Non-cooperative, semi-cooperative, and cooperative games-based grid resource allocation

Khan,; Ahmad, Zainal Arifin

doi:10.1109/ipdps.2006.1639358

Cited by 63 publications

(37 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to the example in Khan and Ahmad [32] discussed in Sect. 2.3 this is not self-interested behaviour.…”

Section: Decentralised Market Mechanismsmentioning

confidence: 79%

“…Khan and Ahmad [32] show that in any cooperative approach, global optima can only be achieved when all the nodes cooperate. In a discussion of lessons learnt from experience with load management in giant-scale web services, Brewer [5] proposes the idea of incorporating, into a request for a resource, a notion of its value or cost.…”

Section: Existing Market-based Approachesmentioning

confidence: 99%

“…Indeed, in Khan and Ahmad's [32] study of various games-based resource allocation methods, non-cooperative agents bid for jobs based on an honest estimation of the estimated time to complete a job, without consideration of the benefit they expect to derive from the bid. This is clearly not the self-interested behaviour relied upon by economics.…”

Section: Existing Market-based Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Resource allocation in decentralised computational systems: an evolutionary market-based approach

Lewis

Marrow

Yao

2009

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

We present a novel market-based method, inspired by retail markets, for resource allocation in fully decentralised systems where agents are self-interested. Our market mechanism requires no coordinating node or complex negotiation. The stability of outcome allocations, those at equilibrium, is analysed and compared for three buyer behaviour models. In order to capture the interaction between self-interested agents, we propose the use of competitive coevolution. Our approach is both highly scalable and may be tuned to achieve specified outcome resource allocations. We demonstrate the behaviour of our approach in simulation, where evolutionary market agents act on behalf of service providing nodes to adaptively price their resources over time, in response to market conditions. We show that this leads the system to the predicted outcome resource allocation. Furthermore, the system remains stable in the presence of small changes in price, when buyers' decision functions degrade gracefully.

show abstract

“…Similarly to the example in Khan and Ahmad [32] discussed in Sect. 2.3 this is not self-interested behaviour.…”

Section: Decentralised Market Mechanismsmentioning

confidence: 79%

Section: Existing Market-based Approachesmentioning

confidence: 99%

Section: Existing Market-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Resource allocation in decentralised computational systems: an evolutionary market-based approach

Lewis

Marrow

Yao

2009

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

show abstract

“…Schedulers have to take into account the network bandwidth availability and the latency of data transfer between a computational node to which a task is going to be submitted, and the storage resource(s) from which the data required is to be retrieved [19], [11]. Therefore, the scheduler needs to be aware of any replicas "close" to the computation node and if the replication is coupled to the scheduling, then create a new copy of the data.…”

Section: Data Grid Elementsmentioning

confidence: 99%

Data Scheduling in Data Grids and Data Centers: A Short Taxonomy of Problems and Intelligent Resolution Techniques

Kołodziej

Khan

2013

Transactions on Computational Collective Intelligence X

View full text Add to dashboard Cite

Abstract. Data-aware scheduling in today's large-scale heterogeneous environments has become a major research issue. Data Grids (DGs) and Data Centers arise quite naturally to support needs of scientific communities to share, access, process, and manage large data collections geographically distributed. Data scheduling, although similar in nature with grid scheduling, is given rise to the definition of a new family of optimization problems. New requirements such as data transmission, decoupling of data from processing, data replication, data access and security are to be added to the scheduling problem are the basis for the definition of a whole taxonomy of data scheduling problems. In this paper we briefly survey the state-of-the-art in the domain. We exemplify the model and methodology for the case of data-aware independent job scheduling in computational grid and present several heuristic resolution methods for the problem.

show abstract

“…Khan [17] classified game-based co-allocation models into three types: cooperative, semi-cooperative and non-cooperative. By extensive simulations, they concluded that the cooperative method leads to better task rejection, utilization and turnaround time as well as comparable load fairness and makespan.…”

Section: Related Workmentioning

confidence: 99%

A Global Benefit Maximization Task-Bundle Allocation

Zheng

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Obtaining maximal benefit is usually the most important goal pursued by Grid resource/service provider. As providers and users being noncooperative inherently, it is a fundamental challenge to design a resource allocation strategy which seems to be fair. In order to adapt to large-scale Grid environment, we adopted a hierarchical grid structure with bundle tasks to describe the Grid system. A model called Intra-Site Cooperative-game of Taskbundle (ISCT) was proposed, in which all subordinate resources participated in making profits. We calculated task market price based on the theoretical proof that the system would gain maximal global benefit if and only if it was in a balanced state. Then we determined the task allocation solution with solving the task assignment amount vector. An Intra-Site Global Benefit Maximization Allocation for Task-bundle (ISGBMAT) was presented, which converted the Grid task-bundle allocation problem into an iteration process involving retail price, market price and assignment amount of tasks. Extensive simulation experiments with real workload traces were conducted to verify our algorithm. The experimental results indicated that ISGBMAT could provide an effective solution with global benefit and completion time optimization and also adapt to dynamic Grid market.

show abstract

Non-cooperative, semi-cooperative, and cooperative games-based grid resource allocation

Abstract: Abstract

Cited by 63 publications

References 21 publications

Resource allocation in decentralised computational systems: an evolutionary market-based approach

Resource allocation in decentralised computational systems: an evolutionary market-based approach

Data Scheduling in Data Grids and Data Centers: A Short Taxonomy of Problems and Intelligent Resolution Techniques

A Global Benefit Maximization Task-Bundle Allocation

Contact Info

Product

Resources

About