检索结果-内蒙古大学图书馆

Multi-Path Alpha-Fair Resource Allocation at Scale in distributed Software-Defined Networks

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2018年第12期36卷 2655-2666页

作者： Allybokus, Zaid Avrachenkov, Konstantin Leguay, Jeremie Maggi, Lorenzo Huawei Technol France Res Ctr F-92100 Boulogne France Inria Sophia Antipolis F-06902 Biot France Nokia Bell Labs Data Analyt Dept F-91620 Nozay France

The performance of computer networks relies on how bandwidth is shared among different flows. Fair resource allocation is a challenging problem particularly when the flows evolve over time. To address this issue, bandwidth sharing techniques that quickly react to the traffic fluctuations are of interest, especially in large-scale settings with hundreds of nodes and thousands of flows. In this context, we propose a distributed algorithm based on the alternating direction method of multipliers (ADMM) that tackles the multi-path fair resource allocation problem in a distributed SDN control architecture. Our ADMM-based algorithm continuously generates a sequence of resource allocation solutions converging to the fair allocation while always remaining feasible, a property that standard primal-dual decomposition methods often lack. Thanks to the distribution of all computer intensive operations, we demonstrate that we can handle large instances at scale.

关键词： Software-defined networks multi-path resource allocation alpha-fairness alternating direction method of multipliers distributed SDN control plane distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

BlockCom: A Blockchain based Commerce Model for Smart Communities using Auction Mechanism

BlockCom: A Blockchain based Commerce Model for Smart Commun...

引用

IEEE International Conference on Communications (IEEE ICC)

作者： Hassija, Vikas Bansal, Gaurang Chamola, Vinay Saxena, Vikas Sikdar, Biplab JIIT Dept Comp Sci & Engn Noida Campus Noida India BITS Pilani Dept Elect & Elect Engn Pilani Campus Pilani Rajasthan India Natl Univ Singapore Dept Elect & Comp Engn Singapore Singapore

ISBN: (纸本)9781728123738

Smart Communities seeks to thrive in a context of broadband economy, its engine and reason for being. The success of any community is a function of its economic backbone or the supply chain. A supply chain can be defined as the integration of customers, retailers, distributors and manufacturers. The changing technology has made the survival in commerce highly competitive and price sensitive. Blockchain technology can be the game-changer for decentralizing infrastructure and building a trust layer for business logic. BlockCom is a commerce model based on the emerging technology of blockchain. This paper presents a double auction scheme for energy trading between customers and suppliers. A smart contract implements a distributed algorithm to maximize individual participating profit. Parties bid to smart contract which act as auctioneer for maximizing the profit. Mathematical parameter named credibility score has been created to deal with trust issues in the decentralized network using byzantine fault tolerant mechanism. BlockCom provides a fresh perspective on the concept of supply chain and commerce.

关键词： Commerce Energy trading Auctioneers contract supply chain DISTRIBUTOR distributed algorithms Engines Purchasing

来源：评论

学校读者我要写书评

暂无评论

Coded Caching with Heterogeneous User Profiles

Coded Caching with Heterogeneous User Profiles

引用

IEEE International Symposium on Information Theory (ISIT)

作者： Wang, Su Peleato, Borja Purdue Univ W Lafayette IN 47907 USA

ISBN: (纸本)9781538692912

Coded caching has been proven to be a useful technique for reducing traffic in networks with point-to-multipoint links. The key idea is to pre-fetch popular content at the end users during off-peak hours, and encode transmissions when resources are scarce in such a way that different users can obtain different information from the same packet. Prior works have proposed placement and delivery algorithms to address a wide range of scenarios with varying file popularities, file sizes, and cache capacities. Both centralized and distributed algorithms have been proposed, and their performance limits have been characterized in terms of peak and average transmission rates. However, existing works have focused on the case where all the end users present an identical distribution of requests;in other words, the popularity of a given file is identical for all users. This assumption is overly simplistic in modern networks, where network operators often build detailed individual profiles on each user. This paper proposes and compares the peak rate of three coded caching schemes when the end users can be classified into distinct groups with different distribution of demands. Specifically, the first scheme ignores the differences between user profiles, the second performs independent caching and delivery of each class of files, and the third ignores the similarities between user profiles. The second scheme derives a method to partition the cache between widely popular files and files that may only be requested by a subset of the users. Our analysis yields some counter-intuitive results.

关键词： Servers Manganese Multicast communication distributed algorithms Classification algorithms Partitioning algorithms Games

来源：评论

学校读者我要写书评

暂无评论

Strongly Linearizable Implementations of Snapshots and Other Types 19

Strongly Linearizable Implementations of Snapshots and Other...

