The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We investigate the impact of an unevenly distributed load among nodes of a distributed key-value store on response times. We find that response times of “get” operations quickly degrade in the presence of power law distributions of load and identify the point, at which the system needs to apply a mitigation approach. The migration technique, which we propose, overcomes the long response times of consistent...
Exascale networks are expected to comprise a significant part of the total monetary cost and 10-20% of the power budget allocated to exascale systems. Yet, our understanding of current and emerging workloads on these networks is limited. Left ignored, this knowledge gap likely will translate into missed opportunities for (1) improved application performance and (2) decreased power and monetary costs...
Message forwarding is an integral part of the decentralized content sharing process as the content delivery success highly depends on it. Existing literature employs spatio-temporal regularity of human movement pattern and pre-existing social relationship to take message forwarding decisions. However, such approaches are ineffectual in environments where those information are unavailable such as a...
In this paper, we evaluate and compare the performance of single-copy and multiple-copy routing protocols in a realistic Vehicular Delay Tolerant Network (VDTN) scenario. The simulations are conducted with the Opportunistic Network Environment (ONE) simulator. The performance is analyzed using delivery probability, overhead ratio, average latency, average number of hops and average buffer time metrics...
In this work, we evaluate the performance ofthree routing protocols epidemic, sprayandwait and maxpropin Vehicular Delay Tolerant Networks (VDTNs). We study theimpact of vehicles density and ttl on the network performance. The simulations are conducted with the Opportunistic NetworkEnvironment (ONE) simulator. The performance is analyzedusing delivery probability, overhead ratio, average latencyand...
Delay-Tolerant Networks (DTNs) are sparse dynamic wireless networks, where most of the time a complete end-to-end path from the source to the destination does not exist. There are many real networks that follow this model, for example, military networks, vehicular ad-hoc networks (VANETs), wildlife tracking sensor networks, etc. In this context, conventional mobile ad-hoc routing schemes would fail,...
Intermittently Connected Mobile Networks (ICMNs) are sparse wireless networks where most of the time an end-to-end path does not exist from source to destination. These networks are characterized by opportunistic connectivity, long and variable delay, asymmetric data rate and high error rate. Hence, they can be appropriately modeled as Delay-Tolerant Networks (DTNs). In this paper, the performance...
This paper focuses on data replication in structured peer-to-peer systems over highly dynamic networks. A Q-learning-based replication approach is proposed. Data availability is periodically computed using the Q-learning function. The reward/penalty property of this function attenuates the impact of the network dynamism on the replication overhead. Hence, the departure of a node does not necessarily...
Distributed Hash Tables (DHTs) provide information lookup within a Peer-to-Peer (P2P) network. A multitude of distributed applications leverages DHTs for offering more advanced services such as distributed file systems, web caches or distributed DNS. For such DHT-based applications, lookup performance is highly important. However, lookup performance is severely affected by network characteristics,...
Due to intermittent connectivity and uncertain node mobility, opportunistic message forwarding algorithms have been widely adopted in delay tolerant networks (DTNs). While existing work proposes practical forwarding algorithms in terms of increasing the delivery rate and decreasing data overhead, little attention has been drawn to the control overhead induced by the algorithms. The control overhead...
The peer-to-peer (P2P) communication model has gained an enormous research interest in the last few years due to its promising properties (e.g., decentralization, self-organization, scalability, etc.) to build large scale distributed applications. However, the P2P systems are characterized by their dynamic behavior as peers can frequently join and leave the network. This property makes the data availability...
Many proposals have been advanced for structured P2P networks, but it is difficult for existing structured P2P networks to achieve dynamic load balancing sufficient. In this paper, we propose a new structured P2P network called Waon, which achieves dynamic load balancing among nodes. Each node in a Waon network controls the number of objects assigned to the node for load balancing of objects. In addition,...
Peer-to-peer (P2P) based content distribution networks (CDNs), e.g., BitTorrent, are widely used in the today's Internet. Since all peers interested in a specific content provide storage and upload capacity those CDNs facilitate a cheap and easy distribution of large amounts of data. However, they generate a lot of costs for Internet Service Providers (ISPs) as normal users also act as a source for...
Mobile ad hoc network and peer-to-peer networks are most advancing and emerging research areas in the recent years. Both of these networks are based on the same phenomenon like self-configuration and self-organization. Although, peer-to-peer network was firstly designed for wired network but now a days it may be deployed over mobile ad hoc network. When P2P networks are deployed over ad hoc network,...
Most Distributed Hash Tables (DHTs) inherently assume interconnecting nodes with homogeneous capabilities. Realistically however, capabilities of nodes on a network widely vary, leading traditional DHTs to inevitably exhibit poor performance in real-world environments. Stealth DHT was previously proposed to address node heterogeneity by enabling a DHT to separate highly capable (super-peers or service)...
We propose a common vector space to describe documents and users in order to create a social network based on affinities, and explore epidemic algorithms to perform searches based on recommendations. Furthermore, we propose using Fuzzy Distributed Tables to help the localization of isolated, affine clusters.
We introduce a trusted self-organized network infrastructure for running anonymous P2P applications, which leverages real-life social links and the basic need for privacy that each individual converts into a carefully built structure dubbed Personal Social Graph (PSG). The PSG is a list owned by each person (enacted by a node in the infrastructure graph), with entries that represent strict trust relationships...
RDF and OWL are used as the data model and schema, respectively, to build the distributed knowledge base of the Semantic Web. The components in RDF models, subjects, predicates, and objects, are identified universally on the web, which makes it suitable for distributed operations. In this paper, we employ the distributed hash table (DHT) technology on peer-to-peer network to develop distributed RDF...
In this paper, we propose an efficient multiple hashes method (called KAD-N) to balance peer loads in the KAD (Kademlia) network. Note that N is the maximum hash times, determining by a cost-effectiveness factor. This method hashes the keyword of an object r times to produce a key for publishing objects, where r is a random number and 1 ?? r ?? N. Simulation results show that the distribution of indexes...
Broadcast is a basic service for many network operations. It had been proposed to maintain a broadcast tree over a P2P network explicitly to support message broadcast from the root to leaves and information aggregation from leaves to the root reversely. We notice that a peer near the root of a broadcast tree has shorter message latency and a smaller possibility of message loss due to join or departure...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.