Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00117
Xuanzhe Li, Samuel Gomena, L. Ballard, Juntao Li, Ehsan Aryafar, Carlee Joe-Wong
Data generated by increasingly pervasive and intelligent devices has led to an explosion in the use of machine learning (ML) and artificial intelligence, with ever more complex models trained to support applications in fields as diverse as healthcare, finance, and robotics. In order to train these models in a reasonable amount of time, the training is often distributed among multiple machines. However, paying for these machines (either by constructing a local cloud infrastructure or renting machines through an external provider such as Amazon AWS) is very costly. We propose to reduce these costs by creating a marketplace of computing resources designed to support distributed machine learning algorithms. Through our marketplace (coined “DeepMarket”), users can lend their spare computing resources (when not needed) or augment their resources with available DeepMarket machines to train their ML models. Such a marketplace directly provides several benefits for two groups of researchers: (i) ML researchers would be able to train their models with much reduced cost, and (ii) network economics researchers would be able to experiment with different compute pricing mechanisms. The focus of this Demo is to introduce the audience to DeepMarket and its user interface (named “PLUTO”). In particular, we will bring a few laptops with pre-installed PLUTO applications so that users can see how they can create an account on DeepMarket servers, lend their resource, borrow available resources, submit ML jobs, and retrieve the results. Our overall goal is to encourage the conference audience to install PLUTO on their own machines and create a user and developer community around DeepMarket.
{"title":"A Community Platform for Research on Pricing and Distributed Machine Learning","authors":"Xuanzhe Li, Samuel Gomena, L. Ballard, Juntao Li, Ehsan Aryafar, Carlee Joe-Wong","doi":"10.1109/ICDCS47774.2020.00117","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00117","url":null,"abstract":"Data generated by increasingly pervasive and intelligent devices has led to an explosion in the use of machine learning (ML) and artificial intelligence, with ever more complex models trained to support applications in fields as diverse as healthcare, finance, and robotics. In order to train these models in a reasonable amount of time, the training is often distributed among multiple machines. However, paying for these machines (either by constructing a local cloud infrastructure or renting machines through an external provider such as Amazon AWS) is very costly. We propose to reduce these costs by creating a marketplace of computing resources designed to support distributed machine learning algorithms. Through our marketplace (coined “DeepMarket”), users can lend their spare computing resources (when not needed) or augment their resources with available DeepMarket machines to train their ML models. Such a marketplace directly provides several benefits for two groups of researchers: (i) ML researchers would be able to train their models with much reduced cost, and (ii) network economics researchers would be able to experiment with different compute pricing mechanisms. The focus of this Demo is to introduce the audience to DeepMarket and its user interface (named “PLUTO”). In particular, we will bring a few laptops with pre-installed PLUTO applications so that users can see how they can create an account on DeepMarket servers, lend their resource, borrow available resources, submit ML jobs, and retrieve the results. Our overall goal is to encourage the conference audience to install PLUTO on their own machines and create a user and developer community around DeepMarket.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130261013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00163
Sangwon Hong, Yoongdoo Noh, Jeyoung Hwang, Chanik Park
Business is innovating with the advent of blockchain that tokenizes digital assets. To expand the blockchain’s potential, Ethereum, a representative permissionless blockchain platform, supports the fungible token (FT) standard ERC-20 and the nonfungible token (NFT) standard ERC-721. Hyperledger Fabric (Fabric), a representative permissioned blockchain platform, proposed FabToken to support tokens in version 2.0.0 alpha. But FabToken contains only FTs, not NFTs. Given the market share in the enterprise blockchains, Fabric needs to support NFTs as soon as possible. This paper presents a unique digital asset management system called FabAsset so that Fabric can run decentralized applications that require NFTs. This paper describes the design of FabAsset, consisting of chaincode and SDK (Software Development Kit), and the prototype of a decentralized signature service leveraging FabAsset to validate its usefulness.
{"title":"FabAsset: Unique Digital Asset Management System for Hyperledger Fabric","authors":"Sangwon Hong, Yoongdoo Noh, Jeyoung Hwang, Chanik Park","doi":"10.1109/ICDCS47774.2020.00163","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00163","url":null,"abstract":"Business is innovating with the advent of blockchain that tokenizes digital assets. To expand the blockchain’s potential, Ethereum, a representative permissionless blockchain platform, supports the fungible token (FT) standard ERC-20 and the nonfungible token (NFT) standard ERC-721. Hyperledger Fabric (Fabric), a representative permissioned blockchain platform, proposed FabToken to support tokens in version 2.0.0 alpha. But FabToken contains only FTs, not NFTs. Given the market share in the enterprise blockchains, Fabric needs to support NFTs as soon as possible. This paper presents a unique digital asset management system called FabAsset so that Fabric can run decentralized applications that require NFTs. This paper describes the design of FabAsset, consisting of chaincode and SDK (Software Development Kit), and the prototype of a decentralized signature service leveraging FabAsset to validate its usefulness.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"54 18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126843822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00070
Tuo Shi, Zhipeng Cai, Jianzhong Li, Hong Gao
In a Device-to-Device (D2D) mobile edge computing system, the mobile devices can share computation and communication resources with each other. A mobile device can offload its computation task to a nearby mobile device. In order to release the computation workload of mobile edge servers and enhance the mobile edge service coverage quality, a set of mobile devices can be selected as sub-servers and provide mobile edge service to nearby devices. Based on the crowdsourcing technique, we have proposed a framework, CROSS, to select sub-servers in a D2D enhanced mobile edge computing system. Two major problems in CROSS framework, the sub-server selection problem and the payoff allocation problem, have been formulated. The first problem is proved to be NP-Hard and solved by an approximation algorithm. The second problem is solved by an auction mechanism. The performance of the CROSS framework is evaluated by experiments. The experimental results show that the CROSS framework is efficient and effective.
{"title":"CROSS: A Crowdsourcing based Sub-Servers Selection Framework in D2D Enhanced MEC Architecture","authors":"Tuo Shi, Zhipeng Cai, Jianzhong Li, Hong Gao","doi":"10.1109/ICDCS47774.2020.00070","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00070","url":null,"abstract":"In a Device-to-Device (D2D) mobile edge computing system, the mobile devices can share computation and communication resources with each other. A mobile device can offload its computation task to a nearby mobile device. In order to release the computation workload of mobile edge servers and enhance the mobile edge service coverage quality, a set of mobile devices can be selected as sub-servers and provide mobile edge service to nearby devices. Based on the crowdsourcing technique, we have proposed a framework, CROSS, to select sub-servers in a D2D enhanced mobile edge computing system. Two major problems in CROSS framework, the sub-server selection problem and the payoff allocation problem, have been formulated. The first problem is proved to be NP-Hard and solved by an approximation algorithm. The second problem is solved by an auction mechanism. The performance of the CROSS framework is evaluated by experiments. The experimental results show that the CROSS framework is efficient and effective.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125177592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00181
Zhiwen Fang, Zhou Yue, Weiyuan Liu, Feng Yang
Video anomaly detection is tasked with the identification of events that do not conform to expected events. Currently, most methods tackle this problem by mining common normal patterns from training data and minimizing the generative errors. In inference phase, a large generative error is assigned to an abnormal event and a small one is for a normal event. However, because these methods only focus on the error intensity but ignore the error pattern, partial abnormal events will own similar generative error intensities to the normal ones. Thus, we propose to tackle the anomaly detection within an efficient image denoising framework. In this framework, the generative errors are treated as a kind of artificial noise, which will be superimposed on the current frame. Then, the contaminated frame is fed into a denoising network, which is trained to output a frame close to the current frame. In the denoising network, the common patterns of training data and the error patterns of each training frame can be learned jointly. It will benefit anomaly detection by restraining the generative errors of normal frames. The results on several challenging benchmark datasets demonstrate the effectiveness of our proposed method.
