1,720,997 research outputs found

    Epidemic Information Diffusion: A Simple Solution to Support Community-based Recommendations in P2P Overlays

    No full text
    Epidemic protocols proved to be very efficient solutions for supporting dynamic and complex information diffusion in highly dis- tributed computing infrastructures, like P2P environments. They are useful bricks for building and maintaining virtual network topologies, in the form of overlay networks as well as to support pervasive diffusion of information when it is injected into the network. This paper proposes a simple architecture exploiting the features of epidemic approaches to foster a collaborative percolation of information between computing nodes belonging to the network aimed at building a system that groups similar users and spread useful information among them

    A Peer-to-Peer recommender system for self-emerging user communities based on Gossip overlays

    No full text
    Gossip-based peer-to-peer protocols proved to be very efficient for supporting dynamic and complex information exchange among distributed peers. They are useful for building and maintaining the network topology itself as well as to support a pervasive diffusion of the information injected into the network. This is very useful in a world where there is a growing need to access and be aware of many types of distributed resources like Internet pages, shared files, online products, news and information. Finding flexible, scalable and efficient mechanisms addressing this topic is a key issue, even with relevant social and economic aspects. In this paper, we propose the general architecture of a system whose aim is to exploit the collaborative exchange of information between peers in order to build a system able to gather similar users and spread useful suggestions among them

    On Democracy in Peer-to-Peer systems

    No full text
    The information flow inside a P2P network is highly dependent on the network structure. In order to ease the diffusion of relevant data toward interested peers, many P2P protocols gather similar nodes by putting them in direct contact. With this approach the similarity between nodes is computed in a point-to-point fashion: each peer individually identifies the nodes that share similar interests with it. This leads to the creation of a sort of "private" communities, limited to each peer neighbors list. This "private" knowledge do not allow to identify the features needed to discover and characterize the correlations that collect similar peers in broader groups. In order to let these correlations to emerge, the collective knowledge of peers must be exploited. One common problem to overcome in order to avoid the "private" vision of the network, is related to how distributively determine the representation of a community and how nodes may decide to belong to it. We propose to use a gossip-like approach in order to let peers elect and identify leaders of interest communities. Once leaders are elected, their profiles are used as community representatives. Peers decide to adhere to a community or another by choosing the most similar representative they know about

    Challenges to be addressed for realising an Ephemeral Cloud Federation

    No full text
    This paper sketches the challenges to address to realise a support able to achieve an Ephemeral Cloud Federation, an innovative cloud computing paradigm that enables the exploitation of a dynamic, personalised and context-aware set of resources. The aim of the Ephemeral Federation is to answer to the need of combining private data-centres with both federation of cloud providers and the resource on the edge of the network. The goal of the Ephemeral Federation is to deliver a context-aware and personalised federations of computational, data and network resources, able to manage their heterogeneity in a highly distributed deployment, which can dynamically bring data and computation close to the final user

    Multidimensional range queries on hierarchical Voronoi overlays

    No full text
    The definition of a support for multi-attribute range queries is mandatory for highly distributed systems. Even if several solutions have been proposed in the last decade, most of them do not meet the requirements of recent platforms, like IoT or smart cities. The paper presents an approach that builds a multidimensional Voronoi graph by exploiting the attributes of the objects published by a node. Our solution overcomes the curse of dimensionality issue affecting Voronoi Tessellations in high dimensional spaces by defining a Voronoi hierarchy. The paper formally defines the structure, analysis the complexity of the operations and presents experimental results

    Hivory: Range Queries on Hierarchical Voronoi Overlays

    No full text
    The problem of defining a support for multidimensional range queries on P2P overlays is currently an active field of research. Several approaches based on the extension of the basic functionalities offered by Distributed Hash Tables have been recently proposed. The main drawback of these approaches is that the locality required for the resolution of a range query cannot be guaranteed by uniform hashing. On the other way, locality preserving hashing functions do not guarantee a good level of load balancing. This paper presents Hivory, a P2P overlay based on a Voronoi tessellation defined by the objects published by peers. Each object is mapped to a site of the Voronoi tessellation and the corresponding Delaunay Triangulation defines the P2P overlay. A hierarchy of Voronoi diagrams is defined by exploiting clusters of objects paired with the same site of the Voronoi diagram. A new Voronoi diagram including the peers of the cluster is created so that the query resolution may be refined by a top down visit of the Voronoi hierarchy. The paper presents the proposed solution, analyses its complexity, and provides a set of experimental results

    ATLAAS-P2P: a two layer network solution for easing the resource discovery process in unstructured networks

    No full text
    ATLAAS-P2P is a two-layered P2P architecture for developing systems providing resource aggregation and approximated discovery in P2P networks. Such systems allow users to search the desired resources by specifying their requirements in a flexible and easy way. From the point of view of resource providers, this system makes available an effective solution supporting providers in being reached by resource requests

    Efficient Resources Distribution for an Ephemeral Cloud/Edge continuum

    No full text
    This paper presents the idea and the concepts behind the vision of an Ephemeral Cloud/Edge Continuum, a cloud/edge computing landscape that enables the exploitation of a widely distributed, dynamic, and context-aware set of resources. The Ephemeral Continuum answer to the need of combining a plethora of heterogeneous devices, which nowadays are pervasively embedding anthropic environments, with both federations of cloud providers and the resources located at the Edge. The aim of the Ephemeral Continuum is to realise a context-aware and personalised federation of computational, data and network resources, able to manage their heterogeneity in a highly distribute
    corecore