Cost-Driven Optimization of Cloud Resource Allocation for Elastic Processes

Schulte, Stefan; Schuller, Dieter; Hoenisch, Philipp; Lampe, Ulrich; Steinmetz, Ralf; Dustdar, Schahram

doi:10.29268/stcc.2013.1.2.1

Cited by 7 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply our prototype and testbed framework ViePEP as presented in [13], [16]. ViePEP is a BPMS and Cloud controller which acts as a middleware between process owners and the Cloud-based computational resources.…”

Section: Discussionmentioning

confidence: 99%

“…ViePEP is a research BPMS for elastic processes. In addition, we have provided optimization approaches for sequential elastic processes [15], [16]. However, more complex process patterns like XOR-blocks, AND-blocks or Repeat Loop orchestration components have not been covered yet, even though these process patterns are very common in real-world business processes [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Complex Elastic Processes

Hoenisch

Schuller

Schulte

et al. 2016

IEEE Trans. Serv. Comput.

Self Cite

View full text Add to dashboard Cite

Business Process Management is a matter of great importance in different industries and application areas. In many cases, it involves the execution of resource-intensive tasks in terms of computing power such as CPU and RAM. Due to the emergence of Cloud computing, theoretically unlimited resources can be used for the enactment of business processes. These Cloud resources render several challenges for Business Process Management Systems to ensure a predefined Quality of Service level during Cloud-based process enactment. Therefore, new solutions for process scheduling and resource allocation are required to tackle these challenges. Within this paper, we present a novel approach to schedule business processes and optimize the used Cloud-based computational resources in a cost-efficient way, thus realizing so-called elastic processes. For that, we specify the Service Instance Placement Problem, i.e., an optimization model which defines the setting of how service instances are scheduled among resources. Through extensive evaluations we show the benefits of our contributions and compare the novel approach against a baseline which follows an ad hoc approach.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimization of Complex Elastic Processes

Hoenisch

Schuller

Schulte

et al. 2016

IEEE Trans. Serv. Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other approaches disregard SLAs, and the optimization is either Pareto-optimal or based on weights or priorities indicating the importance of cost and turnaround time [44,45]. Recent investigations have considered SLAs in terms of deadlines for single tasks and single process instances, but only sequential processes are supported [46,47,48]. Notably, all these approaches to scheduling for elastic processes also take into account resource allocation.…”

Section: Scheduling For Elastic Processesmentioning

confidence: 99%

“…Action Engine The Vienna Platform for Elastic Processes (ViePEP) is an eBPMS implemented for usage with Openstack 13 [46,47,48]. Figure 5 provides an overview of the ViePEP architecture.…”

Section: The Vienna Platform For Elastic Processesmentioning

confidence: 99%

Elastic Business Process Management: State of the art and open challenges for BPM in the cloud

Schulte

Janiesch

Venugopal

et al. 2015

Future Generation Computer Systems

Self Cite

View full text Add to dashboard Cite

With the advent of cloud computing, organizations are nowadays able to react rapidly to changing demands for computational resources. Not only individual applications can be hosted on virtual cloud infrastructures, but also complete business processes. This allows the realization of so-called elastic processes, i.e., processes which are carried out using elastic cloud resources. Despite the manifold benefits of elastic processes, there is still a lack of solutions supporting them.In this paper, we identify the state of the art of elastic Business Process Management with a focus on infrastructural challenges. We conceptualize an architecture for an elastic Business Process Management System and discuss existing work on scheduling, resource allocation, monitoring, decentralized coordination, and state management for elastic processes. Furthermore, we present two representative elastic Business Process Management Systems which are intended to counter these challenges. Based on our findings, we identify open issues and outline possible research directions for the realization of elastic processes and elastic Business Process Management.

show abstract

“…Effective scheduling in cloud computing domain is a vital topic, as it influences dramatically the overall performance of the application as well as resource usage, which is clearly important since the pay-as-you-go model is an intrinsic feature of cloud computing [1]. However, research in the area of cloud scheduling is mainly focused on QoS [8], [9], [10] cost-awareness [11], [12], [13], [14], [15] or SLAconformance [12], [16], [17]. Each of these approaches operates on higher levels of business requirements and service quality, rather than effective resource usage, as the one presented in this paper.…”

Section: Image Processing Tasksmentioning

confidence: 99%

Profiling-Based Task Scheduling for Factory-Worker Applications in Infrastructure-as-a-Service Clouds

Zabolotnyi

Leitner

Dustdar

2014

2014 40th EUROMICRO Conference on Software Engineering and Advanced Applications

Self Cite

View full text Add to dashboard Cite

With the recent advances of cloud computing, effec-tive resource usage (e.g., CPU, memory or network) becomes an important question as application developers have to continuously pay for rented resources, even if they are not used effectively. In order to maintain required performance levels, it is currently common to reserve resources for peak resource usage or possible resource usage overlaps, if more than one task is executed on a host. While this is a reasonable approach for long-running applications or web servers, for some applications with disperse resource usage over time, this strategy causes significant over-provisioning and thus resource wastage and financial loss. In this paper we present a profiling-based task scheduling approach for factory-worker applications that schedules tasks within the defined resource limitations (e.g., existing machine memory size or network quota) and distributes the tasks in the cloud environment in order to use resources effectively. The evaluation of our approach approved the efficiency of the proposed algorithm and minimal performance overhead. In case of evaluated application, presented scheduling process leads up to 33% resource saving with only 1% of performance loss. Abstract-With the recent advances of cloud computing, effective resource usage (e.g., CPU, memory or network) becomes an important question as application developers have to continuously pay for rented resources, even if they are not used effectively. In order to maintain required performance levels, it is currently common to reserve resources for peak resource usage or possible resource usage overlaps, if more than one task is executed on a host. While this is a reasonable approach for long-running applications or web servers, for some applications with disperse resource usage over time, this strategy causes significant overprovisioning and thus resource wastage and financial loss. In this paper we present a profiling-based task scheduling approach for factory-worker applications that schedules tasks within the defined resource limitations (e.g., existing machine memory size or network quota) and distributes the tasks in the cloud environment in order to use resources effectively. The evaluation of our approach approved the efficiency of the proposed algorithm and minimal performance overhead. In case of the evaluated application, the presented scheduling process leads up to 33% resource savings with only 1% of performance loss.

show abstract

Cost-Driven Optimization of Cloud Resource Allocation for Elastic Processes

Cited by 7 publications

References 38 publications

Optimization of Complex Elastic Processes

Optimization of Complex Elastic Processes

Elastic Business Process Management: State of the art and open challenges for BPM in the cloud

Profiling-Based Task Scheduling for Factory-Worker Applications in Infrastructure-as-a-Service Clouds

Contact Info

Product

Resources

About