What question did this study set out to answer?

To develop heuristic algorithms for scheduling tasks based on time-decaying user utility and evaluate them within a market-based resource allocation framework.

June 4, 2004

Balancing risk and reward in a market-based task service

View Full Paper

Ask AI

Bookmark

To develop heuristic algorithms for scheduling tasks based on time-decaying user utility and evaluate them within a market-based resource allocation framework.
Formulated a user value model in which task yield decays linearly as waiting time increases.
Constructed scheduling heuristics inspired by financial investment principles to balance potential yield against future cost risks under uncertain job arrivals.
Evaluated the heuristics within an admission control and bidding framework across multi-site computational grid environments.
Demonstrated that incorporating opportunity costs improves overall yield when allocating shared computational resources.
Showed that risk-aware heuristics mitigate performance losses caused by uncertainty in the future job mix during admission control.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Algorithmic study demonstrates effective risk-reward scheduling in market-based grid computing, highlighting the role of opportunity costs under future job uncertainty.

Cite This Study

Irwin et al. (2004) studied this question.

synapsesocial.com/papers/6a7054ee660549caf2c4e889 https://doi.org/10.1109/hpdc.2004.5

View Full Paper

Ask AI

Bookmark

Implication

Algorithmic study demonstrates effective risk-reward scheduling in market-based grid computing, highlighting the role of opportunity costs under future job uncertainty.

Balancing risk and reward in a market-based task service

Key Points

Discussion

Implication

Cite This Study

Balancing risk and reward in a market-based task service

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider