Preventing Temporal Violations in Scientific Workflows: Where and How

Abstract

Abstract-Due to the dynamic nature of the underlying high-performance infrastructures for scientific workflows such as grid and cloud computing, failures of timely completion of important scientific activities, namely, temporal violations, often take place. Unlike conventional exception handling on functional failures, nonfunctional QoS failures such as temporal violations cannot be passively recovered. They need to be proactively prevented through dynamically monitoring and adjusting the temporal consistency states of scientific workflows at runtime. However, current research on workflow temporal verification mainly focuses on runtime monitoring, while the adjusting strategy for temporal consistency states, namely, temporal adjustment, has so far not been thoroughly investigated. For this issue, two fundamental problems of temporal adjustment, namely, where and how, are systematically analyzed and addressed in this paper. Specifically, a novel minimum probability time redundancy-based necessary and sufficient adjustment point selection strategy is proposed to address the problem of where and an innovative genetic-algorithm-based effective and efficient local rescheduling strategy is proposed to tackle the problem of how. The results of large-scale simulation experiments with generic workflows and specific real-world applications demonstrate that our temporal adjustment strategy can remarkably prevent the violations of both local and global temporal constraints in scientific workflows.

<italic>EnReal</italic>: An Energy-Aware Resource Allocation Method for Scientific Workflow Executions in Cloud Environment

“…We investigate the astrophysics scientific workflows running in the Swinburne high-performance supercomputing facility from Swinburne Astrophysics group (http://astronomy.swinburne.edu.au) [4]. And the datasets used in our experiments are all generated according to the parameters of such scientific workflow.…”

“…With the elasticity of cloud infrastructures, an increasing number of customers choose to deploy applications (e.g., business and scientific applications) in cloud platforms [3]. A large number of scientific applications can be modelled by workflows in many domains, including bioinformatics, astronomy, astrophysics, and high-energy physics [4], [5], to name a few.…”

Resource Management for Business Process Scheduling in the Presence of Availability Constraints

“…Business process and workflow scheduling are known as classical NP-complete problems [Yu and Buyya 2006;Fechner et al 2008;Liu et al 2011]. When resource availability constraints need to be additionally considered, finding the optimal solution to the problem defined above is even computationally harder.…”

“…The problem of mapping tasks onto given resources is known to be NP-complete Buyya 2005, 2006;Fechner et al 2008;Liu et al 2011]. Due to its complexity, lots of heuristic methods have been proposed to address some classical problems, such as job shop scheduling and queuing mechanisms for operating system.…”

Process-Aware Systems

“…However, as stated in [5], it argues that the conventional consistency condition is too restrictive and covers several different states which should be handled differently for the purpose of cost effectiveness. The runtime version of the probability based temporal consistency model is proposed in [33] to facilitate runtime temporal checkpoint selection and verification. However, multiple-state based temporal consistency model cannot support quantitative measurement of temporal consistency states and lacks the ability to support statistical analysis.…”