Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5698007
Francisco Heron de Carvalho Junior, Ricardo C. Corrêa
HPE is a platform of parallel components that complies to the # component model, whose components are intrinsically parallel. This paper describes the design of a new CCA framework based on HPE, aimed to reconcile distribution and parallelism of components. Besides exposing the essential differences between the two platforms, the new framework has a set of features that distinguishes it from other CCA frameworks.
{"title":"The design of a CCA framework with distribution, parallelism, and recursive composition","authors":"Francisco Heron de Carvalho Junior, Ricardo C. Corrêa","doi":"10.1109/GRID.2010.5698007","DOIUrl":"https://doi.org/10.1109/GRID.2010.5698007","url":null,"abstract":"HPE is a platform of parallel components that complies to the # component model, whose components are intrinsically parallel. This paper describes the design of a new CCA framework based on HPE, aimed to reconcile distribution and parallelism of components. Besides exposing the essential differences between the two platforms, the new framework has a set of features that distinguishes it from other CCA frameworks.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"41 1","pages":"339-348"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76225181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697949
David Chiu, G. Agrawal
With the promise on-demand compute/storage resources, many users are deploying data-intensive scientific applications onto Clouds. To accelerate these applications, the prospect of caching intermediate data using the elastic compute and storage framework has proved promising. To this end, we believe that an in-depth study of cache placement decisions over various Cloud storage options would be highly beneficial to a large class of users. While tangential analyses have been proposed, ours in contrast focuses on cost-performance tradeoffs of maintaining a data cache with various parameters of any Cloud application. We have compared several Amazon Web Service (AWS Cloud) resources as possible cache placements and found that application dependent attributes like unit-data size, total cache size, and persistence, have far reaching implications on the cost of cache sustenance. Moreover, while instance-based caches expectedly yield higher cost, the performance that they afford may outweigh lower cost options.
随着按需计算/存储资源的承诺，许多用户正在将数据密集型科学应用程序部署到云上。为了加速这些应用程序，使用弹性计算和存储框架缓存中间数据的前景被证明是有希望的。为此，我们相信对各种云存储选项的缓存放置决策进行深入研究将对大量用户非常有益。虽然已经提出了相关的分析，但我们的对比侧重于使用任何云应用程序的各种参数维护数据缓存的成本-性能权衡。我们比较了几种Amazon Web Service (AWS云)资源作为可能的缓存位置，发现应用程序相关的属性，如单元数据大小、总缓存大小和持久性，对缓存维持的成本有深远的影响。此外，尽管基于实例的缓存预期会产生更高的成本，但它们提供的性能可能会超过成本更低的选项。
{"title":"Evaluating caching and storage options on the Amazon Web Services Cloud","authors":"David Chiu, G. Agrawal","doi":"10.1109/GRID.2010.5697949","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697949","url":null,"abstract":"With the promise on-demand compute/storage resources, many users are deploying data-intensive scientific applications onto Clouds. To accelerate these applications, the prospect of caching intermediate data using the elastic compute and storage framework has proved promising. To this end, we believe that an in-depth study of cache placement decisions over various Cloud storage options would be highly beneficial to a large class of users. While tangential analyses have been proposed, ours in contrast focuses on cost-performance tradeoffs of maintaining a data cache with various parameters of any Cloud application. We have compared several Amazon Web Service (AWS Cloud) resources as possible cache placements and found that application dependent attributes like unit-data size, total cache size, and persistence, have far reaching implications on the cost of cache sustenance. Moreover, while instance-based caches expectedly yield higher cost, the performance that they afford may outweigh lower cost options.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"480 1","pages":"17-24"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76372782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697951
Yun Tian, P. J. Rhodes
Partial Replicas have been used to parallelize access to regions of large spatial data sets on geographically distributed machines, saving network bandwidth and improving data availability. In this paper, we present the Globus Toolkit R-tree, (GTR-tree) to efficiently select partial replicas using the Globus Toolkit Replica Location Service (RLS) middleware. First, the limitations inherent in the Globus RLS service for spatial data are analyzed, motivating the usefulness of the GTR-tree for solving the partial replica selection problem. We then describe our implementation of the R-tree data structure on top of an unmodified Globus RLS. The R-tree is an important data structure for spatial computation, and results in very significant performance gains. Our performance results and evaluation demonstrate enormous improvements for spatial replica selection over a plain RLS.
