Proceedings of the 20th International Conference on Distributed Computing and Networking最新文献_第2页

Sublinear-time mutual visibility for fat oblivious robots 肥胖遗忘机器人的亚线性时间互可见性

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288602

Pavan Poudel, Gokarna Sharma, Aisha Aljohani

引用次数: 9

Reconfigurable dataflow graphs for processing-in-memory 用于内存处理的可重构数据流图

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288605

C. Shelor, K. Kavi

{"title":"Reconfigurable dataflow graphs for processing-in-memory","authors":"C. Shelor, K. Kavi","doi":"10.1145/3288599.3288605","DOIUrl":"https://doi.org/10.1145/3288599.3288605","url":null,"abstract":"In order to meet the ever-increasing speed differences between processor clocks and memory access times, there has been an interest in moving computation closer to memory. The near data processing or processing-in-memory is particularly suited for very high bandwidth memories such as the 3D-DRAMs. There are different ideas proposed for PIMs, including simple in-order processors, GPUs, specialized ASICs and reconfigurable designs. In our case, we use Coarse-Grained Reconfigurable Logic to build dataflow graphs for computational kernels as the PIM. We show that our approach can achieve significant speedups and save energy consumed by computations. We evaluated our designs using several processing technologies for building the coarse-gained logic units. The DFPIM concept showed good performance improvement and excellent energy efficiency for the streaming benchmarks that were analyzed. The DFPIM in a 28 nm process with an implementation in each of 16 vaults of a 3D-DRAM logic layer showed an average speed-up of 7.2 over that using 32 cores of an Intel Xeon server system. The server processor required 368 times more energy to execute the benchmarks than the DFPIM implementation.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130435328","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}

引用次数: 2

To protect ecological system from electromagnetic radiation of mobile communication 保护生态系统免受移动通信的电磁辐射

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3295595

Avirup Das, Srabani Kundu

{"title":"To protect ecological system from electromagnetic radiation of mobile communication","authors":"Avirup Das, Srabani Kundu","doi":"10.1145/3288599.3295595","DOIUrl":"https://doi.org/10.1145/3288599.3295595","url":null,"abstract":"The ever-increasing use of mobile phones, IoT, and the related infrastructures like wireless access points and mobile base stations is becoming a prominent source of non-ionizing electromagnetic field (EMF) having some harmful effects on our ecology. In this work, the effect of the non-ionizing electromagnetic radiation of BTS (Base Transceiver Station) and the Wi-Fi access points on our ecological system has been investigated over frequency band 900 MHz to 2500 MHz. A testbed is designed utilizing sensors to measure the EMF strength over a given region, and a heat map is generated. Using the standard safe limit of specific absorption rate (SAR) this heat map may enable us to issue alerts whenever the measured EMF exceeds the SAR limit. The stream of data from these sensors may be uploaded on a cloud to implement an adaptive transmitter power control mechanism to reduce the signal strength dynamically to maintain the safe limit of SAR. A modular design is proposed to implement a cloud-based transmission power control mechanism that can be applied for BTS as well as Wi-Fi routers in cellular networks.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129222388","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}

引用次数: 3

Multi-tenant mobile offloading systems for real-time computer vision applications 用于实时计算机视觉应用的多租户移动卸载系统

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288634

Zhou Fang, Jeng-Hau Lin, M. Srivastava, Rajesh K. Gupta

{"title":"Multi-tenant mobile offloading systems for real-time computer vision applications","authors":"Zhou Fang, Jeng-Hau Lin, M. Srivastava, Rajesh K. Gupta","doi":"10.1145/3288599.3288634","DOIUrl":"https://doi.org/10.1145/3288599.3288634","url":null,"abstract":"Offloading techniques enable many emerging computer vision applications on mobile platforms by executing compute-intensive tasks on resource-rich servers. Although there have been a significant amount of research efforts devoted in optimizing mobile offloading frameworks, most previous works are evaluated in a single-tenant setting, that is, a server is assigned to a single client. However, in a practical scenario that servers must handle tasks from many clients running diverse applications, contention on shared server resources may degrade application performance. In this work, we study scheduling techniques to improve serving performance in multi-tenant mobile offloading systems, for computer vision algorithms running on CPUs and deep neural networks (DNNs) running on GPUs. For CPU workloads, we present methods to mitigate resource contention and to improve delay using a Plan-Schedule approach. The planning phase predicts future workloads from all clients, estimates contention, and adjusts future task start times to remove or reduce contention. The scheduling phase dispatches arriving offloaded tasks to the server that minimizes contention. For DNN workloads running on GPUs, we propose adaptive batching algorithms using information of batch size, model complexity and system load to achieve the best Quality of Service (QoS), which are measured from accuracy and delay of DNN tasks. We demonstrate the improvement of serving performance using several real-world applications with different server deployments.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"17 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116708643","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}