{"title":"Image Denoising for Efficient Anomaly Detection in Videos","authors":"Zhiwen Fang, Zhou Yue, Weiyuan Liu, Feng Yang","doi":"10.1109/ICDCS47774.2020.00181","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00181","url":null,"abstract":"Video anomaly detection is tasked with the identification of events that do not conform to expected events. Currently, most methods tackle this problem by mining common normal patterns from training data and minimizing the generative errors. In inference phase, a large generative error is assigned to an abnormal event and a small one is for a normal event. However, because these methods only focus on the error intensity but ignore the error pattern, partial abnormal events will own similar generative error intensities to the normal ones. Thus, we propose to tackle the anomaly detection within an efficient image denoising framework. In this framework, the generative errors are treated as a kind of artificial noise, which will be superimposed on the current frame. Then, the contaminated frame is fed into a denoising network, which is trained to output a frame close to the current frame. In the denoising network, the common patterns of training data and the error patterns of each training frame can be learned jointly. It will benefit anomaly detection by restraining the generative errors of normal frames. The results on several challenging benchmark datasets demonstrate the effectiveness of our proposed method.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128155794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00095
S. Maheshwari, P. Netalkar, D. Raychaudhuri
This paper presents a novel control plane protocol designed to enable cooperative resource sharing in heterogeneous edge cloud scenarios. While edge clouds offer the advantage of potentially lower latency for time critical applications, computing load generated by mobile users at the network edge can be very bursty as compared with aggregated traffic served by a data center. This motivates the design of a shared control plane which enables dynamic resource sharing between edge clouds in a region. The proposed control plane is designed to exchange key compute and network parameters (such as CPU GIPS, % utilization, and network bandwidth) needed for cooperation between heterogeneous edge clouds across network domains. The protocol thus enables sharing mechanisms such as dynamic resource assignment, compute offloading, load balancing, multi-node orchestration, and service migration. A specific distributed control plane (DISCO) based on overlay neighbor distribution with hop-count limit is described and evaluated in terms of control overhead and performance using an experimental proto-type running on the ORBIT radio grid testbed. The prototype system implements a heterogeneous network with 18 autonomous systems each with a compute cluster that participates in the control plane protocol and executes specified resource sharing algorithms. Experimental results are given comparing the performance of the baseline with no cooperation to that of cooperative algorithms for compute offloading, cluster computing and service chaining. An application level evaluation of latency vs. offered load is also carried out for an example time-critical application (image analysis for traffic lane detection). The results show significant performance gains (as much as 45% for the cluster computing example) vs. the no cooperation baseline in each case at the cost of relatively modest complexity and overhead.
{"title":"DISCO: Distributed Control Plane Architecture for Resource Sharing in Heterogeneous Mobile Edge Cloud Scenarios","authors":"S. Maheshwari, P. Netalkar, D. Raychaudhuri","doi":"10.1109/ICDCS47774.2020.00095","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00095","url":null,"abstract":"This paper presents a novel control plane protocol designed to enable cooperative resource sharing in heterogeneous edge cloud scenarios. While edge clouds offer the advantage of potentially lower latency for time critical applications, computing load generated by mobile users at the network edge can be very bursty as compared with aggregated traffic served by a data center. This motivates the design of a shared control plane which enables dynamic resource sharing between edge clouds in a region. The proposed control plane is designed to exchange key compute and network parameters (such as CPU GIPS, % utilization, and network bandwidth) needed for cooperation between heterogeneous edge clouds across network domains. The protocol thus enables sharing mechanisms such as dynamic resource assignment, compute offloading, load balancing, multi-node orchestration, and service migration. A specific distributed control plane (DISCO) based on overlay neighbor distribution with hop-count limit is described and evaluated in terms of control overhead and performance using an experimental proto-type running on the ORBIT radio grid testbed. The prototype system implements a heterogeneous network with 18 autonomous systems each with a compute cluster that participates in the control plane protocol and executes specified resource sharing algorithms. Experimental results are given comparing the performance of the baseline with no cooperation to that of cooperative algorithms for compute offloading, cluster computing and service chaining. An application level evaluation of latency vs. offered load is also carried out for an example time-critical application (image analysis for traffic lane detection). The results show significant performance gains (as much as 45% for the cluster computing example) vs. the no cooperation baseline in each case at the cost of relatively modest complexity and overhead.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132940513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00057
K. Konwar, Saptaparni Kumar, Lewis Tseng
Shared register emulations on top of message-passing systems provide an illusion of a simpler shared memory system which can make the task of a system designer easier. Numerous shared register applications have a considerably high read-to-write ratio. Thus, having algorithms that make reads more efficient than writes is a fair trade-off.Typically, such algorithms for reads and writes are asymmetric and sacrifice the stringent consistency condition atomicity, as it is impossible to have fast reads for multi-writer atomicity. Safety is a consistency condition that has has gathered interest from both the systems and theory community as it is weaker than atomicity yet provides strong enough guarantees like "strong consistency" or read-my-write consistency. One requirement that is assumed by many researchers is that of the reliable broadcast (RB) primitive, which ensures the "all or none" property during a broadcast. One drawback is that such a primitive takes 1.5 rounds to complete and requires server-to-server communication.This paper implements an efficient multi-writer multi-reader safe register without using a reliable broadcast primitive. Moreover, we provide fast reads or one-shot reads – our read operations can be completed in one round of client-to-server communication. Of course, this comes with the price of requiring more servers when compared to prior solutions assuming reliable broadcast. However, we show that this increased number of servers is indeed necessary as we prove a tight bound on the number of servers required to implement Byzantine-fault tolerant safe registers in a system without reliable broadcast.We extend our results to data stored using erasure coding as well. We present an emulation of single-writer multi-reader safe register based on MDS codes. The usage of MDS codes reduces storage and communication costs. On the negative side, we also show that to use MDS codes and at the same time achieve one-shot reads, we need even more servers.