{"title":"The Globus Toolkit R-tree for partial spatial replica selection","authors":"Yun Tian, P. J. Rhodes","doi":"10.1109/GRID.2010.5697951","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697951","url":null,"abstract":"Partial Replicas have been used to parallelize access to regions of large spatial data sets on geographically distributed machines, saving network bandwidth and improving data availability. In this paper, we present the Globus Toolkit R-tree, (GTR-tree) to efficiently select partial replicas using the Globus Toolkit Replica Location Service (RLS) middleware. First, the limitations inherent in the Globus RLS service for spatial data are analyzed, motivating the usefulness of the GTR-tree for solving the partial replica selection problem. We then describe our implementation of the R-tree data structure on top of an unmodified Globus RLS. The R-tree is an important data structure for spatial computation, and results in very significant performance gains. Our performance results and evaluation demonstrate enormous improvements for spatial replica selection over a plain RLS.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"27 1","pages":"169-176"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84570154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697800
S. Itoh, Yuetsu Kodama, H. Shimizu, S. Sekiguchi, Hiroshi Nakamura, Naohiko Mori
Cooling power occupies large portion of power consumption in a Data Center. Improving efficiency of cooling is one of the most efficient ways to reduce power consumption in a Data Center. However it is not obvious how we can find out sufficient but not too much operation of cooling facility. In this paper, we measure temperature of racks, servers and processors and power consumption of IT equipment and CRAC under several different conditions. From these investigations, we find out the following. It is possible to reduce cooling power by leading cool air to rack directly. Monitoring processor temperature and controlling number of CRAC and volume of air are useful methods to adjust the capability of CRAC.
{"title":"Power consumption and efficiency of cooling in a Data Center","authors":"S. Itoh, Yuetsu Kodama, H. Shimizu, S. Sekiguchi, Hiroshi Nakamura, Naohiko Mori","doi":"10.1109/GRID.2010.5697800","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697800","url":null,"abstract":"Cooling power occupies large portion of power consumption in a Data Center. Improving efficiency of cooling is one of the most efficient ways to reduce power consumption in a Data Center. However it is not obvious how we can find out sufficient but not too much operation of cooling facility. In this paper, we measure temperature of racks, servers and processors and power consumption of IT equipment and CRAC under several different conditions. From these investigations, we find out the following. It is possible to reduce cooling power by leading cool air to rack directly. Monitoring processor temperature and controlling number of CRAC and volume of air are useful methods to adjust the capability of CRAC.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"59 1","pages":"305-312"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76947722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697946
S. Di, Cho-Li Wang
Fully decentralized resource allocation for P2P desktop Grid allows each participating node to act as both resource provider and requester. The system performance indicators (including throughput, makespan, etc) are easily degraded by the unbalanced load distribution, which is probably caused by the fast-changing states of heterogeneous resources due to arbitrary task submissions. Although the cooperative load rebalancing methods can mitigate the problem, they are likely to introduce the contention on under-utilized resources with growing task arrival rates, leading to the sub-optimal load balancing efficacy. Our focus is on how to optimize load balancing status by taking into account minimizing the conflict of autonomic task migration decisions in P2P desktop Grid. Our load rebalancing process is modeled as a set of independent stochastic Bernoulli trials by letting each heavily loaded node push its surplus loads to its surrounding lightly loaded nodes. We proved that the surplus load amount should be shifted based on a proper ratio by considering decision conflicts and designed a novel load balancing algorithm with provably small decision conflict probability. We derived an upper-bound for this probability, which will be reduced down to about 2% under our algorithm. Finally, we validated via simulation that the system performance can be significantly improved accordingly.
{"title":"Conflict-minimizing dynamic load balancing for P2P desktop Grid","authors":"S. Di, Cho-Li Wang","doi":"10.1109/GRID.2010.5697946","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697946","url":null,"abstract":"Fully decentralized resource allocation for P2P desktop Grid allows each participating node to act as both resource provider and requester. The system performance indicators (including throughput, makespan, etc) are easily degraded by the unbalanced load distribution, which is probably caused by the fast-changing states of heterogeneous resources due to arbitrary task submissions. Although the cooperative load rebalancing methods can mitigate the problem, they are likely to introduce the contention on under-utilized resources with growing task arrival rates, leading to the sub-optimal load balancing efficacy. Our focus is on how to optimize load balancing status by taking into account minimizing the conflict of autonomic task migration decisions in P2P desktop Grid. Our load rebalancing process is modeled as a set of independent stochastic Bernoulli trials by letting each heavily loaded node push its surplus loads to its surrounding lightly loaded nodes. We proved that the surplus load amount should be shifted based on a proper ratio by considering decision conflicts and designed a novel load balancing algorithm with provably small decision conflict probability. We derived an upper-bound for this probability, which will be reduced down to about 2% under our algorithm. Finally, we validated via simulation that the system performance can be significantly improved accordingly.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"30 1","pages":"137-144"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89860994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5698011
Steven R. Brandt, Gabrielle Allen
Software codes in scientific computing often implement their own little languages for expressing configuration data, interface definitions, and runtime parameters. Such languages are of particular importance for component-based frameworks. These languages can initially be somewhat ad-hoc and then expand organically.
