Chedar: peer-to-peer middleware

Proceedings of the 4th International Mobile Multimedia Communications Conference

Papadopouli

2008

PhotoJournal is a novel location-based media sharing application that enables users to build interactive journals that associate multimedia files with locations on maps and share this information with other users. Its underlying information discovery and sharing mechanism is 7DS that runs in either pure peer-to-peer or centralized server-to-client mode, depending on the availability of a server and/or an infrastructure. 7DS-enabled devices act as miniature caches, sharing information with each other. When access to an information server (e.g., web server) is not available, the local 7DS instance running on the device enables the device to search and access information from other peers in proximity. We have implemented the prototype and evaluated the delay to access the data using three testbeds. Two of these testbeds employ a centralized (server-to-client) architecture, while the third one applies the peer-to-peer paradigm. Depending on the underlying network technology and device capabilities, this delay varies. The results encourage us to perform additional empirical-based studies under increased traffic load conditions and initiate a user-study in the premises of a museum and a research park.

Section: Related Workmentioning

confidence: 99%

You’ve Got Photos! The design and evaluation of a location-based media-sharing application

Proceedings of the 4th International Mobile Multimedia Communications Conference

Papadopouli

2008

“…The Cheese Factory -project [3] has implemented a Java-based peer-to-peer computing platform called Chedar [1]. Chedar can be used to build a network of workstations where each node provides and consumes resources such as computing power, files and devices.…”

Section: Peer-to-peer Studiomentioning

confidence: 99%

“…At first, P2PStudio was developed to collect data from a Chedar network [1] consisting of tens of workstations. Experimenting with self-organization of topology and different resource discovery algorithms however usually requires a controlled environment to obtain results that are repeatable.…”

Section: P2pstudio In Peer-to-peer Network Researchmentioning

confidence: 99%

P2PStudio

Proceedings of the ACM International Workshop on Performance Monitoring, Measurement, and Evaluation of Heterogeneous Wireless

Vapa

Auvinen

et al. 2006

Peer-to-Peer Studio has been developed as a monitoring, controlling and visualization tool for peer-to-peer networks. It uses a centralized architecture to gather events from a peer-to-peer network and can be used to visualize network topology and to send different commands to individual peer-to-peer nodes. The tool has been used with Chedar Peer-to-Peer network to study the behavior of different peerto-peer resource discovery and topology management algorithms and for visualizing the results of NeuroSearch resource discovery algorithm produced by the Peer-to-Peer Realm network simulator. This paper presents the features, the architecture and the protocols of Peer-to-Peer Studio and the experience gained from using the tool for peer-to-peer networks research.

“…Earlier in our project [4] we had developed Chedar P2P middleware [2], which provided the basis for building P2PDisCo on top of it. P2PDisCo allows the workstations joined in a Chedar P2P network to publish certain distributed computing application as a resource in Chedar P2P network.…”

Section: Speeding the Execution With P2pdiscomentioning

confidence: 99%

P2PRealm - Peer-to-Peer Network Simulator

2006 11th Intenational Workshop on Computer-Aided Modeling, Analysis and Design of Communication Links and Networks

Vapa

Keltanen

et al.

Self Cite

Abstract-Peer-to-Peer Realm (P2PRealm) is an efficient peer-topeer network simulator for studying algorithms based on neural networks. In contrast to many simulators, which emphasize on detailed network simulation, the speed of simulation in P2PRealm is essential, because neural networks require a time consuming training phase. Efficiency has been obtained by optimizing training loops inside the simulator, using Java Native Interface (JNI) as well as distributing the simulator to hundreds of workstations using the P2PDisCo platform. In this paper we describe the architecture of P2PRealm and its input/output interfaces. Also, we present the mechanisms used for internally optimizing the implementation and the configuration used for distribution. Finally, we present the use of P2PRealm with the P2PStudio network visualization tool.