The aim of this sixth workshop is to explore the promise of P2P to offer exciting new possibilities in distributed information processing and database technologies. Nowadays network technologies allow the deployment of systems composed of a big number of devices and calculators whose complexity may lead to high management costs. Besides, the investments required to guarantee robustness and reliability may become unsustainable. Examples of this kind of systems are grid networks and enterprises' or governmental server clusters spread all over the world and used for business, social or scientific purposes. Other application scenarios are emerging where the system can not be configured by specific adjustments on its single components, for instance in sensor networks with thousands or millions of micro-devices. Viable solutions require the system to be able to self-configure, self- manage, self-recovery, more generally speaking it must be able to selforganize without human interaction, adapting its working and optimization strategies to resource usage and to overall efficiency. The P2P paradigm lends itself to constructing large scale complex, adaptive, autonomous and heterogeneous database and information systems, endowed with clearly specified and differential capabilities to negotiate, bargain, coordinate and self-organize the information exchanges in large scale networks. Peer-to-peer systems have concretely shown how to aggregate huge computation and information resources from small autonomous and heterogeneous calculators. Although no centralized coordination exists, these systems are able to organize themselves and can offer basic services for information discovery. The literature on peer-to-peer systems, which has grown rapidly in the last years, has highlighted the potential of this new paradigm offering more efficient and reliable solutions for self-organization of big distributed systems. The realization of these promises lies fundamentally in the availability of enhanced services such as structured ways for representing, classifying, querying and registering shared information, verification and certification of information, content distributed schemes and quality of content, security features, information discovery and accessibility, interoperation and composition of active information services, and finally market-based mechanisms to allow cooperative and non cooperative information exchanges. The exploitation of the knowledge extracted from the peers' network is definitely a further potential of such systems. For example, the possibility of performing distributed data mining on the big amount of data that peer-to-peer systems are able to put together, also exploiting their huge parallel computing potential, may lead to extract knowledge potentially useful for scientific, social and commercial purposes, depending on the network domain. Moreover, in-network data mining algorithms would supply the capability of generating and transmitting highlevel models instead of raw data allowing to significantly reduce network traffic and the network could forecast events and return only relevant information to user requests. The use of semantics for the descriptions of peers and services could introduce new approaches for querying, sharing, distributing and organizing knowledge. Such approach generates several challenges related to the association of services/contents to ontologies, the interoperability/ integration of ontologies, the exploitation of emergent semantics required for understanding different contents and the automation of such processes. For example, in mobile computing the possibility of data and services related to physical location and the relation with peers and sensors in physical proximity could introduce new opportunities and also new technical challenges. Such dynamic environments, which are inherently characterized by mobility and heterogeneity of resources like devices, participants, services, information and data representation, pose several issues on how to search and localize resources, how to efficiently route traffic, up to higher level problems related to semantic interoperability and information relevance. Finally, the classical problems related to efficient methods for the indexing and querying data, workload balancing and traffic redistribution and the retrieving of data in P2P systems still present aspects that have not been completely investigated. Concerning these issues, the P2P and the database community may mutually benefit. The database research has much to contribute to the P2P grand challenge through its wealth of techniques for sophisticated semantics-based data models, clever indexing algorithms and efficient data placement, query processing techniques and transaction processing. The database community could benefit from the P2P computing vision by developing loosely coupled federations of databases where databases can join and leave the network at will, a single global schema is not a possibility, and answers need not be complete but best effort. We are aware that the research on these themes has a main relevance since the effects of these architectures that embrace peer-to-peer, data and information systems will involve the structure of complex organizations (business, scientific or otherwise) and on the emergence and the formation of social communities, and on how the information is organized and processed.The workshop is build on the success of the five preceding editions since VLDB 2003, whose proceedings have been always published by Springer in Lecture Notes in Computer Science series. It concentrates on exploring the synergies between current database research and P2P computing, in fact it is our belief that database research has much to contribute to the P2P grand challenge through its wealth of techniques for sophisticated semantics-based data models, new indexing algorithms and efficient data placement, query processing techniques and transaction processing. Database technologies in the new information age will form the crucial components of the first generation of complex adaptive P2P information systems, which will be characterized by their ability to continuously self-organize, adapt to new circumstances, promote emergence as an inherent property, optimize locally but not necessarily globally, deal with approximation and incompleteness. This workshop also concentra! tes on the impact of complex adaptive information systems on current database technologies and their relation to emerging industrial technologies. The workshop co-location with VLDB, the major international database and information systems conference, is important in order to actually bring together key researchers from all over the world working on databases and P2P computing with the intention of strengthening this connection. Researchers from other related areas such as distributed systems, networks, multi-agent systems and complex systems are also invited, in fact we believe that mostly in the P2P paradigm, as an interdisciplinary theme, different approaches and point of views may generate cross-fertilization ideas and high-quality results.
Sixth International Workshop on Databases, Information Systems and Peer-to-Peer Computing (DBISP2P 2008) / Bergamaschi, Sonia; Boon Chong, Seet; Noria, Foukia; Nigel, Stanger; Gianluca, Moro. - (2008).