引用次数: 9

Scheduling virtual wifi interfaces for high bandwidth video upstreaming using multipath TCP 调度虚拟wifi接口，使用多路径TCP实现高带宽视频上行

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288620

Shobhi Maheshwari, Philip Lundrigan, S. Kasera

{"title":"Scheduling virtual wifi interfaces for high bandwidth video upstreaming using multipath TCP","authors":"Shobhi Maheshwari, Philip Lundrigan, S. Kasera","doi":"10.1145/3288599.3288620","DOIUrl":"https://doi.org/10.1145/3288599.3288620","url":null,"abstract":"Live video upstreaming refers to the flow of live data in the upstream direction from mobile devices to other entities across the Internet and has found use in many modern applications such as remote driving, the recent social media trend of live video broadcasting along with the traditional applications of video calling/conferencing. Combined with the high definition video capturing capabilities of modern mobile devices, live video upstreaming is creating more upstream data traffic then what present day cellular networks are equipped to support, often resulting in sub-optimal video experience, especially in remote or crowded areas with low cellular connectivity and no WiFi. We propose that instead of using its single cellular connection, a mobile device connects to multiple nearby mobile devices and splits the live video data over the cellular bandwidth of these devices using Multipath TCP protocol. The use of MPTCP, for upstreaming live video data, has largely remained unexplored especially for scenarios where WiFi connectivity is not available. We use wireless interface virtualization, offered by Linux, to enable Multipath TCP to scale and connect to a large number of cellular devices. We design and build a system that is able to assess the instantaneous bandwidth of all the connected cellular devices/hotspots and uses the set of the most capable cellular devices for splitting and forwarding the live video data. We test our system in various settings and our experiments show that our system greatly increases the bandwidth and reliability of TCP connections in most cases and in cases where there is a significant difference in the throughput across cellular hotspots, our solution is able to recognize and isolate the better performing cellular hotspots to provide a stable throughput.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121722914","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}

引用次数: 0

Improving efficacy of concurrent internal binary search trees using local recovery 利用局部恢复提高并发内部二叉搜索树的效率

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288615

Arunmoezhi Ramachandran, N. Mittal

{"title":"Improving efficacy of concurrent internal binary search trees using local recovery","authors":"Arunmoezhi Ramachandran, N. Mittal","doi":"10.1145/3288599.3288615","DOIUrl":"https://doi.org/10.1145/3288599.3288615","url":null,"abstract":"Binary Search Tree (BST) is an important data structure for managing ordered data. Many algorithms have been proposed for concurrent manipulation of a binary search tree in an asynchronous shared memory system that supports search, insert and delete operations based on both external and internal representations of a search tree. An important step in executing an operation on a tree is to traverse the tree from top-to-down in order to locate the operation's window. A process may need to perform this traversal several times to handle failures occurring due to other processes performing concurrent updates on the tree. Most concurrent algorithms that have been proposed so far use a naïve approach and simply restart the traversal from the root of the tree. In this work, we present a new approach to recover from such failures more efficiently for certain types of concurrent binary search tree algorithms using local recovery by restarting the traversal from the \"middle\" of the tree in order to locate an operation's window (tree section of interest). Our approach is sufficiently general in the sense that it can be applied to most of the existing concurrent binary search trees using internal representation based on both blocking as well as non-blocking approaches. Using experimental evaluation, we demonstrate that our local recovery approach can significantly improve the performance of a concurrent internal BST by up to 124.7% when the contention is high.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"63 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114045146","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}