引用

38th ACM Symposium on Principles of distributed Computing (PODC)

作者： Ovens, Sean Woelfel, Philipp Univ Calgary Calgary AB Canada

ISBN: (纸本)9781450362177

Linearizability is the gold standard of correctness conditions for shared memory algorithms, and historically has been considered the practical equivalent of atomicity. However, it has been shown [16] that replacing atomic objects with linearizable implementations can affect the probability distribution of execution outcomes in randomized algorithms. Thus, linearizable objects are not always suitable replacements for atomic objects. A stricter correctness condition called strong linearizability has been developed and shown to be appropriate for randomized algorithms in a strong adaptive adversary model [16]. We devise several new lock-free strongly linearizable implementations from atomic registers. In particular, we give the first strongly linearizable lock-free snapshot implementation that uses bounded space. This improves on the unbounded space solution of Denysyuk and Woelfel [14]. As a building block, our algorithm uses a lock-free strongly linearizable ABA-detecting register. We obtain this object by modifying the wait-free linearizable ABA-detecting register of Aghazadeh and Woelfel [5], which, as we show, is not strongly linearizable. Aspnes and Herlihy [8] identified a wide class of types that have wait-free linearizable implementations. These types require that any pair of operations either commute, or one overwrites the other. Aspnes and Herlihy gave a general wait-free linearizable implementation of such types, employing an atomic snapshot object. We show that this implementation is strongly linearizable, proving that all types in this class have a lock-free strongly linearizable implementation from atomic registers.

关键词： distributed algorithms shared memory strong linearizability snapshots ABA lock-freedom

来源：评论

学校读者我要写书评

暂无评论

distributed Fault Diagnosis in Discrete Event Systems via Set Intersection Refinements

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2018年第10期63卷 3601-3607页

作者： Keroglou, Christoforos Hadjicostis, Christoforos N. Univ Cyprus Dept Elect & Comp Engn CY-1678 Nicosia Cyprus Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

We extend and verify diagnosability for a class of set intersection refinement strategies, which can be used for distributed state estimation and fault diagnosis in nondeterministic finite automata that are observed at multiple observation sites. These strategies allow observation sites to (periodically) communicate their diagnostic information (i.e., possible states along with corresponding status, such as normal operation and/or fault type) to other observation sites, which subsequently fuse all available diagnostic information (via set intersection operations), and continue operation based on the refined diagnostic information. We verify diagnosability using the proposed distributed protocol, with polynomial complexity, via compositions of (extended versions of) local verifiers, which are capable of capturing the refinement of information under the set intersection operations, as well as the influence of the refinement process on immediate or future diagnosis decisions.

关键词： Discrete event systems distributed algorithms distributed diagnosis fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Jointly Compressing and Caching Data in Wireless Sensor Networks 5

Jointly Compressing and Caching Data in Wireless Sensor Netw...

引用

5th IEEE International Conference on Smart Computing (SMARTCOMP)

作者： Panigrahy, Nitish K. Li, Jian Zafari, Faheem Towsley, Don Yu, Paul Univ Massachusetts Amherst MA 01003 USA Imperial Coll London London England US Army Res Lab Adelphi MD USA

ISBN: (纸本)9781728116891

We propose a novel policy for data compression and caching in a wireless sensor network (WSN) that provably optimizes utility and cost jointly, providing a theoretical basis to understand the compression-caching tradeoff for data analytics in a WSN. Our optimization framework provides analytical answers to how much compression should be performed at each sensor, and where the data should be cached in the network. We propose a distributed algorithm to implement the optimal policy and adapt to the changes (e.g., cache size and request processes) in the network. We evaluate our approach through extensive simulations on WSNs.

关键词： Wireless sensor networks Data compression Optimization Data analysis distributed algorithms Adaptation models Data integrity

来源：评论

学校读者我要写书评

暂无评论

Efficient Multiparty Interactive Coding for Insertions, Deletions, and Substitutions [Extended Abstract] 19

Efficient Multiparty Interactive Coding for Insertions, Dele...

