On large computational grids, performance is one of the main problems that has to be addressed but another important issue is the underlying interconnection network that has to be reliable in order to ensure the nodes' intercommunication and the migration of the appropriate load from one node to others. Reliability and performance are both influenced by the topology type of the underlying network. Fully connected networks for example provide better performance, the number of links however increases the cost of the system. In this paper, we considered these three factors, namely performance, reliability and cost, simulating performance for different network topologies and different reliability thresholds. The simulation results demonstrate that 1) regular topologies behave better than irregular topologies, and 2) the topology of the network is more influential to performance than the actual number of physical links.
{"title":"Quality Interplay in Regular vs. Irregular Grid Topologies","authors":"I. Savvas, D. Tselios, George Kakarontzas","doi":"10.1109/WETICE.2008.23","DOIUrl":"https://doi.org/10.1109/WETICE.2008.23","url":null,"abstract":"On large computational grids, performance is one of the main problems that has to be addressed but another important issue is the underlying interconnection network that has to be reliable in order to ensure the nodes' intercommunication and the migration of the appropriate load from one node to others. Reliability and performance are both influenced by the topology type of the underlying network. Fully connected networks for example provide better performance, the number of links however increases the cost of the system. In this paper, we considered these three factors, namely performance, reliability and cost, simulating performance for different network topologies and different reliability thresholds. The simulation results demonstrate that 1) regular topologies behave better than irregular topologies, and 2) the topology of the network is more influential to performance than the actual number of physical links.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"94 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120904051","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}
Lluis Pamies-Juarez, P. López, Marc Sánchez Artigas
Symmetric exchanges has been used for peer-to-peer resource allocation systems to maintain fairness among the number of resources that each peer contributes to the network. The problem of these systems is that they do not take into account resource's quality in their fairness measure. Resource quality is an important factor to obtain fair allocations. When this factor is not kept in mind, high quality peers can obtain low quality resources, bringing the system to an unfair state. In this work we present a generic resource allocation system that improves the system fairness in the presence of quality heterogeneity. With low network overhead, our system provide near complete allocation while maintaining network stability and fairness.
{"title":"Reciprocal Exchange for Resource Allocation in Peer-to-Peer Networks","authors":"Lluis Pamies-Juarez, P. López, Marc Sánchez Artigas","doi":"10.1109/WETICE.2008.11","DOIUrl":"https://doi.org/10.1109/WETICE.2008.11","url":null,"abstract":"Symmetric exchanges has been used for peer-to-peer resource allocation systems to maintain fairness among the number of resources that each peer contributes to the network. The problem of these systems is that they do not take into account resource's quality in their fairness measure. Resource quality is an important factor to obtain fair allocations. When this factor is not kept in mind, high quality peers can obtain low quality resources, bringing the system to an unfair state. In this work we present a generic resource allocation system that improves the system fairness in the presence of quality heterogeneity. With low network overhead, our system provide near complete allocation while maintaining network stability and fairness.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122932770","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}
A crucial aspect of managing data-centric and pervasive networks is the design of proper self-organizing data-distribution approaches, including aggregation, collection, diffusion, and so on.In this paper we introduce the collective sort problem for network environments that aims at collecting and segregating data by similarity. Data is collected and segregated in localized areas of the network selected by an emergent process.A solution to the problem is analyzed for a coordination scenario featuring a grid-like distributed set of Linda tuple spaces and a set of sorting agents executing a probabilistic protocol resembling brood collection in ant colonies.Based on simulation, we show how patterns of data collection emerge in spite of the very basic observation and computation abilities of sorting agents.
{"title":"Collective Sort and Emergent Patterns of Tuple Distribution in Grid-Like Networks","authors":"Matteo Casadei, Mirko Viroli, Marco Santarelli","doi":"10.1109/WETICE.2008.21","DOIUrl":"https://doi.org/10.1109/WETICE.2008.21","url":null,"abstract":"A crucial aspect of managing data-centric and pervasive networks is the design of proper self-organizing data-distribution approaches, including aggregation, collection, diffusion, and so on.In this paper we introduce the collective sort problem for network environments that aims at collecting and segregating data by similarity. Data is collected and segregated in localized areas of the network selected by an emergent process.A solution to the problem is analyzed for a coordination scenario featuring a grid-like distributed set of Linda tuple spaces and a set of sorting agents executing a probabilistic protocol resembling brood collection in ant colonies.Based on simulation, we show how patterns of data collection emerge in spite of the very basic observation and computation abilities of sorting agents.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129749322","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}
Computational grids have become an imperative rising platform for high-performance computing. However, the grid and the grid applications development are still far from being affirmed, which is mainly due to the undeveloped grid-enabled computing environments. For that reason in this paper we propose a toolbox, called GrIPLab 1.0 (Grid Image Processing Laboratory), that aims at providing high performance image-processing platform in a grid computing environment by using the GLite middleware developed in the EGEE project. GrIPLab 1.0 is a combination of vision algorithms (the most common and some novel approaches) on which complex distributed vision applications can be modeled as a simple sequence of choices in a user friendly interface. Therefore, the main advantage of the presented dynamic grid toolbox is that provides a novel and comfortable access for scientific software developers and users without prior knowledge of grid technologies or even the underlying architecture. In this paper, we discuss the infrastructure that provides flexible and useful mechanism to achieve series image processing operations and we analyze the advantages of using such a system.
{"title":"GRIPLAB 1.0: Grid Image Processing Laboratory for Distributed Machine Vision Applications","authors":"Antonino Crisafi, D. Giordano, C. Spampinato","doi":"10.1109/WETICE.2008.44","DOIUrl":"https://doi.org/10.1109/WETICE.2008.44","url":null,"abstract":"Computational grids have become an imperative rising platform for high-performance computing. However, the grid and the grid applications development are still far from being affirmed, which is mainly due to the undeveloped grid-enabled computing environments. For that reason in this paper we propose a toolbox, called GrIPLab 1.0 (Grid Image Processing Laboratory), that aims at providing high performance image-processing platform in a grid computing environment by using the GLite middleware developed in the EGEE project. GrIPLab 1.0 is a combination of vision algorithms (the most common and some novel approaches) on which complex distributed vision applications can be modeled as a simple sequence of choices in a user friendly interface. Therefore, the main advantage of the presented dynamic grid toolbox is that provides a novel and comfortable access for scientific software developers and users without prior knowledge of grid technologies or even the underlying architecture. In this paper, we discuss the infrastructure that provides flexible and useful mechanism to achieve series image processing operations and we analyze the advantages of using such a system.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114218707","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}
Xavier León, Xavier Vilajosana, R. Brunner, R. Krishnaswamy, L. Navarro, Felix Freitag, J. Marquès
Large scale systems such as the grid need scalable and efficient resource allocation mechanisms to fulfil the requirements of its participants and applications while the whole system is regulated to work efficiently. Economics inspired models have shown ability to handle efficiently the allocation of resources and services, scaling up well as they are decentralized. Our model considers the arbitration of decisions at the local scope and short term, the regulation of the system at global scope, and the sharing of information between global and local environments. This paper presents a scalable model and evaluates by simulation a system where global market information circulates in aggregated and scalable form, the rate of demand by participants is globally regulated by a currency mechanism, preference is regulated by a reputation mechanism, and local regulation among competing participants is resolved by auction mechanisms. The paper shows how scalable systems benefit from distributed marketplaces supporting global information flow to regulate and optimize local and global behavior.
{"title":"Information and Regulation in Decentralized Marketplaces for P2P-Grids","authors":"Xavier León, Xavier Vilajosana, R. Brunner, R. Krishnaswamy, L. Navarro, Felix Freitag, J. Marquès","doi":"10.1109/WETICE.2008.12","DOIUrl":"https://doi.org/10.1109/WETICE.2008.12","url":null,"abstract":"Large scale systems such as the grid need scalable and efficient resource allocation mechanisms to fulfil the requirements of its participants and applications while the whole system is regulated to work efficiently. Economics inspired models have shown ability to handle efficiently the allocation of resources and services, scaling up well as they are decentralized. Our model considers the arbitration of decisions at the local scope and short term, the regulation of the system at global scope, and the sharing of information between global and local environments. This paper presents a scalable model and evaluates by simulation a system where global market information circulates in aggregated and scalable form, the rate of demand by participants is globally regulated by a currency mechanism, preference is regulated by a reputation mechanism, and local regulation among competing participants is resolved by auction mechanisms. The paper shows how scalable systems benefit from distributed marketplaces supporting global information flow to regulate and optimize local and global behavior.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124759035","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}
In the last few years grid computing is evolving into a business-innovating technology that is driving commercial adoption. Such a new scenario calls for powerful strategies able to guarantee stringent QoS requirements in order to meet SLAs between customers and provider. For this reason, it is necessary to analyze and predict performance with respect to different load conditions or management strategies. In this paper, we present a methodology to analyze performance in gLite Grids through the use of Generalized Stochastic Petri Nets (GSPNs). We will present a cluster-level model of a typical gLite site taking into account the coexistence between normal and MPI-based jobs.We will investigate the influence of different strategies (e.g., scheduling) on the performance of the whole site highlighting aspects related to both customer and provider point-of-views.
{"title":"A GSPN Model to Analyze Performance Parameters in gLite Grids","authors":"Dario Bruneo, M. Scarpa, A. Puliafito","doi":"10.1109/WETICE.2008.39","DOIUrl":"https://doi.org/10.1109/WETICE.2008.39","url":null,"abstract":"In the last few years grid computing is evolving into a business-innovating technology that is driving commercial adoption. Such a new scenario calls for powerful strategies able to guarantee stringent QoS requirements in order to meet SLAs between customers and provider. For this reason, it is necessary to analyze and predict performance with respect to different load conditions or management strategies. In this paper, we present a methodology to analyze performance in gLite Grids through the use of Generalized Stochastic Petri Nets (GSPNs). We will present a cluster-level model of a typical gLite site taking into account the coexistence between normal and MPI-based jobs.We will investigate the influence of different strategies (e.g., scheduling) on the performance of the whole site highlighting aspects related to both customer and provider point-of-views.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"323 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122628436","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}
The paradigm of service-oriented computing (SOC) introduces emerging concepts for distributed- and e-business processing enabling the sharing and reuse of service-centric capabilities. The underpinning for an organization's use of SOC techniques is the ability to discover and compose Web services. Leading industry approaches rely heavily on syntactical approaches for managing service-based business processes. As such, these approaches are limited since the true functionality of ambiguous capabilities (i.e. web service operations) cannot be inferred. We introduce approaches that disambiguate services by interleaving process-based control with semantic annotations. In this paper, we introduce a generalized architecture where intelligent software agents control process-oriented composition that leverages the descriptiveness of semantics. An outcome of this work is the specification of a multiple agent system where a query agent interacts with multiple repository agents to perform business-oriented service composition.
{"title":"An Agent-Based Approach for Composition of Semantic Web Services","authors":"A. Bansal, S. Kona, M. Brian Blake, G. Gupta","doi":"10.1109/WETICE.2008.19","DOIUrl":"https://doi.org/10.1109/WETICE.2008.19","url":null,"abstract":"The paradigm of service-oriented computing (SOC) introduces emerging concepts for distributed- and e-business processing enabling the sharing and reuse of service-centric capabilities. The underpinning for an organization's use of SOC techniques is the ability to discover and compose Web services. Leading industry approaches rely heavily on syntactical approaches for managing service-based business processes. As such, these approaches are limited since the true functionality of ambiguous capabilities (i.e. web service operations) cannot be inferred. We introduce approaches that disambiguate services by interleaving process-based control with semantic annotations. In this paper, we introduce a generalized architecture where intelligent software agents control process-oriented composition that leverages the descriptiveness of semantics. An outcome of this work is the specification of a multiple agent system where a query agent interacts with multiple repository agents to perform business-oriented service composition.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116087693","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}
M. Leoni, Andrea Marrella, Massimo Mecella, S. Valentini, Sebastian Sardiña
Process management systems (PMSs) can be used not only in classical business scenarios, but also in highly dynamic and uncertain environments, for example, in supporting operators during emergency management for coordinating their activities. In such challenging situations, processes should be adapted in order to cope with anomalous situations, including connection anomalies and task faults. This requires the provision of intelligent support for the planning and enactment of complex processes, that allows to capture the knowledge about the dynamic context of a process. In this paper, we show how this knowledge, together with information about the capabilities of the available actors, may be specified and used to not only to support the selection of an appropriate set of agents to fill the roles in a given task, but also to solve the problem of adaptivity. The paper describes a first prototype of a PMS based on well-known artificial intelligence techniques and how it can be extended to tackle adaptation.
