Scalable peer-to-peer process management - the OSIRIS approach

Schuler, Christoph; Weber, Robert A.; Schuldt, Heiko; Schek, Hans-Jörg

doi:10.1109/icws.2004.1314720

Cited by 49 publications

(40 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moving to a software based approach poses serious questions regarding accountability in these situations -currently associated with human administrators -and liability. Both of these topics are outside of the scope of this paper, but the preference in supervised management approaches lends evidence to the importance of these criteria [4,17,19,25,31,35]. It is possible that greater accuracy in heuristic approaches can alleviate these issues, however this is an area that is still to be explored.…”

Section: Introductionmentioning

confidence: 97%

Evaluating Unsupervised Fault Detection in Self-Healing Systems Using Stochastic Primitives

Schneider

Barker

Dobson

2015

EAI Endorsed Transactions on Self-Adaptive Systems

View full text Add to dashboard Cite

Autonomous fault detection represents one approach for reducing operational costs in large-scale computing environments. However, little empirical evidence exists regarding the implementation or comparison of such methodologies, or offers proof that such approaches reduce costs. This paper compares the effectiveness of several types of stochastic primitives using unsupervised learning to heuristically determine the root causes of faults. The results suggest that self-healing systems frameworks leveraging these techniques can reliably and autonomously determine the source of an anomaly within as little as five minutes. This finding lays the foundation for determining the potential these approaches have for reducing operational costs and ultimately concludes with new avenues for exploring anomaly prediction.

show abstract

Section: Introductionmentioning

confidence: 97%

Evaluating Unsupervised Fault Detection in Self-Healing Systems Using Stochastic Primitives

Schneider

Barker

Dobson

2015

EAI Endorsed Transactions on Self-Adaptive Systems

View full text Add to dashboard Cite

show abstract

“…Dynamic leader election in logical peer groups [13] adapts to dynamically arriving and departing providers but has been proposed only for sequential requests. OSIRIS [5] makes its pre-selection final only during execution, but requires a reliable and globally available synchronisation node to handle parallel service flows. In dynamic ad hoc networks such a node may not exist.…”

Section: Related Workmentioning

confidence: 99%

“…Research has led to composition solutions that bind a merge node early through a single entity [4], [5], [6]. Although this reduces the coordination effort, it also reduces the composite's flexibility to react to runtime changes.…”

Section: Introductionmentioning

confidence: 99%

Synchronising Service Compositions in Dynamic Ad Hoc Environments

Groba

Clarke

2012

2012 IEEE First International Conference on Mobile Services

View full text Add to dashboard Cite

Abstract-Service compositions in dynamic ad hoc environments face frequent changes in the network and service topology. Late service binding is a way to adapt to runtime changes but requires additional communication over error-prone and energy-constrained networks. In particular, synchronising parallel service flows relies on steady message exchange when mutually unknown service providers have to agree on a common merge node. Binding the merge node early through a single entity reduces the need for coordination. However, it compromises flexibility and may nonetheless increase communication as the decision entity has only partial view of the system. This paper proposes a multi-party late binding protocol as a solution for flexible, communication-aware service composition in dynamic ad hoc environments. The protocol integrates the discovery of unknown synchronisation partners with the exchange of binding suggestions to reduce communication. We embed this protocol in our model for opportunistic service composition and evaluate it against an early binding approach. Simulation results show that while being overall equally successful, late service binding outperforms early binding with respect to communication overhead and response time.

show abstract

“…In the Mobile Composition Style (P2PC-M) style [41,42], both the whole process specification and its related instances, which contain the state information of process execution, are dynamically brought to the next invoked service during run-time. [43] employed a combination of Static Composition Style to create a true P2P-based service process execution runtime environment and utilized the Mobil Composition Style to partition a process into a set of distributed execution units.…”

Section: Broker Stylesmentioning

confidence: 99%

Reference Architectural Styles for Service-Oriented Computing

Dillon

Chang

2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Architecting service-oriented systems is a complex design activity. It involves making trade-offs among a number of interdependent design decisions, which are drawn from a range of concerns by various software stakeholders. In order to achieve effective and efficient SOC design we believe a careful study of architectural styles that can form the reference architecture is important. Hence, this paper provides a study of architectural styles for the reference architecture of SOC-based software systems. We propose a classification scheme for the architecture styles. These architectural styles are extracted from existing research projects and industry practices based on our classification scheme. For all those identified styles, we present an evolution trend driven by engineering principles for Internet-scale systems. As a result, this paper moves the first step towards creating a Reference Architecture that can be utilised to provide sensible guidance on the design of Web services application architecture

show abstract

Scalable peer-to-peer process management - the OSIRIS approach

Abstract: Abstract

Cited by 49 publications

References 22 publications

Evaluating Unsupervised Fault Detection in Self-Healing Systems Using Stochastic Primitives

Evaluating Unsupervised Fault Detection in Self-Healing Systems Using Stochastic Primitives

Synchronising Service Compositions in Dynamic Ad Hoc Environments

Reference Architectural Styles for Service-Oriented Computing

Contact Info

Product

Resources

About