Sixth International Workshop on Databases, Information Systems and Peer-to-Peer Computing (DBISP2P 2008)
BERGAMASCHI, Sonia;
2008
Abstract
The aim of this sixth workshop is to explore the promise of P2P to offer exciting new possibilities in distributed information processing and database technologies. Nowadays network technologies allow the deployment of systems composed of a big number of devices and calculators whose complexity may lead to high management costs. Besides, the investments required to guarantee robustness and reliability may become unsustainable. Examples of this kind of systems are grid networks and enterprises' or governmental server clusters spread all over the world and used for business, social or scientific purposes. Other application scenarios are emerging where the system can not be configured by specific adjustments on its single components, for instance in sensor networks with thousands or millions of micro-devices. Viable solutions require the system to be able to self-configure, self- manage, self-recovery, more generally speaking it must be able to selforganize without human interaction, adapting its working and optimization strategies to resource usage and to overall efficiency. The P2P paradigm lends itself to constructing large scale complex, adaptive, autonomous and heterogeneous database and information systems, endowed with clearly specified and differential capabilities to negotiate, bargain, coordinate and self-organize the information exchanges in large scale networks. Peer-to-peer systems have concretely shown how to aggregate huge computation and information resources from small autonomous and heterogeneous calculators. Although no centralized coordination exists, these systems are able to organize themselves and can offer basic services for information discovery. The literature on peer-to-peer systems, which has grown rapidly in the last years, has highlighted the potential of this new paradigm offering more efficient and reliable solutions for self-organization of big distributed systems. The realization of these promises lies fundamentally in the availability of enhanced services such as structured ways for representing, classifying, querying and registering shared information, verification and certification of information, content distributed schemes and quality of content, security features, information discovery and accessibility, interoperation and composition of active information services, and finally market-based mechanisms to allow cooperative and non cooperative information exchanges. The exploitation of the knowledge extracted from the peers' network is definitely a further potential of such systems. For example, the possibility of performing distributed data mining on the big amount of data that peer-to-peer systems are able to put together, also exploiting their huge parallel computing potential, may lead to extract knowledge potentially useful for scientific, social and commercial purposes, depending on the network domain. Moreover, in-network data mining algorithms would supply the capability of generating and transmitting highlevel models instead of raw data allowing to significantly reduce network traffic and the network could forecast events and return only relevant information to user requests. The use of semantics for the descriptions of peers and services could introduce new approaches for querying, sharing, distributing and organizing knowledge. Such approach generates several challenges related to the association of services/contents to ontologies, the interoperability/ integration of ontologies, the exploitation of emergent semantics required for understanding different contents and the automation of such processes. For example, in mobile computing the possibility of data and services related to physical location and the relation with peers and sensors in physical proximity could introduce new opportunities and also new technical challenges. Such dynamic environments, which are inherently characterized by mobility and heterogeneity of resources like devices, participants, services, information and data representation, pose several issues on how to search and localize resources, how to efficiently route traffic, up to higher level problems related to semantic interoperability and information relevance. Finally, the classical problems related to efficient methods for the indexing and querying data, workload balancing and traffic redistribution and the retrieving of data in P2P systems still present aspects that have not been completely investigated. Concerning these issues, the P2P and the database community may mutually benefit. The database research has much to contribute to the P2P grand challenge through its wealth of techniques for sophisticated semantics-based data models, clever indexing algorithms and efficient data placement, query processing techniques and transaction processing. The database community could benefit from the P2P computing vision by developing loosely coupled federations of databases where databases can join and leave the network at will, a single global schema is not a possibility, and answers need not be complete but best effort. We are aware that the research on these themes has a main relevance since the effects of these architectures that embrace peer-to-peer, data and information systems will involve the structure of complex organizations (business, scientific or otherwise) and on the emergence and the formation of social communities, and on how the information is organized and processed.The workshop is build on the success of the five preceding editions since VLDB 2003, whose proceedings have been always published by Springer in Lecture Notes in Computer Science series. It concentrates on exploring the synergies between current database research and P2P computing, in fact it is our belief that database research has much to contribute to the P2P grand challenge through its wealth of techniques for sophisticated semantics-based data models, new indexing algorithms and efficient data placement, query processing techniques and transaction processing. Database technologies in the new information age will form the crucial components of the first generation of complex adaptive P2P information systems, which will be characterized by their ability to continuously self-organize, adapt to new circumstances, promote emergence as an inherent property, optimize locally but not necessarily globally, deal with approximation and incompleteness. This workshop also concentra! tes on the impact of complex adaptive information systems on current database technologies and their relation to emerging industrial technologies. The workshop co-location with VLDB, the major international database and information systems conference, is important in order to actually bring together key researchers from all over the world working on databases and P2P computing with the intention of strengthening this connection. Researchers from other related areas such as distributed systems, networks, multi-agent systems and complex systems are also invited, in fact we believe that mostly in the P2P paradigm, as an interdisciplinary theme, different approaches and point of views may generate cross-fertilization ideas and high-quality results.Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris