2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)最新文献_第6页

Adaptive ViFi: A Dynamic Protocol for IoT Nodes in Challenged WiFi Network Conditions 自适应ViFi:挑战WiFi网络条件下物联网节点的动态协议

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00028

Dheryta Jaisinghani, Naman Gupta, Mukulika Maity, Vinayak S. Naik

{"title":"Adaptive ViFi: A Dynamic Protocol for IoT Nodes in Challenged WiFi Network Conditions","authors":"Dheryta Jaisinghani, Naman Gupta, Mukulika Maity, Vinayak S. Naik","doi":"10.1109/MASS50613.2020.00028","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00028","url":null,"abstract":"We address the problem of connecting IoT nodes to the Internet via challenged networks, which are characterized by minimal or intermittent network association. Examples of such networks can be found in forests with distant access points or in railway stations with overburdened access points. In such places, it is difficult for a node to establish and maintain an association with the access point. There exist several solutions that demonstrate the feasibility of data transfer using low bit-rate broadcast of discovery frames that do not necessitate association. We categorize them into a representative protocol called ViFi. However, the low bit-rate broadcast traffic hampers the performance of heavilyutilized networks by consuming significant airtime and resulting in a severe drop in goodput. We come up with a novel adaptive version of ViFi, Adaptive ViFi, that adapts to network conditions and intelligently selects a channel and an interval for the data transmission. In principle, our proposed solution is agnostic to WiFi standard, client, or AP in use. We develop an end-to-end working prototype on Raspberry Pi and hostapd-based access points. With a set of extensive experiments, we find that Adaptive ViFi gracefully addresses the limitations of ViFi in a heavily utilized network, at the same time it achieves up to 10.7x higher goodput than the ViFi. It co-exists well with other WiFi-based non-IoT clients with minimal impact on their goodput (4%). It scales well with a delivery rate of 77% and 50% with 150 and 300 nodes, respectively.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124406519","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

Multi-Agent Reinforcement Learning for Cooperative Edge Caching in Internet of Vehicles 基于多智能体强化学习的车联网协同边缘缓存

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00062

Kai Jiang, Huan Zhou, Deze Zeng, Jie Wu

{"title":"Multi-Agent Reinforcement Learning for Cooperative Edge Caching in Internet of Vehicles","authors":"Kai Jiang, Huan Zhou, Deze Zeng, Jie Wu","doi":"10.1109/MASS50613.2020.00062","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00062","url":null,"abstract":"Edge caching has been emerged as a promising solution to alleviate the redundant traffic and the content access latency in the future Internet of Vehicles (IoVs). Several Reinforcement Learning (RL) based edge caching methods have been proposed to improve the cache utilization and reduce the backhaul traffic load. However, they can only obtain the local sub-optimal solution, as they neglect the influence of environment by other agents. In this paper, we investigate the edge caching strategy with consideration of the content delivery and cache replacement by exploiting the distributed Multi-Agent Reinforcement Learning (MARL). We first propose a hierarchical edge caching architecture for IoVs and formulate the corresponding problem with the objective to minimize the long-term cost of content delivery in the system. Then, we extend the Markov Decision Process (MDP) in the single agent RL to the multi-agent system, and propose a distributed MARL based edge caching algorithm to tackle the optimization problem. Finally, extensive simulations are conducted to evaluate the performance of the proposed distributed MARL based edge caching method. The simulation results show that the proposed MARL based edge caching method significantly outperforms other benchmark methods in terms of the total content access cost, edge hit rate and average delay. Especially, our proposed method greatly reduces an average of 32% total content access cost compared with the conventional RL based edge caching methods.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125714480","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: 18

Reducing Makespans of DAG Scheduling through Interleaving Overlapping Resource Utilization 通过交叉重叠资源利用减少DAG调度的最大时间跨度

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00055

Yubin Duan, Ning Wang, Jie Wu

{"title":"Reducing Makespans of DAG Scheduling through Interleaving Overlapping Resource Utilization","authors":"Yubin Duan, Ning Wang, Jie Wu","doi":"10.1109/MASS50613.2020.00055","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00055","url":null,"abstract":"As data center clusters need to process quintillion bytes of data per day, it becomes a critical problem that efficiently scheduling jobs to improve resource utilization. However, the data analysis job usually contains multiple stages with dependent relationships, which brings challenges for scheduling. Those stages are modeled as Directed Acyclic Graphs (DAGs) and the general DAG scheduling problem is NP-hard. In this paper, we notice that in some parallel computing frameworks such as Spark, the execution of each stage could be divided into multiple phases that use different resources. We observe that interleaving different resources in a pipelined manner could improve resource utilization. Based on this observation, we propose to minimize the job makespan by exploiting resource pipeline. We first theoretically analyze the scheduling for perfectly parallel stages. In this case, our scheduling problem is equivalent to a DAG shop problem which is NP-hard. A contention-free scheduler is proposed and its approximation properties are analyzed. Stages of real-world jobs are usually not perfectly parallel. For general jobs, a reinforcement learning (RL) based scheduler is proposed to adaptively adjust the resource contention. We evaluate our contention-free and RL-based schedulers on a Spark cluster deployed on the Amazon EC2. Experiments on real-world and synthetic datasets show our RL-based scheduler can improve the CPU and network utilization by 33.0% and 29.7%, respectively.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125639252","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: 4

New Algorithm of QoS Constrained Routing for Node Energy Optimization of Edge Computing 面向边缘计算节点能量优化的QoS约束路由新算法

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00065

De-gan Zhang, Jinyu Du, Ting Zhang, Peng Yang, Hong-rui Fan

引用次数: 1

Slimmer: Accelerating 3D Semantic Segmentation for Mobile Augmented Reality Slimmer:为移动增强现实加速3D语义分割

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00079

Huanle Zhang, Bo Han, C. Y. Ip, P. Mohapatra

{"title":"Slimmer: Accelerating 3D Semantic Segmentation for Mobile Augmented Reality","authors":"Huanle Zhang, Bo Han, C. Y. Ip, P. Mohapatra","doi":"10.1109/MASS50613.2020.00079","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00079","url":null,"abstract":"Three-Dimensional (3D) semantic segmentation is an essential building block for interactive Augmented Reality (AR). However, existing Deep Neural Network (DNN) models for segmenting 3D objects are not only computation-intensive but also memory heavy, hindering their deployment on resourceconstrained mobile devices. We present the design, implementation and evaluation of Slimmer, a generic and model-independent framework for accelerating 3D semantic segmentation and facilitating its real-time applications on mobile devices. In contrast to the current practice that directly feeds a point cloud to DNN models, Slimmer is motivated by our observation that these models remain high accuracy even if we remove a fraction of points from the input, which can significantly reduce the inference time and memory usage of these models. Our design of Slimmer faces two key challenges. First, the simplification method of point clouds should be lightweight. Otherwise, the reduced inference time may be canceled out by the incurred overhead of input-data simplification. Second, Slimmer still needs to accurately segment the removed points from the input to create a complete segmentation of the original input, again, using a lightweight method. Our extensive performance evaluation demonstrates that, by addressing these two challenges, Slimmer can dramatically reduce the resource utilization of a representative DNN model for 3D semantic segmentation. For example, if we can tolerate 1% accuracy loss, the reduction could be $sim$20% for inference time and$sim$9% for memory usage. The reduction increases to around $sim$27% for inference time and$sim$15% for memory usage when we can tolerate 2% accuracy loss.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127919165","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: 8

Outdoor Playground Localization System for Tracking Young Children Using Ubisense Sensor Network 基于Ubisense传感器网络的儿童户外游乐场定位系统

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00010

Ying Luo, Dwight W. Irvin, Neal Buss, Alex Gutiérrez, B. Rous

引用次数: 2

Machine Learning on Camera Images for Fast mmWave Beamforming 用于快速毫米波波束形成的相机图像机器学习

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00049

Batool Salehi, M. Belgiovine, Saray Sanchez, Jennifer G. Dy, Stratis Ioannidis, K. Chowdhury

引用次数: 12

Multi-UAV Situational Awareness via Distributed and Approximate Computing Techniques 基于分布式和近似计算技术的多无人机态势感知