引用次数: 0

Majority vote and monopolies in social networks 多数投票和垄断社交网络

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288633

C. Avin, Zvi Lotker, Assaf Mizrachi, D. Peleg

{"title":"Majority vote and monopolies in social networks","authors":"C. Avin, Zvi Lotker, Assaf Mizrachi, D. Peleg","doi":"10.1145/3288599.3288633","DOIUrl":"https://doi.org/10.1145/3288599.3288633","url":null,"abstract":"Occasionaly, every society needs to reach a decision among its members. For this, it may use a voting mechanism, i.e., collect the votes of the group members and output a decision that best expresses the group's will. To make up their minds, individuals often discuss the issue with friends before taking their votes, thus mutually affecting each other's votes. Individuals are also, to some extent, influenced by the opinions of key figures in their culture, such as politicians, publicists, etc., commonly considered as the \"elite\" of the society. This work studies the \"power of the elite\": to what extent can the elite of a social network influence the rest of society to accept its opinion, and thus become a monopoly. We present an empirical study of local majority voting in social networks, where the elite forms a coalition against all other (common) nodes. The results, obtained on several social networks, indicate that an elite of size [MATH HERE] (where m is the number of connections) has disproportionate power, relative to its size, with respect to the rest of society: it wins the majority voting and remains stable over time.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132561216","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}

引用次数: 10

An efficient user privacy preserving multi-server private information retrieval: an efficient privacy preserving information storage and retrieval framework 一种高效的用户隐私保护多服务器隐私信息检索:一种高效的隐私保护信息存储与检索框架

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3299724

Radhakrishna Bhat, N. Sunitha

引用次数: 0

Flocking along line by autonomous oblivious mobile robots 自主遗忘移动机器人沿直线聚集

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3295583

S. Chaudhuri

{"title":"Flocking along line by autonomous oblivious mobile robots","authors":"S. Chaudhuri","doi":"10.1145/3288599.3295583","DOIUrl":"https://doi.org/10.1145/3288599.3295583","url":null,"abstract":"Swarm robot is a collection of tiny identical autonomous mobile robots who collaboratively perform a given task. One of the main objectives of swarm robots is to place themselves on a geographic region forming a particular geometric pattern in order to execute some jobs in cooperation, e.g., covering or guarding a region, moving a big object. This paper proposes a deterministic distributed algorithm for a set of tiny disc shaped swarm robots (also known as fat robots) to form a straight line and then moving this line by coordinating the motion of the robots. This phenomenon of moving of robots while maintaining the straight line formation, is known as Flocking of robots. The robots are homogeneous, autonomous, anonymous. They need very less computational power. They sense their surrounding, compute destinations to move to and move there. They do not have any explicit message sending or receiving capability. They forget their past sensed and computed data. The robots do not agree on any global coordinate system or origin. The robots are not aware of the total number of robots in the system. All these disabilities of the robots make them less expensive in cost as well as simple in software and hardware requirements. The algorithm presented in this paper assures collision free movements of the robots.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133236426","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}

引用次数: 2

Perfectly secure message transmission over partially synchronous networks 在部分同步网络上完全安全的消息传输

Proceedings of the 20th International Conference on Distributed Computing and Networking Pub Date : 2019-01-04 DOI: 10.1145/3288599.3288612

R. Kishore, Anupriya Inumella, K. Srinathan

{"title":"Perfectly secure message transmission over partially synchronous networks","authors":"R. Kishore, Anupriya Inumella, K. Srinathan","doi":"10.1145/3288599.3288612","DOIUrl":"https://doi.org/10.1145/3288599.3288612","url":null,"abstract":"In a distributed network, we consider two special nodes called the sender S and the receiver R that are connected by n node-disjoint (except for S and R) bi-directional wires. Out of these n wires, the adversary can control at most t wires (of its choice) in Byzantine fashion. In this setting, our goal is to design a message transmission protocol Π that assures the following two conditions hold: (1) by the end of the protocol Π, R gets the correct message m transmitted by S without any error (perfect reliability), and (2) the adversary learns no information about m, whatsoever, in information theoretic sense (perfect secrecy). Protocols that satisfy these two conditions are known as the Perfectly Secure Message Transmission (PSMT) protocols. However, out of the n wires that exist, if some number of wires say ns, fortunately, happen to be synchronous (serendipitous synchrony) then we ask under what conditions do PSMT protocols tolerating t-Byzantine faults exist. In the literature, it is known that, if either ns > 2t or n > 3t then PSMT protocols trivially exist. Therefore, we consider the case where we have at most 2t synchronous wires (i.e., ns ≤ 2t) and at most 3t wires overall (i.e., n ≤ 3t). Interestingly, we prove that in this case, no PSMT protocol exists. This concludes that, in designing PSMT protocols (tolerating the given fixed number of faults), either (serendipitous) synchronous wires alone are sufficient or we get absolutely no extra advantage of a wire being synchronous over asynchronous.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116400636","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}

引用次数: 1