{"title":"Semi-Fast Byzantine-tolerant Shared Register without Reliable Broadcast","authors":"K. Konwar, Saptaparni Kumar, Lewis Tseng","doi":"10.1109/ICDCS47774.2020.00057","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00057","url":null,"abstract":"Shared register emulations on top of message-passing systems provide an illusion of a simpler shared memory system which can make the task of a system designer easier. Numerous shared register applications have a considerably high read-to-write ratio. Thus, having algorithms that make reads more efficient than writes is a fair trade-off.Typically, such algorithms for reads and writes are asymmetric and sacrifice the stringent consistency condition atomicity, as it is impossible to have fast reads for multi-writer atomicity. Safety is a consistency condition that has has gathered interest from both the systems and theory community as it is weaker than atomicity yet provides strong enough guarantees like \"strong consistency\" or read-my-write consistency. One requirement that is assumed by many researchers is that of the reliable broadcast (RB) primitive, which ensures the \"all or none\" property during a broadcast. One drawback is that such a primitive takes 1.5 rounds to complete and requires server-to-server communication.This paper implements an efficient multi-writer multi-reader safe register without using a reliable broadcast primitive. Moreover, we provide fast reads or one-shot reads – our read operations can be completed in one round of client-to-server communication. Of course, this comes with the price of requiring more servers when compared to prior solutions assuming reliable broadcast. However, we show that this increased number of servers is indeed necessary as we prove a tight bound on the number of servers required to implement Byzantine-fault tolerant safe registers in a system without reliable broadcast.We extend our results to data stored using erasure coding as well. We present an emulation of single-writer multi-reader safe register based on MDS codes. The usage of MDS codes reduces storage and communication costs. On the negative side, we also show that to use MDS codes and at the same time achieve one-shot reads, we need even more servers.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130498551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00067
Zhijun Li, Yongrui Chen
Today’s wireless networks have become increasingly heterogenous, mobile and dense. To satisfy the rising demands of ubiquitous connections, billions of multi-radio gateways have to be deployed, inevitably incurring high deployment cost and extra traffic overhead. Recent advances on Cross-Technology Communication (CTC) have shown its ability to avoid these drawbacks. However, the state-of-the-art CTCs from Bluetooth to WiFi, two of the most popular wireless techniques, still suffer from low data-rate (e.g., 3.1Kbps), which severely restricts their applicability. We present BlueFi, the first physical-layer CTC (PHY-CTC) from Bluetooth Low Energy (BLE) to WiFi, which enables high throughput, bidirectional and parallel transmissions between BLE and WiFi via spectral analysis. The key observation is that commodity WiFi chipsets can operate in the spectral analysis mode, in which WiFi can recognize specific BLE signal waveforms in frequency domain at symbol-level granularity. Leveraging this feature, we manufacture desired waveforms by choosing frame payload at BLE side, and observe spectral patterns at WiFi side. To achieve bidirectional links, we design a PHY-CTC method from WiFi to BLE based on signal emulation. We implement our prototype on USRP (with 802.11g PHY) and commodity BLE devices. Extensive evaluations show that BlueFi can achieve 120Kbps per link from BLE to WiFi with more than 95% frame reception ratio, over 38x faster than state-of-the-art CTCs. Moreover, BlueFi can support 9 wireless links in parallel, leading to the total throughput over 1Mbps.
