Grid resource allocation by means of option contracts

In Grid environments, where virtual organization resources are allocated to users using mechanisms analogue to market economies, strong price fluctuations can have an impact on the nontrivial quality-of-service expected by end users. In this paper, we investigate the effects of the use of option con...

Full description

Bibliographic Details
Main Authors: Bossenbroek, Anton, Tirado-Ramos, Alfredo, Sloot, Peter M. A.
Other Authors: School of Computer Engineering
Format: Journal Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/95966
http://hdl.handle.net/10220/10175
_version_ 1826117105914740736
author Bossenbroek, Anton
Tirado-Ramos, Alfredo
Sloot, Peter M. A.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Bossenbroek, Anton
Tirado-Ramos, Alfredo
Sloot, Peter M. A.
author_sort Bossenbroek, Anton
collection NTU
description In Grid environments, where virtual organization resources are allocated to users using mechanisms analogue to market economies, strong price fluctuations can have an impact on the nontrivial quality-of-service expected by end users. In this paper, we investigate the effects of the use of option contracts on the quality of service offered by a broker-based Grid resource allocation model. Option contracts offer users the possibility to buy or sell Grid resources in the future for a strike price specified in a contract. By buying, borrowing and selling option contracts using a hedge strategy users can benefit from expected price changes. In this paper, we consider three hedge strategies: the butterfly spread which profits from small changes, the straddle which benefits from large price changes, and the call strategy which benefits from soaring prices. Using our model based on an abstract Grid architecture, we find that the use of hedge strategies augment the ratio of successfully finished jobs to failed jobs. We show that the degree of successfulness from hedge strategies changes when the number of contributed resources changes. By means of a model, we also show that the effects of the butterfly spread is mainly explained by the amount of contributed resources. The dynamics of the two other hedge strategies are best explained by observing the price behavior. We also find that by using hedge strategies the users can increase the probability that a job will finish before the deadline. We conclude that hedging using options is a promising approach to improve resource allocation in environments where resources are allocated by using a commodity market mechanism.
first_indexed 2024-10-01T04:22:18Z
format Journal Article
id ntu-10356/95966
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:22:18Z
publishDate 2013
record_format dspace
spelling ntu-10356/959662020-05-28T07:17:49Z Grid resource allocation by means of option contracts Bossenbroek, Anton Tirado-Ramos, Alfredo Sloot, Peter M. A. School of Computer Engineering DRNTU::Engineering::Computer science and engineering In Grid environments, where virtual organization resources are allocated to users using mechanisms analogue to market economies, strong price fluctuations can have an impact on the nontrivial quality-of-service expected by end users. In this paper, we investigate the effects of the use of option contracts on the quality of service offered by a broker-based Grid resource allocation model. Option contracts offer users the possibility to buy or sell Grid resources in the future for a strike price specified in a contract. By buying, borrowing and selling option contracts using a hedge strategy users can benefit from expected price changes. In this paper, we consider three hedge strategies: the butterfly spread which profits from small changes, the straddle which benefits from large price changes, and the call strategy which benefits from soaring prices. Using our model based on an abstract Grid architecture, we find that the use of hedge strategies augment the ratio of successfully finished jobs to failed jobs. We show that the degree of successfulness from hedge strategies changes when the number of contributed resources changes. By means of a model, we also show that the effects of the butterfly spread is mainly explained by the amount of contributed resources. The dynamics of the two other hedge strategies are best explained by observing the price behavior. We also find that by using hedge strategies the users can increase the probability that a job will finish before the deadline. We conclude that hedging using options is a promising approach to improve resource allocation in environments where resources are allocated by using a commodity market mechanism. 2013-06-11T04:34:31Z 2019-12-06T19:23:49Z 2013-06-11T04:34:31Z 2019-12-06T19:23:49Z 2009 2009 Journal Article Bossenbroek, A., Tirado-Ramos, A., & Sloot, P.M.A. (2009). Grid Resource Allocation by Means of Option Contracts. IEEE Systems Journal, 3(1), 49-64. https://hdl.handle.net/10356/95966 http://hdl.handle.net/10220/10175 10.1109/JSYST.2008.2011255 en IEEE systems journal © 2009 IEEE.
spellingShingle DRNTU::Engineering::Computer science and engineering
Bossenbroek, Anton
Tirado-Ramos, Alfredo
Sloot, Peter M. A.
Grid resource allocation by means of option contracts
title Grid resource allocation by means of option contracts
title_full Grid resource allocation by means of option contracts
title_fullStr Grid resource allocation by means of option contracts
title_full_unstemmed Grid resource allocation by means of option contracts
title_short Grid resource allocation by means of option contracts
title_sort grid resource allocation by means of option contracts
topic DRNTU::Engineering::Computer science and engineering
url https://hdl.handle.net/10356/95966
http://hdl.handle.net/10220/10175
work_keys_str_mv AT bossenbroekanton gridresourceallocationbymeansofoptioncontracts
AT tiradoramosalfredo gridresourceallocationbymeansofoptioncontracts
AT slootpeterma gridresourceallocationbymeansofoptioncontracts