{"title":"Coordinating Mobile Actors in Pervasive and Mobile Scenarios: An AI-Based Approach","authors":"M. Leoni, Andrea Marrella, Massimo Mecella, S. Valentini, Sebastian Sardiña","doi":"10.1109/WETICE.2008.30","DOIUrl":"https://doi.org/10.1109/WETICE.2008.30","url":null,"abstract":"Process management systems (PMSs) can be used not only in classical business scenarios, but also in highly dynamic and uncertain environments, for example, in supporting operators during emergency management for coordinating their activities. In such challenging situations, processes should be adapted in order to cope with anomalous situations, including connection anomalies and task faults. This requires the provision of intelligent support for the planning and enactment of complex processes, that allows to capture the knowledge about the dynamic context of a process. In this paper, we show how this knowledge, together with information about the capabilities of the available actors, may be specified and used to not only to support the selection of an appropriate set of agents to fill the roles in a given task, but also to solve the problem of adaptivity. The paper describes a first prototype of a PMS based on well-known artificial intelligence techniques and how it can be extended to tackle adaptation.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128685972","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}
The sixth "Agent-based Computing for Enterprise Collaboration" workshop at WETICE 2008 focused on the areas of: agent-based semantic composition of Web services; agent-oriented software engineering methodologies and tools; and large scale multi-agent systems. The intention of this workshop was to bring together researches in the fields of software agents as they relate to the context of enterprise collaboration. This report briefly discusses the content of the papers presented at the workshop by respective authors. Moreover, the report ends with a summary of the main issues and challenges touched during the concluding discussion session.
{"title":"Agent-Based Computing for Enterprise Collaboration Synergies of Agents and Services","authors":"F. Bergenti, M. Blake, Giacomo Cabri","doi":"10.1109/WETICE.2008.67","DOIUrl":"https://doi.org/10.1109/WETICE.2008.67","url":null,"abstract":"The sixth \"Agent-based Computing for Enterprise Collaboration\" workshop at WETICE 2008 focused on the areas of: agent-based semantic composition of Web services; agent-oriented software engineering methodologies and tools; and large scale multi-agent systems. The intention of this workshop was to bring together researches in the fields of software agents as they relate to the context of enterprise collaboration. This report briefly discusses the content of the papers presented at the workshop by respective authors. Moreover, the report ends with a summary of the main issues and challenges touched during the concluding discussion session.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227718","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}
The challenge of intelligence in pervasive computing scenarios is a difficult and fascinating one. While MASs (Multi-Agent Systems) provide for a principled approach to pervasive intelligent systems, large scale and physical distribution call for expressive coordination models and technologies promoting distribution of intelligence. Also, the issue of situatedness of intelligence mandates effective agent models and technologies enabling the engineering of agent-based systems immersed within dynamic and articulated pervasive computing environments. Moving MAS coordination toward situatedness - from both a theoretical and a technological viewpoint-is then a fundamental step toward intelligent MAS in pervasive computing scenarios. In this paper we show how a language for MAS coordination - ReSpecT - can be extended according to a meta-model which provides a simple and solid grounding for MAS situatedness - A&A (Agents & Artifacts) - and present a simple case study where the extended A&A ReSpecT is used to coordinate an agent-oriented pervasive system for sensing and controlling environmental properties.
{"title":"Situating A&A ReSpecT for Pervasive Environment Applications","authors":"Matteo Casadei, Andrea Omicini","doi":"10.1109/WETICE.2008.31","DOIUrl":"https://doi.org/10.1109/WETICE.2008.31","url":null,"abstract":"The challenge of intelligence in pervasive computing scenarios is a difficult and fascinating one. While MASs (Multi-Agent Systems) provide for a principled approach to pervasive intelligent systems, large scale and physical distribution call for expressive coordination models and technologies promoting distribution of intelligence. Also, the issue of situatedness of intelligence mandates effective agent models and technologies enabling the engineering of agent-based systems immersed within dynamic and articulated pervasive computing environments. Moving MAS coordination toward situatedness - from both a theoretical and a technological viewpoint-is then a fundamental step toward intelligent MAS in pervasive computing scenarios. In this paper we show how a language for MAS coordination - ReSpecT - can be extended according to a meta-model which provides a simple and solid grounding for MAS situatedness - A&A (Agents & Artifacts) - and present a simple case study where the extended A&A ReSpecT is used to coordinate an agent-oriented pervasive system for sensing and controlling environmental properties.","PeriodicalId":259447,"journal":{"name":"2008 IEEE 17th Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126451835","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：