Choice of Aggregation Groups for Layered Performance Model Simplification

Islam, Farhana; Petriu, Dorina C.; Woodside, Murray

doi:10.1145/3184407.3184411

Cited by 1 publication

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Dependency-Group Aggregation [21], in which some tasks are preserved and groups of other tasks are identified according to their relationships to the preserved tasks. The concept is introduced in this chapter, but detailed consideration is deferred to Chapters 4 and 5.…”

Section: Discussionmentioning

confidence: 99%

“…For queueing resources there is a well-established expectation that overall queueing delays are reduced when resources are aggregated together, which is well-known, for example, if a set of identical servers with separate queues are merged into a multiserver [21]. However, there are no comparable exact results available for layered servers in a LQN.…”

Section: Expectations Regarding Aggregationmentioning

confidence: 99%

“…In this section, a much larger and more complex case is included here to see the scalability of the simplification process in terms of model size. Figure 6.11 shows a model called "case-50" with 50 tasks and 50 processors that was generated randomly [21]. In this example, we preserve one resource or more at a time to show how amount of preservation effects the model's accuracy.…”

Section: Scalabilitymentioning

confidence: 99%

See 2 more Smart Citations

Simplifying Layered Queueing Network Models

Islam¹

Self Cite

View full text Add to dashboard Cite

The amount of detail to include in a performance model is usually regarded as a judgment to be made by an expert modeler and the question "how much detail is necessary?" is seldom asked and is difficult to answer. However, if a simpler model gives essentially the same performance predictions, it may be more useful than a detailed model. It may solve more quickly, for instance, and may be easier to understand. Or a model for a complex subsystem such as a database server may be usefully simplified so it can be included in larger system models. This research proposes an aggregation process for layered queuing models that reduces the number of queues (called tasks and hosts/processors, in layered models) while preserving the total execution demand and the bottleneck characteristics (the highest saturated resource(s)) of the detailed model. This thesis demonstrates how the simplification process can greatly reduce the number of tasks and processors with a very small relative error. The application of proposed simplification process is applied on a number of case studies. A Java application called "LQN model simplifier" was built that takes an LQN model as input and generates a series of simplified models after applying simplification operations to the original model.iii

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Expectations Regarding Aggregationmentioning

confidence: 99%

Section: Scalabilitymentioning

confidence: 99%

See 1 more Smart Citation