引用

38th ACM Symposium on Principles of distributed Computing (PODC)

作者： Gelles, Ran Kalai, Yael Tauman Ramnarayan, Govind Bar Ilan Univ Ramat Gan Israel Microsoft Res Redmond WA USA MIT 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9781450362177

In the field of interactive coding, two or more parties wish to carry out a distributed computation over a communication network that may be noisy. The ultimate goal is to develop efficient coding schemes that can tolerate a high level of noise while increasing the communication by only a constant factor (i.e., constant rate). In this work we consider synchronous communication networks over an arbitrary topology, in the powerful adversarial insertion-deletion noise model. Namely, the noisy channel may adversarially alter the content of any transmitted symbol, as well as completely remove a transmitted symbol or inject a new symbol into the channel. We provide efficient, constant rate schemes that successfully conduct any computation with high probability as long as the adversary corrupts at most epsilon/m fraction of the total communication, where m is the number of links in the network and epsilon is a small constant. This scheme assumes an oblivious adversary which is independent of the parties' inputs and randomness. We can remove this assumption and resist a worst-case adversary at the price of being resilient to epsilon/m log m errors. While previous work considered the insertion-deletion noise model in the two-party setting, to the best of our knowledge, our scheme is the first multiparty scheme that is resilient to insertions and deletions. Furthermore, our scheme is the first computationally efficient scheme in the multiparty setting that is resilient to adversarial noise.

关键词： interactive coding distributed algorithms error correcting codes

来源：评论

学校读者我要写书评

暂无评论

Topology Distribution for Video-Conferencing Applications 10

Topology Distribution for Video-Conferencing Applications

引用

10th IEEE International Conference on Networks of the Future (NoF)

作者： Altamirano Silva, Mauricio Bertone, Raul Schaefer, Joerg Frankfurt Univ Appl Sci Fac Comp Sci & Engn Nibelungenpl 1 D-60318 Frankfurt Germany

ISBN: (纸本)9781728144450

We describe an architecture and an implementation to support arbitrary real-time video and audio conferences (or any other streaming applications) based on WebRTC. Our solution makes use of a hybrid approach where the media streams are distributed over a peer-to-peer (P2P) architecture and the control data is coordinated using a centralized service. It is based on a topology-distance algorithm developed by one of the authors to optimize latency and other QoS metrics. It also makes use of an open source protocol developed by the authors - the Adaptive Topology Orchestration Protocol (ATOP), which is described in a forthcoming publication. Our architecture comprises a modular design to support a flexible approach addressing the different requirements of several use cases such as broadcast, many-to-many and one-to-one or a mixture between any of these. We compare our architecture and its performance to existing alternative approaches to support our design choices. The performance figures presented deliver also important information about the scalability of our approach.

关键词： distributed algorithms peer-to-peer geolocation WebRTC WebSocket overlay multicast tree videoconference

来源：评论

学校读者我要写书评

暂无评论

Massively Parallel Computation via Remote Memory Access 19

Massively Parallel Computation via Remote Memory Access

引用

31st ACM Symposium on Parallelism in algorithms and Architecturess (SPAA)

作者： Behnezhad, Soheil Dhulipala, Laxman Esfandiari, Hossein Lacki, Jakub Mirrokni, Vahab Schudy, Warren Univ Maryland College Pk MD 20742 USA CMU Pittsburgh PA USA Google New York NY USA

ISBN: (纸本)9781450361842

We introduce the Adaptive Massively Parallel Computation (AMPC) model, which is an extension of the widely popular Massively Parallel Computation (MPC) model. At a high level, the AMPC model strengthens the MPC model by storing all messages sent within a round in a distributed data store. In the following round all machines are provided with random read access to the data store, subject to the same constraints on the total amount of communication as in the MPC model. Our model is inspired by the previous empirical studies of distributed graph algorithms [9, 28] using MapReduce and a distributed hash table service [17]. This extension allows us to give new graph algorithms with much lower round complexities compared to the best known solutions in the MPC model. In particular, in the AMPC model we show how to solve maximal independent set in O(1) rounds, and connectivity/minimum spanning tree in O(log log(m/n) n) rounds, which is an exponential improvement upon the best known algorithms in the MPC model with sublinear space per machine. Our results imply that the 2-Cycle conjecture, the most popular hardness conjecture in the MPC model, does not hold in the AMPC model.

关键词： distributed algorithms graph algorithms massively parallel computation remote memory access

来源：评论

学校读者我要写书评

暂无评论

Data Mining algorithms Parallelization in Logic Programming Framework for Execution in Cluster 19th

Data Mining Algorithms Parallelization in Logic Programming ...

引用

19th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems (NEW2AN) / 12th Conference on the Internet of Things and Smart Spaces ruSMART (Are You Smart)

作者： Malov, Aleksey Rodionov, Sergey Shorov, Andrey St Petersburg Electrotech Univ LETI St Petersburg Russia

This article describes an approach to parallelizing of data mining algorithms in logical programming framework, for distributed data processing in cluster. As an example Naive Bayes algorithm implementation in Prolog ... 详细信息

ISBN: (纸本)9783030308599;9783030308582

关键词： Parallel algorithms distributed algorithms Data mining distributed data mining MapReduce Logical programming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：