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00051

Khizar Anjum, Vidyasagar Sadhu, D. Pompili

{"title":"Multi-UAV Situational Awareness via Distributed and Approximate Computing Techniques","authors":"Khizar Anjum, Vidyasagar Sadhu, D. Pompili","doi":"10.1109/MASS50613.2020.00051","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00051","url":null,"abstract":"Recently, much progress has been made in using Neural Networks (NNs) for important yet narrowly focused tasks such as image classification (e.g., VGG-Net, ResNet), playing complex games like GO or other Computer Vision (CV) tasks. While these achievements are impressive, they are either achieved on computers with virtually unlimited resources or with little regard to real-time actionability. In this paper, we propose to combine the ubiquity of low-resource mobile devices, e.g., drones, with approximate- and distributed-computing techniques in order to make these NN techniques deployable on resource-constrained devices as well as to provide realtime information about the environment. We target situational awareness, which involves sensing the crucial factors in a new environment on a real-time basis. Specifically, we introduce intelligence to a team of drones in the form of real-time detection of a suspect/weapon using local resources and suspect identification in an emergency situation. We validate our proposed methods using Microsoft AirSim simulator via both simulations and hardware-in-the-loop emulations.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"428 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115597008","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

Fine-grained Frequencies for Simultaneous Intra-Group One-to-All Dissemination 组内一对所有同步传播的细粒度频率

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00064

Jagnyashini Debadarshini, C. Shekhar, Sudipta Saha

{"title":"Fine-grained Frequencies for Simultaneous Intra-Group One-to-All Dissemination","authors":"Jagnyashini Debadarshini, C. Shekhar, Sudipta Saha","doi":"10.1109/MASS50613.2020.00064","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00064","url":null,"abstract":"Simultaneous intra-group communication is one of the possible ways to handle the scaling issues in large decentralized systems. FDMA is an elegant strategy to carry out intra-group activities in parallel. However, due to increasing congestion in the licence free ISM bands, especially in the urban area, its hard to get enough number of good standard channels for multi-group setting in decentralized systems like IoT/WSN. In this work, we leverage concurrent transmission for efficient simultaneous intra-group one-to-all dissemination. Concurrent transmissions based strategies schedule the packet-transmissions in a special way so that the overlapping packets, instead of colliding with each other, result in constructive-interference or capture-effect. We propose a simple strategy to exploit this feature under concurrent transmission to achieve fruitful simultaneous intra-group communication in overlapping channels. Through extensive evaluation in testbeds for WSN/IoT under 2.4 GHz ISM band we show that, the proposed strategy can efficiently support simultaneous intra-group one-to-all dissemination even with allocation of channels having Center Frequency Distance (CFD) 1 MHz in most of the common group divisions. Experiments with a wide variety of group divisions also reveal that under concurrent transmission a CFD of 3 MHz and above can tolerate strong inter-group interference when the groups are quite mixed with each other which can be quite common specially when the nodes are mobile.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114885661","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

Out-of-Band Multiple Path Discovery Protocol for Robust In-Band Millimeter Wave Links 稳健带内毫米波链路的带外多径发现协议

2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS) Pub Date : 2020-12-01 DOI: 10.1109/MASS50613.2020.00054

Masoud Zarifneshat, Li Xiao

{"title":"Out-of-Band Multiple Path Discovery Protocol for Robust In-Band Millimeter Wave Links","authors":"Masoud Zarifneshat, Li Xiao","doi":"10.1109/MASS50613.2020.00054","DOIUrl":"https://doi.org/10.1109/MASS50613.2020.00054","url":null,"abstract":"Millimeter-wave technology has proved to be one of the enabling technologies of the fifth generation of wireless networks. Despite the merits of the millimeter-wave spectrum, its directionality imposes more overhead on communication systems than the non-millimeter wave spectrum. In this paper, we propose using signaling in another frequency band to discover the paths surrounding a receiver working in the millimeter-wave spectrum. In this way, the receiver does not have to do an expensive beam scan in the millimeter wave band and repair the interrupted ongoing millimeter communication much faster by choosing the beam covering the best path discovered by another frequency band. Our experiments in various environments by millimeterwave hardware platforms show that a non-millimeter wave frequency band’s paths can be used to align the beams in millimeterwave frequency. Existing out-of-band path discovery methods typically need a specially designed hardware for scanning and can only find the single line-of-sight path. Our proposed method uses commercial off-the-shelf products to perform out-of-band scanning and discover both line-of-sight path and non-line-of-sight paths for millimeter wave communication.","PeriodicalId":105795,"journal":{"name":"2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114981206","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