{"title":"BlueFi: Physical-layer Cross-Technology Communication from Bluetooth to WiFi","authors":"Zhijun Li, Yongrui Chen","doi":"10.1109/ICDCS47774.2020.00067","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00067","url":null,"abstract":"Today’s wireless networks have become increasingly heterogenous, mobile and dense. To satisfy the rising demands of ubiquitous connections, billions of multi-radio gateways have to be deployed, inevitably incurring high deployment cost and extra traffic overhead. Recent advances on Cross-Technology Communication (CTC) have shown its ability to avoid these drawbacks. However, the state-of-the-art CTCs from Bluetooth to WiFi, two of the most popular wireless techniques, still suffer from low data-rate (e.g., 3.1Kbps), which severely restricts their applicability. We present BlueFi, the first physical-layer CTC (PHY-CTC) from Bluetooth Low Energy (BLE) to WiFi, which enables high throughput, bidirectional and parallel transmissions between BLE and WiFi via spectral analysis. The key observation is that commodity WiFi chipsets can operate in the spectral analysis mode, in which WiFi can recognize specific BLE signal waveforms in frequency domain at symbol-level granularity. Leveraging this feature, we manufacture desired waveforms by choosing frame payload at BLE side, and observe spectral patterns at WiFi side. To achieve bidirectional links, we design a PHY-CTC method from WiFi to BLE based on signal emulation. We implement our prototype on USRP (with 802.11g PHY) and commodity BLE devices. Extensive evaluations show that BlueFi can achieve 120Kbps per link from BLE to WiFi with more than 95% frame reception ratio, over 38x faster than state-of-the-art CTCs. Moreover, BlueFi can support 9 wireless links in parallel, leading to the total throughput over 1Mbps.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"85 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114030114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00124
M. Sallal, Steve A. Schneider, M. Casey, François Dupressoir, H. Treharne, Catalin Dragan, Luke Riley, Phil Wright
This paper discusses an approach for incremental change to an online voting system, introducing a verifiability layer based on the Selene protocol to a trusted-third-party-based system, resulting in a fully verifiable and transparent e-voting system. The paper also describes how to use Distributed Ledger Technology as a component of the implementation of Selene to manage the verifiability data in a distributed way for resilience and trust.
{"title":"Augmenting an Internet Voting System with Selene Verifiability using Permissioned Distributed Ledger","authors":"M. Sallal, Steve A. Schneider, M. Casey, François Dupressoir, H. Treharne, Catalin Dragan, Luke Riley, Phil Wright","doi":"10.1109/ICDCS47774.2020.00124","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00124","url":null,"abstract":"This paper discusses an approach for incremental change to an online voting system, introducing a verifiability layer based on the Selene protocol to a trusted-third-party-based system, resulting in a fully verifiable and transparent e-voting system. The paper also describes how to use Distributed Ledger Technology as a component of the implementation of Selene to manage the verifiability data in a distributed way for resilience and trust.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116501171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00022
Bharath Balasubramanian, P. Zave, R. Schlichting, Mohammad Salehe, S. Narayanan, S. H. Mortazavi, E. D. Lara, M. Hiltunen, Kaustubh R. Joshi, Gueyoung Jung
A crucial requirement for many multi-site production services operating at global scale is the need for exclusive access to latest state. Here, a novel approach to address these requirements through the abstraction of a critical section over geo-distributed state is proposed. This abstraction is realized in a key-value store called MUSIC, which provides critical sections with novel semantics suitable for geo-distributed state referred to as entry consistency under failures (ECF). The semantics of ECF in MUSIC, its formal verification, and its implementation are presented, along with details of how MUSIC has been used to realize various fundamental geo-distributed structuring paradigms. MUSIC has been deployed in production geo-distributed services at AT&T as part of the Open Network Automation Platform (ONAP). Our evaluation of MUSIC shows that, despite providing additional properties, MUSIC has higher throughput (~1.4-17.17 times) than Zookeeper for larger critical section sizes and outperforms (~2-4 times) similar structures in which state updates use Paxos or CockroachDB transactions.
