Filters








41,477 Hits in 11.0 sec

Trading computation for bandwidth: reducing communication in distributed control systems using state estimators

J.K. Yook, D.M. Tilbury, N.R. Soparkar
2002 IEEE Transactions on Control Systems Technology  
This paper describes a new framework for distributed control systems in which estimators are used at each node to estimate the values of the outputs at the other nodes.  ...  The estimated values are then used to compute the control algorithms at each node.  ...  In this section, we outline a framework for reducing communication using state estimators.  ... 
doi:10.1109/tcst.2002.1014671 fatcat:f5qbxiebuzbgpoeawh5ounpyeu

Computation-Communication Trade-offs and Sensor Selection in Real-time Estimation for Processing Networks [article]

Luca Ballotta, Luca Schenato, Luca Carlone
2020 arXiv   pre-print
We consider a network in charge of estimating the state of a dynamical system and provide three contributions.  ...  This leads to a fundamental communication-computation trade-off, where each node has to decide on the optimal amount of preprocessing in order to maximize the network performance.  ...  On the one hand, the control literature extensively investigates the co-design of estimation and control for networked control systems in the presence of communication constraints, such as data rate, quantization  ... 
arXiv:1911.05859v8 fatcat:6y5frgpap5cbzekmolqwoitole

Understanding the design trade-offs among current multicore systems for numerical computations

Seunghwa Kang, David A. Bader, Richard Vuduc
2009 2009 IEEE International Symposium on Parallel & Distributed Processing  
We illustrate the software implementation process on each platform for a set of widely-used kernels from computational statistics that are simple to reason about; measure and analyze the performance of  ...  Our primary aim is to aid application designers in better mapping their software to the most suitable architecture, with an additional goal of influencing future computing system design.  ...  We acknowledge NVIDIA Corp. for its donation of GPU cards and the professor partnership award, and the Sony-Toshiba-IBM Center of Competence for use of Cell/B.E. resources that have contributed to this  ... 
doi:10.1109/ipdps.2009.5161055 dblp:conf/ipps/KangBV09 fatcat:wyjc4escnvfp5lf5ar5ulireom

Optimal Accuracy-Time Trade-off for Deep Learning Services in Edge Computing Systems [article]

Minoo Hosseinzadeh, Andrew Wachal, Hana Khamfroush, Daniel E. Lucani
2020 arXiv   pre-print
With the increasing demand for computationally intensive services like deep learning tasks, emerging distributed computing platforms such as edge computing (EC) systems are becoming more popular.  ...  Edge computing systems have shown promising results in terms of latency reduction compared to the traditional cloud systems.  ...  ACKNOWLEDGEMENTS This work is funded by research grants provided by the Cisco Systems Inc. and the National Science Foundation (NSF) under the grant numbers 1215519250 and 1948387 respectively.  ... 
arXiv:2011.08381v1 fatcat:4yh32sbkzzanpgjr4ozril7c2y

A Distributed Multi-agent Market Place for HPC Compute Cycle Resource Trading [article]

Stefan J. Zasada, Peter V. Coveney
2015 arXiv   pre-print
In this paper we present our solutions to this problem, a resource trading platform that allows users to purchase access to resources within a distributed e-infrastructure.  ...  Computer simulation is finding a role in an increasing number of scientific disciplines, concomitant with the rise in available computing power.  ...  MAPPER (no 261507) and ComPat (no 223979) projects, the EPSRC Rapid Prototyping of Usable Grid Middleware (GR/T27488/01) grant, and also by OMII under the Managed Programme Robust Application Hosting in  ... 
arXiv:1512.04343v1 fatcat:5uylsi7mnvcudcvwzg6cm32gs4

Trading Network Performance for Cash in the Bitcoin Blockchain

Enrico Tedeschi, Håvard D. Johansen, Dag Johansen
2018 Proceedings of the 8th International Conference on Cloud Computing and Services Science  
On Distributed Communications: Introduction to Distributed Communication Networks. The Rand Corporation, . [ ] M. Bowles. Machine Learning in Python: Essential Techniques for Predictive Analysis.  ...  Our first concern while studying fees and tolls is to analyze whether is possible or not for applications to control available bandwidth given from the system by paying higher fees to miners. .  ...  for tx in self . transactions : 20 tx . block_height = self . height Listing C. : Transaction object structure obtained using Bitcoin's s. 1 class Transaction : E Usage Trading Network Performance  ... 
doi:10.5220/0006805906430650 dblp:conf/closer/TedeschiJJ18 fatcat:2mk7uuuleffezjz6qvqhmdmrha

Trading link utilization for queueing delays: An adaptive approach

Rade Stanojević, Robert Shorten
2010 Computer Communications  
estimation.  ...  Understanding the relationship between queueing delays and link utilization for general traffic conditions is an important open problem in networking research.  ...  The following theorem shows that, assuming that estima-torsB preserves order of B on the grid T α = {t(0) · α n , n ∈ Z} the controller (9) runs system to the state that is close to global optima.  ... 
doi:10.1016/j.comcom.2010.02.014 fatcat:ffsz2yujxfdqzk5iiawhs6poz4

Improving retouched Bloom filter for trading off selected false positives against false negatives

Benoit Donnet, Bruno Baynat, Timur Friedman
2010 Computer Networks  
Where distributed agents must share voluminous set membership information, Bloom filters provide a compact, though lossy, way for them to do so.  ...  Numerous recent networking papers have examined the trade-offs between the bandwidth consumed by the transmission of Bloom filters, and the error rate, which takes the form of false positives.  ...  Using filters reduces the bandwidth requirements, but the false positives can significantly reduce the amount of topology information that the system gleans.  ... 
doi:10.1016/j.comnet.2010.07.003 fatcat:6wfeeevxsjgmxggcoa6orum6eu

Performance evaluation and design trade-offs for wireless network-on-chip architectures

Kevin Chang, Sujay Deb, Amlan Ganguly, Xinmin Yu, Suman Prasad Sah, Partha Pratim Pande, Benjamin Belzer, Deukhyoun Heo
2012 ACM Journal on Emerging Technologies in Computing Systems  
Networks-on-Chip (NoCs) have emerged as communication backbones to enable a high degree of integration in multicore Systems-on-Chip (SoCs).  ...  RELATED WORK The NoC paradigm has emerged as a communication backbone to enable a high degree of integration in multicore System-on-Chips (SoCs) [Pande et al. 2005 ].  ...  In a ring-based upper-level network, the same principle of distributed routing and token flow control is used.  ... 
doi:10.1145/2287696.2287706 fatcat:zn7hoy447fdx3hvkoaqnm26kgq

Performance Evaluation and Design Trade-Offs for Network-on-Chip Interconnect Architectures

P.P. Pande, C. Grecu, M. Jones, A. Ivanov, R. Saleh
2005 IEEE transactions on computers  
Multiprocessor system-on-chip (MP-SoC) platforms are emerging as an important trend for SoC design.  ...  These communication-centric interconnect fabrics are characterized by different trade-offs with regard to latency, throughput, energy dissipation, and silicon area requirements.  ...  In addition, they wish to thank the expert reviewers for their extremely valuable comments, which helped them enhance the quality of their work.  ... 
doi:10.1109/tc.2005.134 fatcat:xl2pkf22hvfvxpjggxdmtjrkr4

The Diversity-Bandwidth Tradeoff

Sinan Aral, Marshall W. Van Alstyne
2010 Social Science Research Network  
JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive.  ...  The University of Chicago Press is collaborating with JSTOR to digitize, preserve and extend access to The authors propose that a trade-off between network diversity and communications bandwidth regulates  ...  We control for seasonal and transitory variation in our data by using dummy variables for each month and year.  ... 
doi:10.2139/ssrn.958158 fatcat:z24jlzufyvbrvclllynqna5mje

Compute-Bound and Low-Bandwidth Distributed 3D Graph-SLAM [article]

Jincheng Zhang, Andrew R. Willis, Jamie Godwin
2020 arXiv   pre-print
Our approach uses DVO SLAM, a leading algorithm for 3D mapping, and extends it by computationally isolating map integration tasks from local Guidance, Navigation, and Control tasks and includes an addition  ...  This article describes a new approach for distributed 3D SLAM map building.  ...  Due to the bandwidth constraints and limited communication range, it is challenging to share raw data or other large amounts of data among the agents in a distributed SLAM system. 26 A distributed communication  ... 
arXiv:2005.10222v1 fatcat:6encp3i2mrdetfknxbekzsyqv4

Trading structure for randomness in wireless opportunistic routing

Szymon Chachulski, Michael Jennings, Sachin Katti, Dina Katabi
2007 Computer communication review  
Opportunistic routing is a recent technique that achieves high throughput in the face of lossy wireless links.  ...  We implemented MORE in the Click modular router running on off-the-shelf PCs equipped with 802.11 (WiFi) wireless interfaces.  ...  These probabilities are distributed to other nodes in the network in a manner similar to link state protocols [9] .  ... 
doi:10.1145/1282427.1282400 fatcat:7lrvblisajbzzlkrnfddj2xchm

A Distributed Scheme for Value-Based Bandwidth Reconfiguration [chapter]

Åke Arvidsson, Johannes Göbel, Anthony Krzesinski, Peter Taylor
2009 Lecture Notes in Computer Science  
The scheme resembles the bandwidth broker concept in that it deploys trading, but different in that it acts according to local rules and without centralised control.  ...  This paper presents a scheme for reallocating bandwidth in path-oriented transport networks based on, for example, MPLS, ATM, SDH or SONET.  ...  WALRAS was used [7] in the design of a system where bandwidth is traded at prices computed to reflect current and future requirements.  ... 
doi:10.1007/978-3-642-04576-9_2 fatcat:uhrax2rpnrcrfehrlrx622kadm

BACombo—Bandwidth-Aware Decentralized Federated Learning

Jingyan Jiang, Liang Hu, Chenghao Hu, Jiate Liu, Zhi Wang
2020 Electronics  
In BACombo, we propose a segmented gossip aggregation mechanism that makes full use of node-to-node bandwidth for speeding up the communication time.  ...  Federated learning allows computing nodes to only synchronize the locally-trained models instead of their original data in distributed training.  ...  of the system. (2) The computation times of each worker vary significantly due to the difference in the computing devices and network environment.  ... 
doi:10.3390/electronics9030440 fatcat:suv6rkc465eodilc2dcrxjky7a
« Previous Showing results 1 — 15 out of 41,477 results