{"title":"Piraha: A simplified grammar parser for component little languages","authors":"Steven R. Brandt, Gabrielle Allen","doi":"10.1109/GRID.2010.5698011","DOIUrl":"https://doi.org/10.1109/GRID.2010.5698011","url":null,"abstract":"Software codes in scientific computing often implement their own little languages for expressing configuration data, interface definitions, and runtime parameters. Such languages are of particular importance for component-based frameworks. These languages can initially be somewhat ad-hoc and then expand organically.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"60 1","pages":"379-382"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74286920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697972
G. Engelbrecht, J. Bisbal, S. Benkner, Alejandro F Frangi
Researchers in data intensive domains, like the Virtual Physiological Human initiative (VPH-I), are commonly overwhelmed with the vast and increasing amount of data available. Advanced studies in biomedicine and other domains often require a considerable amount of effort to achieve data access to a critical mass of relevant data to analyze the problem at hand. We aim to improve this situation and propose a novel application of Quality of Service (QoS) mechanisms for data services. This enables scientists to obtain exactly the data they require, rather than being spoilt for choice which data source might comprise suitable data. The proposed QoS support includes a negotiation model based on service level agreements (SLAs), which in turn comprises data-related service level objectives (SLOs) to express the required guarantees about the quantity or quality of data. Moreover a corresponding QoS management model is presented which resolves the complex process of the SLA generation within data access and data mediation services. The benefits of this approach are materialized in the context of the @neurIST data environment and an initial experimental evaluation demonstrates promising performance improvements in a real world scenario.
数据密集型领域的研究人员，如虚拟生理人计划(Virtual Physiological Human initiative, VPH-I)，通常被大量不断增加的可用数据所淹没。生物医学和其他领域的高级研究往往需要付出相当大的努力，才能获得关键数量的相关数据，以分析手头的问题。我们的目标是改善这种情况，并提出了一种新的数据服务质量(QoS)机制的应用。这使科学家能够准确地获得他们需要的数据，而不是被选择哪个数据源可能包含合适的数据所困扰。建议的QoS支持包括一个基于服务水平协议(sla)的协商模型，该模型又由与数据相关的服务水平目标(slo)组成，以表示对数据数量或质量的所需保证。提出了相应的QoS管理模型，解决了数据访问和数据中介服务中SLA生成的复杂过程。这种方法的好处在@neurIST数据环境中得到了体现，初步的实验评估表明，在现实世界的场景中，这种方法的性能有了很大的提高。
{"title":"Towards negotiable SLA-based QoS support for biomedical data services","authors":"G. Engelbrecht, J. Bisbal, S. Benkner, Alejandro F Frangi","doi":"10.1109/GRID.2010.5697972","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697972","url":null,"abstract":"Researchers in data intensive domains, like the Virtual Physiological Human initiative (VPH-I), are commonly overwhelmed with the vast and increasing amount of data available. Advanced studies in biomedicine and other domains often require a considerable amount of effort to achieve data access to a critical mass of relevant data to analyze the problem at hand. We aim to improve this situation and propose a novel application of Quality of Service (QoS) mechanisms for data services. This enables scientists to obtain exactly the data they require, rather than being spoilt for choice which data source might comprise suitable data. The proposed QoS support includes a negotiation model based on service level agreements (SLAs), which in turn comprises data-related service level objectives (SLOs) to express the required guarantees about the quantity or quality of data. Moreover a corresponding QoS management model is presented which resolves the complex process of the SLA generation within data access and data mediation services. The benefits of this approach are materialized in the context of the @neurIST data environment and an initial experimental evaluation demonstrates promising performance improvements in a real world scenario.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"14 1","pages":"259-265"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84990968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697977
Peter Chronz, P. Wieder
Service level agreements are an intrinsic part of service level management frameworks. They are electronic contracts, or part of a contract, and capture quality-of-service guarantees, responsibilities and constraints related to the provision and consumption of services. In the area of distributed systems a handful of service level agreement specifications exist, designed to support the automated management of service-related agreements. Each of these specifications has a different focus and targets a different group of usage scenarios and stakeholders. In this paper, we show, based on the example of the WS-Agreement specification, how to make use of SLA@SOI's service level agreement model SLA* to map between different service level agreement representations and thus be able to integrate a variety of different specifications into one service-oriented infrastructure.