{"title":"MUSIC: Multi-Site Critical Sections over Geo-Distributed State","authors":"Bharath Balasubramanian, P. Zave, R. Schlichting, Mohammad Salehe, S. Narayanan, S. H. Mortazavi, E. D. Lara, M. Hiltunen, Kaustubh R. Joshi, Gueyoung Jung","doi":"10.1109/ICDCS47774.2020.00022","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00022","url":null,"abstract":"A crucial requirement for many multi-site production services operating at global scale is the need for exclusive access to latest state. Here, a novel approach to address these requirements through the abstraction of a critical section over geo-distributed state is proposed. This abstraction is realized in a key-value store called MUSIC, which provides critical sections with novel semantics suitable for geo-distributed state referred to as entry consistency under failures (ECF). The semantics of ECF in MUSIC, its formal verification, and its implementation are presented, along with details of how MUSIC has been used to realize various fundamental geo-distributed structuring paradigms. MUSIC has been deployed in production geo-distributed services at AT&T as part of the Open Network Automation Platform (ONAP). Our evaluation of MUSIC shows that, despite providing additional properties, MUSIC has higher throughput (~1.4-17.17 times) than Zookeeper for larger critical section sizes and outperforms (~2-4 times) similar structures in which state updates use Paxos or CockroachDB transactions.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/ICDCS47774.2020.00107
Daping Li, Ji-guang Wan, Jun Wang, Jian Zhou, Kai Lu, Peng Xu, Fei Wu, C. Xie
The Intel Optane DC Persistent Memory Module (AEP), which is the first commercial available Non-Volatile Memory (NVM) product, offers comparable performance with DRAM while providing larger capacities and data persistence. Existing researches that substitute NVM with DRAM or hybridize them are either emulator-based or focused on how to improve the energy efficiency for writes. Unfortunately, the energy efficiency of the real AEP system is less explored. Based on real AEP, we observe that even though eliminating the DRAM-like refresh energy consumptions, AEP consumes significant different energy at different performance levels. Specifically, requests with time intervals (dispersed) underperform in both performance and energy efficiency when compared with the case of requests without time intervals (compact). This disparity and parallelism exploitation potentials motivate us to propose Sprint-AEP, an energy-efficiency-oriented scheduling method for AEP-equipped servers. Sprint-AEP fully activates adequate AEPs to serve most of the requests by deferring the write requests and prefetching the hottest data. The remaining AEPs will stay in idle mode with a low idle power to save energy. Besides, we also utilize the read parallelism to accelerate the sync and prefetching processes. Compared with energy-unaware AEP usages, our experimental results show that Sprint-AEP saves up to 26% energy with little performance degradation.
英特尔Optane DC Persistent Memory Module (AEP)是第一款商用非易失性内存(NVM)产品，在提供更大容量和数据持久性的同时，提供与DRAM相当的性能。现有的用DRAM替代NVM或混合它们的研究要么是基于仿真器的，要么是关注如何提高写入的能效。不幸的是，真正的AEP系统的能源效率很少被探索。基于实际的AEP，我们观察到，即使消除了类似dram的刷新能耗，AEP在不同性能水平上消耗的能量也有显著差异。具体来说，与没有时间间隔(紧凑)的请求相比，具有时间间隔(分散)的请求在性能和能源效率方面都表现不佳。这种差异和并行开发潜力促使我们提出了Sprint-AEP，这是一种针对配备aep的服务器的面向能效的调度方法。Sprint-AEP通过延迟写请求和预取最热的数据来充分激活足够的aep来服务大多数请求。剩余的aep将保持低空闲功率的空闲模式，以节省能源。此外，我们还利用读并行性来加速同步和预取过程。与不考虑能量的AEP使用相比，我们的实验结果表明，Sprint-AEP在性能下降很小的情况下节省了高达26%的能量。
{"title":"Disperse Access Considered Energy Inefficiency in Intel Optane DC Persistent Memory Servers","authors":"Daping Li, Ji-guang Wan, Jun Wang, Jian Zhou, Kai Lu, Peng Xu, Fei Wu, C. Xie","doi":"10.1109/ICDCS47774.2020.00107","DOIUrl":"https://doi.org/10.1109/ICDCS47774.2020.00107","url":null,"abstract":"The Intel Optane DC Persistent Memory Module (AEP), which is the first commercial available Non-Volatile Memory (NVM) product, offers comparable performance with DRAM while providing larger capacities and data persistence. Existing researches that substitute NVM with DRAM or hybridize them are either emulator-based or focused on how to improve the energy efficiency for writes. Unfortunately, the energy efficiency of the real AEP system is less explored. Based on real AEP, we observe that even though eliminating the DRAM-like refresh energy consumptions, AEP consumes significant different energy at different performance levels. Specifically, requests with time intervals (dispersed) underperform in both performance and energy efficiency when compared with the case of requests without time intervals (compact). This disparity and parallelism exploitation potentials motivate us to propose Sprint-AEP, an energy-efficiency-oriented scheduling method for AEP-equipped servers. Sprint-AEP fully activates adequate AEPs to serve most of the requests by deferring the write requests and prefetching the hottest data. The remaining AEPs will stay in idle mode with a low idle power to save energy. Besides, we also utilize the read parallelism to accelerate the sync and prefetching processes. Compared with energy-unaware AEP usages, our experimental results show that Sprint-AEP saves up to 26% energy with little performance degradation.","PeriodicalId":158630,"journal":{"name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128754225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：