Delay-tolerant networking (DTN) provides a platform for applications in environments where end-to-end paths may be highly unreliable or do not exist at all. In many applications such as distributed wikis or photo shar...
详细信息
ISBN:
(纸本)9781424433032
Delay-tolerant networking (DTN) provides a platform for applications in environments where end-to-end paths may be highly unreliable or do not exist at all. In many applications such as distributed wikis or photo sharing, users need to be able to find content even when they do not know an unambiguous identifier. In order do bring these applications to the domain of DTNs, a search scheme is required that works despite the unreliable network conditions. In this paper, we introduce a search scheme that makes no assumptions about the underlying routing protocols and the format of search requests. We evaluate different algorithms for forwarding and terminating search queries, using simulations with different classes of DTN routing protocols for different mobility scenarios.
In this paper, we consider the problem of estimating the parameters - the central directions of arrival (DOA) and angular spread of distributed source by one-dimension searching algorithm. The central DOA and angular ...
详细信息
Combinatorial Auctions are auctions where bidders can place bids on combinations of items, called packages or bundles, rather than just on individual items. In this paper we extend this concept to distributed system, ...
详细信息
ISBN:
(纸本)9783540922940
Combinatorial Auctions are auctions where bidders can place bids on combinations of items, called packages or bundles, rather than just on individual items. In this paper we extend this concept to distributed system, by proposing a distributed Combinatorial Auctioning System consisting of auctioneers and bidders who communicate by message-passing. We also propose a fair division algorithm that is based on our DCAS concept and model. Our model consist of auctioneers that are distributed in the system each having local bidders. Auctioneers collect local bids for the bundles. One of the auctioneers acts obtains all the bids from other auctioneers, and performs the computations necessary for the combinatorial auction. We also briefly discuss how basic and extended fairness are implemented in resource allocation by our algorithm.
We first characterize the minimal link-sets L whose directions must be reversed for reestablishing one or more directed paths from each node x to a fixed destination node d in a network when a link fails. Then, we giv...
详细信息
ISBN:
(纸本)9783540922940
We first characterize the minimal link-sets L whose directions must be reversed for reestablishing one or more directed paths from each node x to a fixed destination node d in a network when a link fails. Then, we give a distributed O(vertical bar E vertical bar) algorithm for determining such a link-set L, where vertical bar E vertical bar = #(links in the network). This improves the previous lower bound O(n(2)), where n = #(nodes in the network). The minimality of the reversed link-set L has other important consequences.
Graphics processing units (GPUs) are powerful computational devices tailored towards the needs of the 3-D gaming industry for high-performance, real-time graphics engines. Nvidia Corporation released a new generation ...
详细信息
ISBN:
(纸本)9780769536422
Graphics processing units (GPUs) are powerful computational devices tailored towards the needs of the 3-D gaming industry for high-performance, real-time graphics engines. Nvidia Corporation released a new generation of GPUs designed for general-purpose computing in 2006, and it released a GPU programming language called CUDA in 2007. The DNA microarray technology is a high throughput tool for assaying mRNA abundance in cell samples. In. data analysis, scientists often apply hierarchical clustering of the genes, where a fundamental operation is to calculate all pairwise distances. If there are n genes, it takes O(n(2)) time. In this work, GPUs and the CUDA language are used to calculate pairwise distances. For Manhattan distance, GPU/CUDA achieves a 40 to 90 times speed-up compared to the central processing unit implementation;for Pearson correlation coefficient, the speed-up is 28 to 38 times.
In this paper, the downlink performance of distributed antenna systems (DAS) in a multi-cell environment is investigated. The individual power constraints (IPC) for the distributed antennas and the total power constra...
详细信息
ISBN:
(纸本)9781424436927
In this paper, the downlink performance of distributed antenna systems (DAS) in a multi-cell environment is investigated. The individual power constraints (IPC) for the distributed antennas and the total power constraint (TPC) for all the distributed antennas are proposed to characterize the inter-cell interference power limits and the total transmit power consumption, respectively. When the large-scale channel state information is available at the transmitter, the problem of power allocation among distributed antennas with the target of downlink ergodic capacity maximization is formulated with consideration of IPC and TPC. Based on system scale-up, an approximation of the objective function is derived, which is further proved to be concave on the transmit powers of the distributed antennas. Consequently, a simple sub-optimal power allocation scheme is proposed by substituting the approximation for the objective function. The system capacity with the suboptimal power allocation is illustrated to be quite close to the optimal one obtained by numerical optimizations.
