Xiao Liu PhD Thesis.pdf - Faculty of Information and Communication ...

(deadlines) and local temporal constraints for workflow segments and/or individual
activities (milestones) are required to be set as temporal QoS constraints in cloud
workflow specifications. The problem for the conventional QoS constraint setting
strategies lies in three aspects: first, estimated workflow activity durations (based on
user experiences or simple statistics) are often inaccurate in cloud workflow system
environments; second, these constrains are not well balanced between user
requirements and system performance; third, the time overheads of the setting
process is non-trivial, especially for large numbers of local temporal constraints. To
address the above issues, a statistical time-series pattern based forecasting strategy is
first investigated to predict the duration intervals of cloud workflow activities.
Afterwards, based on the weighted joint normal distribution of workflow activity
durations, a probabilistic setting strategy is applied to assign coarse-grained
temporal constraints through a negotiation process between service users and service
providers, and then the fine-grained temporal constraints can be propagated along
scientific cloud workflows in an automatic fashion, i.e. with very small time
overheads.
At scientific cloud workflow runtime, in Component 2, the state of cloud
workflow execution towards specific temporal constraints, i.e. temporal consistency,
is monitored constantly by the checkpoint selection and temporal verification
component. The two major limitations of conventional checkpoint selection and
temporal verification are as follows: first, the selection of multiple types of
checkpoints and the verification of multiple types of temporal consistency states
incur huge cost but most of them are actually unnecessary; second, though the
violations of multiple temporal consistency states can be verified, there is no clear
indication for the level of temporal violations, i.e. it does not support the quantitative
measurement of temporal violations. To address the above issues, with our
probability based temporal consistency model, the probability range for statistically
recoverable and non-recoverable temporal violations are defined in the first place.
Afterwards, we monitor cloud workflow executions through the following two steps:
first, a minimum probability time redundancy based temporal checkpoint selection
strategy determines the activity points where potential temporal violations take place;
second, probability temporal consistency based temporal verification is conducted
on a checkpoint to check the current temporal consistency state and the types of
8