{"title":"Integrating WS-Agreement with a framework for service-oriented infrastructures","authors":"Peter Chronz, P. Wieder","doi":"10.1109/GRID.2010.5697977","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697977","url":null,"abstract":"Service level agreements are an intrinsic part of service level management frameworks. They are electronic contracts, or part of a contract, and capture quality-of-service guarantees, responsibilities and constraints related to the provision and consumption of services. In the area of distributed systems a handful of service level agreement specifications exist, designed to support the automated management of service-related agreements. Each of these specifications has a different focus and targets a different group of usage scenarios and stakeholders. In this paper, we show, based on the example of the WS-Agreement specification, how to make use of SLA@SOI's service level agreement model SLA* to map between different service level agreement representations and thus be able to integrate a variety of different specifications into one service-oriented infrastructure.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"75 1","pages":"225-232"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79946951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5697960
N. Yigitbasi, D. Epema
It is not uncommon that grid users observe highly variable performance when they submit similar workloads at different times. From the users' point of view, such inconsistent performance is undesirable, and it leads to user dissatisfaction and confusion. We tackle this performance inconsistency problem using overprovisioning which is increasing the system capacity by a factor that we call the overprovisioning factor (к). Although overprovisioning is not cost effective, its simplicity makes it the preferred method for providing performance guarantees. Hence in this work, we present a realistic investigation of overprovisioning in grids. Towards this end, first we present a performance and cost evaluation of static and dynamic overprovisioning strategies. We find that the dynamic overprovisioning strategy, for which we use computing clouds, provides better consistency with lower costs compared to static strategies, and overprovisioning beyond a certain value of к (in our case к=2.5) incurs significant costs without significant consistency improvements. Then, we design and evaluate a feedback-controlled system to dynamically determine к to give performance guarantees to grid users. We show that our system determines к dynamically and provides significant improvements over the initial system, as high as 67%, in the number of jobs that meet the performance requirements.
{"title":"Static and dynamic overprovisioning strategies for performance consistency in grids","authors":"N. Yigitbasi, D. Epema","doi":"10.1109/GRID.2010.5697960","DOIUrl":"https://doi.org/10.1109/GRID.2010.5697960","url":null,"abstract":"It is not uncommon that grid users observe highly variable performance when they submit similar workloads at different times. From the users' point of view, such inconsistent performance is undesirable, and it leads to user dissatisfaction and confusion. We tackle this performance inconsistency problem using overprovisioning which is increasing the system capacity by a factor that we call the overprovisioning factor (к). Although overprovisioning is not cost effective, its simplicity makes it the preferred method for providing performance guarantees. Hence in this work, we present a realistic investigation of overprovisioning in grids. Towards this end, first we present a performance and cost evaluation of static and dynamic overprovisioning strategies. We find that the dynamic overprovisioning strategy, for which we use computing clouds, provides better consistency with lower costs compared to static strategies, and overprovisioning beyond a certain value of к (in our case к=2.5) incurs significant costs without significant consistency improvements. Then, we design and evaluate a feedback-controlled system to dynamically determine к to give performance guarantees to grid users. We show that our system determines к dynamically and provides significant improvements over the initial system, as high as 67%, in the number of jobs that meet the performance requirements.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"46 1","pages":"145-152"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78710283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/GRID.2010.5698019
Evangelos Pournaras, M. Warnier, F. Brazier
Self-management of tree overlay networks for distributed applications is the challenge this paper addresses. Eight local adaptation strategies are introduced based on which autonomous self-organized agents establish connections that build and maintain a tree topology. Quantitative and qualitative experimental evaluation illustrates and compares the effects of adaptation strategies in the resulting tree topologies according to a defined self-organization goal and four metrics: connectedness, connectivity, instability and robustness. This paper concludes that further applicability of adaptation strategies in other self-organization goals and topologies is promising.
{"title":"Adaptation strategies for self-management of tree overlay networks","authors":"Evangelos Pournaras, M. Warnier, F. Brazier","doi":"10.1109/GRID.2010.5698019","DOIUrl":"https://doi.org/10.1109/GRID.2010.5698019","url":null,"abstract":"Self-management of tree overlay networks for distributed applications is the challenge this paper addresses. Eight local adaptation strategies are introduced based on which autonomous self-organized agents establish connections that build and maintain a tree topology. Quantitative and qualitative experimental evaluation illustrates and compares the effects of adaptation strategies in the resulting tree topologies according to a defined self-organization goal and four metrics: connectedness, connectivity, instability and robustness. This paper concludes that further applicability of adaptation strategies in other self-organization goals and topologies is promising.","PeriodicalId":6372,"journal":{"name":"2010 11th IEEE/ACM International Conference on Grid Computing","volume":"46 1","pages":"401-409"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90059821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：