In this paper, we propose the distributed algorithm for joint optimal cross-layer design in multi-radio multi-channel multi-hop networks. The main objective of this work is to joint optimize injected rate and resource...
详细信息
The 17th internationalconference on computing in High Energy and Nuclear Physics (CHEP) was held on 21–27 March 2009 in Prague, Czech Republic. CHEP is a major series of internationalconferences for physicists and ...
The 17th internationalconference on computing in High Energy and Nuclear Physics (CHEP) was held on 21–27 March 2009 in Prague, Czech Republic. CHEP is a major series of internationalconferences for physicists and computing professionals from the worldwide High Energy and Nuclear Physics community, Computer Science, and Information Technology. The CHEP conference provides an international forum to exchange information on computing experience and needs for the community, and to review recent, ongoing and future activities. Recent conferences were held in Victoria, Canada 2007, Mumbai, India in 2006, Interlaken, Switzerland in 2004, San Diego, USA in 2003, Beijing, China in 2001, Padua, Italy in 2000. The CHEP'09 conference had 600 attendees with a program that included plenary sessions of invited oral presentations, a number of parallel sessions comprising 200 oral and 300 poster presentations, and an industrial exhibition. We thanks all the presenters, for the excellent scientific content of their contributions to the conference. conference tracks covered topics on Online computing, Event Processing, Software Components, Tools and Databases, Hardware and computing Fabrics, Grid Middleware and networking Technologies, distributed Processing and Analysis and Collaborative Tools. The conference included excursions to Prague and other Czech cities and castles and a banquet held at the Zofin palace in Prague. The next CHEP conference will be held in Taipei, Taiwan on 18–22 October 2010. We would like thank the Ministry of Education Youth and Sports of the Czech Republic and the EU ACEOLE project for the conference support, further to commercial sponsors, the international Advisory Committee, the Local Organizing Committee members representing the five collaborating Czech institutions Jan Gruntorad (co-chair), CESNET, z.s.p.o., Prague Andrej Kugler, Nuclear Physics Institute AS CR v.v.i., Rez Rupert Leitner, Charles University in Prague, Faculty of Mathematics and Physi
Estimating network path properties such as latency, loss and available bandwidth is crucial to assist distributed applications such as P2P make the best use of Internet resources. Though quite a number of approaches a...
详细信息
ISBN:
(纸本)9781424436927
Estimating network path properties such as latency, loss and available bandwidth is crucial to assist distributed applications such as P2P make the best use of Internet resources. Though quite a number of approaches are proposed to estimate these metrics, they have disadvantages of do not adapt to different network topologies, only apply to specific performance metric, and so on. In this paper, based on the architecture and routing characteristics of Internet, we propose a novel network path property estimation mechanism named NetGuru, which divides Internet into individual performance domains (PD) and maintains a performance server (PS) for each PD. NetGuru provides path performance estimation service to distributed applications through the collaboration of PSes in different PDs. Simulation result demonstrates that NetGuru can help improve P2P file transfer application efficiency.
This paper analyzes the outage probability of the downlink distributed antenna system (DAS) with selective transmission (ST) scheme and maximum ratio combining (MRC) over shadowed Rayleigh fading channels. Firstly, th...
详细信息
ISBN:
(纸本)9781424436927
This paper analyzes the outage probability of the downlink distributed antenna system (DAS) with selective transmission (ST) scheme and maximum ratio combining (MRC) over shadowed Rayleigh fading channels. Firstly, the probability density function (PDF) is derived for the output signal to noise ratio (SNR) after MRC at the receiver. Then, under the ST scheme, an approximate analytical expression of outage probability is derived for the downlink ST-MRC DAS over the shadowed Rayleigh fading channels. Simulation results show that the derived analytical expression can evaluate the realistic system performance quite accurately.
暂无评论