechanism is expected to support cloud service providers in elastically managing their limited resources in a cloud computing environment in terms of quality of service.

show abstract

Optimizing performance and energy in computational grids using non-cooperative game theory

Wilkins

Ahmad

Sheikh

et al. 2010

International Conference on Green Computing

View full text Add to dashboard Cite

A Novel Algorithm for Task Scheduling in Grid Computing Based on Game Theory

Cited by 6 publications

References 12 publications

A Game Theoretic Resource Allocation Model Based on Extended Second Price Sealed Auction in Grid Computing

A Game Theoretic Resource Allocation Model Based on Extended Second Price Sealed Auction in Grid Computing

Dynamic task assignment and resource management in cloud services by using bargaining solution

Optimizing performance and energy in computational grids using non-cooperative game theory

Contact Info

Product

Resources

About