End-to-End Quality of Service Management for Distributed Real-Time Embedded Applications

Manghwani, Prakash; Loyall, Joseph; Sharma, Prabha; Gillen, Matthew; Ye, J.

doi:10.1109/ipdps.2005.197

Cited by 17 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RELATED WORK Compared to related research presented in [19], the resource management framework used in MACRO -RACE -is an adaptive resource management framework that can be customized and configured using model-driven deployment and configuration tools such as the Platform-Independent Component Modeling Language (PICML) [20]. Moreover, RACE provides adaptive resource and QoS management capabilities more transparently and non-intrusively than Kokyu [21], QuO [22], and Qoskets [23], [24], [25]. In particular, it allocates CPU, memory, and networking resources to application components and tracks and manages utilization of various system resources, as well as application QoS.…”

Section: ) Summarymentioning

confidence: 99%

Intelligent Resource Management and Dynamic Adaptation in a Distributed Real-time and Embedded Sensor Web System

Kinnebrew

Otte

Shankaran

et al. 2009

2009 IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing

View full text Add to dashboard Cite

Abstract-Sensor webs are often composed of servers connected to distributed real-time embedded (DRE) systems that operate in open environments where operating conditions, workload, resource availability, and connectivity cannot be accurately characterized a priori. The South East Alaska MOnitoring Network for Science, Telecommunications, Education, and Research (SEAMONSTER) project exhibits many common system management and dynamic operation challenges for effective, autonomous system adaptation in a representative sensor web. These challenges cover both field operation (e.g., power management through system sleep/wake cycles and reaction to local environmental changes) and server operation (e.g., system adaptation for new/modified goals, resource allocation for a changing set of applications, and configuration changes for fluctuating workload). This paper presents the results of integrating and applying quality-of-service (QoS)-enabled component middleware, dynamic resource management, and autonomous agent technologies to address these challenges in SEAMONSTER.

show abstract

Section: ) Summarymentioning

confidence: 99%

Intelligent Resource Management and Dynamic Adaptation in a Distributed Real-time and Embedded Sensor Web System

Kinnebrew

Otte

Shankaran

et al. 2009

2009 IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing

View full text Add to dashboard Cite

show abstract

“…The design of the LRM is illustrated in Figure 9 and described in more detail in [15]. The LRM takes as inputs the resource allocations, minimums and maximums for each QoS attribute (e.g., size, rate, compression level, etc.…”

Section: The Prototype Local Resource Managermentioning

confidence: 99%

“…The others will be starved (i.e., receive no resource allocation). This metric looks for the feasible solution that runs the highest number of applications (whether that solution is the highest utility solution or not 15 ) and collect the number of applications running as a percentage of the number available to run. C. Highest percent of applications requesting the most-shared resource: In general, as more applications request a given resource, the contention for the resource increases.…”

Section: B Highest Percent Of Applications Not-starved In Any Feasibmentioning

confidence: 99%

“…For example, if a scenario has an allocation in which 500% (i.e., 5x of what's available) of a resource is requested and another scenario has no more than 95% of any resource requested, the first scenario indicates a more severe potential bottleneck than the second. 15 The utility of a solution is based on not only the number of applications that are running but also on the QoS levels at which the applications run, so a solution that runs fewer applications but at higher QoS levels could be of higher overall utility than one that runs more applications but at lower QoS levels.…”

Section: Highest Percent Of Resource Requested By Applications (Inmentioning

confidence: 99%

See 1 more Smart Citation

Building for the Future: China's Progress in Space Technology During the Tenth 5-Year Plan and the U.S. Response

Pollpeter¹

2008

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. SPONSOR/MONITOR'S ACRONYM(S) 9. SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES)AFRL/RISE 525 Brooks Rd Rome NY 13441-4505 SPONSORING/MONITORING AGENCY REPORT NUMBER AFRL-RI-RS-TR-2008-13 DISTRIBUTION AVAILABILITY STATEMENT APPROVED FOR PUBLIC RELEASE; DISTRIBUTION UNLIMITED. PA# WPAFB 08-0091 SUPPLEMENTARY NOTES ABSTRACTUnder the DynRIIC project, we produced results in two primary areas of QoS management for information spaces: architecture and algorithms. In the architecture area, we conceived, designed, and prototyped a multi-layered QoS management architecture suitable for information spaces. The multi-layered QoS management system works alongside the information manager in an information space and assigns QoS levels and resource allocations, produces and enforces QoS policies, and actuates QoS controls, including resource controls and information shaping.In the algorithms area, we developed several QoS allocation algorithms that work with the QoS management system, including resource and QoS allocation for single and multiple information spaces. We evaluated the algorithms indicating the relative merits and use of these algorithms in various scenarios, and prototyped some of the algorithms in the QoS decision maker components of the QoS management system. SUBJECT TERMSInfospace, infosphere, community of interest (COI), composable, dynamic, interoperability, information management SECURITY CLASSIFICATION OF:19a. NAME OF RESPONSIBLE PERSON

show abstract

“…Our QoS management capability extends existing IMS middleware to manage the production, delivery, and consumption of information that meets client needs within available resources, to mediate competing demands for resources, and to adjust to dynamic conditions. Our QoS Management System (QMS) middleware, illustrated in Figure 1, builds upon our previous work in QoS management for distributed object and component systems [7,15,16,17,18,19,28]. The QMS is multi-layered middleware, described in more detail in [14], with an information space QoS manager (ISQM) 1 that provides aggregate QoS allocations and policy for clients and operations throughout an information space.…”

Section: Introductionmentioning

confidence: 99%

QoS Allocation Algorithms for Publish-Subscribe Information Space Middleware

Loyall¹,

Gillen²,

Sharma³

2008

Middleware 2008

View full text Add to dashboard Cite

Abstract. Information spaces have emerged as a powerful concept for providing managed exchange of information between members of communities of interest (COIs), including information brokering and dissemination by publishsubscribe-query middleware. To support COIs with real-time or critical information exchange requirements, information spaces require quality of service (QoS) management algorithms that consider the complex system dynamics within information spaces, that allocate multiple resources, and that scale to information spaces of reasonable size. This paper presents two algorithms for multi-resource QoS allocation within information spaces. The first algorithm always provides an optimal allocation and includes optimizations that enable it to scale to information spaces of moderate size. The second algorithm is an approximation algorithm that provides near optimal solutions in most situations and scales to much larger information spaces. The paper also presents analyses and experimental results of the effectiveness and efficiency of the algorithms.

show abstract

End-to-End Quality of Service Management for Distributed Real-Time Embedded Applications

Cited by 17 publications

References 10 publications

Intelligent Resource Management and Dynamic Adaptation in a Distributed Real-time and Embedded Sensor Web System

Intelligent Resource Management and Dynamic Adaptation in a Distributed Real-time and Embedded Sensor Web System

Building for the Future: China's Progress in Space Technology During the Tenth 5-Year Plan and the U.S. Response

QoS Allocation Algorithms for Publish-Subscribe Information Space Middleware

Contact Info

Product

Resources

About