Extended reality (XR) is touted as the next frontier of the digital future. XR includes all immersive technologies of augmented reality (AR), virtual reality (VR), and mixed reality (MR). XR applications obtain the real-world context of the user from an underlying system, and provide rich, immersive, and interactive virtual experiences based on the user's context in real-time. XR systems process streams of data from device sensors, and provide functionalities including perceptions and graphics required by the applications. These processing steps are computationally intensive, and the challenge is that they must be performed within the strict latency requirements of XR. This poses limitations on the possible XR experiences that can be supported on mobile devices with limited computing resources. In this XR context, edge computing is an effective approach to address this problem for mobile users. The edge is located closer to the end users and enables processing and storing data near them. In addition, the development of high bandwidth and low latency network technologies such as 5G facilitates the application of edge computing for latency-critical use cases [4], [11]. This work presents an XR system for enabling flexible edge-assisted XR.
{"title":"Poster: Enabling Flexible Edge-assisted XR","authors":"Jin Heo, Ketan Bhardwaj, Ada Gavrilovska","doi":"10.1145/3453142.3491408","DOIUrl":"https://doi.org/10.1145/3453142.3491408","url":null,"abstract":"Extended reality (XR) is touted as the next frontier of the digital future. XR includes all immersive technologies of augmented reality (AR), virtual reality (VR), and mixed reality (MR). XR applications obtain the real-world context of the user from an underlying system, and provide rich, immersive, and interactive virtual experiences based on the user's context in real-time. XR systems process streams of data from device sensors, and provide functionalities including perceptions and graphics required by the applications. These processing steps are computationally intensive, and the challenge is that they must be performed within the strict latency requirements of XR. This poses limitations on the possible XR experiences that can be supported on mobile devices with limited computing resources. In this XR context, edge computing is an effective approach to address this problem for mobile users. The edge is located closer to the end users and enables processing and storing data near them. In addition, the development of high bandwidth and low latency network technologies such as 5G facilitates the application of edge computing for latency-critical use cases [4], [11]. This work presents an XR system for enabling flexible edge-assisted XR.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74530207","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}
Federated learning allows a large group of edge workers to collaboratively train a shared model without revealing their local data. It has become a powerful tool for deep learning in heterogeneous environments. User privacy is preserved by keeping the training data local to each device. However, federated learning still requires workers to share their weights, which can leak private information during collaboration. This paper introduces SecureFL, a practical framework that provides end-to-end security of federated learning. SecureFL integrates widely available Trusted Execution Environments (TEE) to protect against privacy leaks. SecureFL also uses carefully designed partitioning and aggregation techniques to ensure TEE efficiency on both the cloud and edge workers. SecureFL is both practical and efficient in securing the end-to-end process of federated learning, providing reasonable overhead given the privacy benefits. The paper provides thorough security analysis and performance evaluation of SecureFL, which show that the overhead is reasonable considering the substantial privacy benefits that it provides.
{"title":"SecureFL: Privacy Preserving Federated Learning with SGX and TrustZone","authors":"E. Kuznetsov, Yitao Chen, Ming Zhao","doi":"10.1145/3453142.3491287","DOIUrl":"https://doi.org/10.1145/3453142.3491287","url":null,"abstract":"Federated learning allows a large group of edge workers to collaboratively train a shared model without revealing their local data. It has become a powerful tool for deep learning in heterogeneous environments. User privacy is preserved by keeping the training data local to each device. However, federated learning still requires workers to share their weights, which can leak private information during collaboration. This paper introduces SecureFL, a practical framework that provides end-to-end security of federated learning. SecureFL integrates widely available Trusted Execution Environments (TEE) to protect against privacy leaks. SecureFL also uses carefully designed partitioning and aggregation techniques to ensure TEE efficiency on both the cloud and edge workers. SecureFL is both practical and efficient in securing the end-to-end process of federated learning, providing reasonable overhead given the privacy benefits. The paper provides thorough security analysis and performance evaluation of SecureFL, which show that the overhead is reasonable considering the substantial privacy benefits that it provides.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88911896","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}
Kumseok Jung, Julien Gascon-Samson, K. Pattabiraman
While many IoT platforms provide high-level programming environments to hide the complexities of heterogeneity and network dynamism, they come with the cost of adopting a framework-specific API. In this demo paper, we present a demo of OneOS, a middleware providing a distributed computing environment through the standard POSIX API. We demonstrate running a video stream processing application as a distributed POSIX pipeline on the OneOS network.
{"title":"Demo: OneOS - Middleware for Running Edge Computing Applications as Distributed POSIX Pipelines","authors":"Kumseok Jung, Julien Gascon-Samson, K. Pattabiraman","doi":"10.1145/3453142.3491423","DOIUrl":"https://doi.org/10.1145/3453142.3491423","url":null,"abstract":"While many IoT platforms provide high-level programming environments to hide the complexities of heterogeneity and network dynamism, they come with the cost of adopting a framework-specific API. In this demo paper, we present a demo of OneOS, a middleware providing a distributed computing environment through the standard POSIX API. We demonstrate running a video stream processing application as a distributed POSIX pipeline on the OneOS network.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79508950","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}
With today's ubiquitous deployment of video cameras and other edge devices, progress in edge computing is happening at an incredible speed. Yet, one aspect of real-time video analytics at the edge that is still underdeveloped is the support for processing multitenant, multi-application scenarios with a limited set of resources. Existing systems either fail to provide the necessary performance, or rely too heavily on edge or cloud servers to handle the workload. This work proposes a new approach, inspired by both Function-as-a-Service and microservices architecture in order to efficiently place and execute video analytics pipelines on edge devices. The main contributions of this work are the ability to dynamically add and run new applications on already deployed systems, and the capability to horizontally distribute pipelines across other neigh-bouring edge devices. We prototype an implementation that we evaluate using multiple concurrent applications per device. Results show that our system provides more flexibility for on-the-fly re-configuration than existing works do, with 20 % improvement in latency and 3.9 X increase in throughput.
{"title":"Microservice-based Edge Device Architecture for Video Analytics","authors":"Si Young Jang, B. Kostadinov, Dongman Lee","doi":"10.1145/3453142.3491283","DOIUrl":"https://doi.org/10.1145/3453142.3491283","url":null,"abstract":"With today's ubiquitous deployment of video cameras and other edge devices, progress in edge computing is happening at an incredible speed. Yet, one aspect of real-time video analytics at the edge that is still underdeveloped is the support for processing multitenant, multi-application scenarios with a limited set of resources. Existing systems either fail to provide the necessary performance, or rely too heavily on edge or cloud servers to handle the workload. This work proposes a new approach, inspired by both Function-as-a-Service and microservices architecture in order to efficiently place and execute video analytics pipelines on edge devices. The main contributions of this work are the ability to dynamically add and run new applications on already deployed systems, and the capability to horizontally distribute pipelines across other neigh-bouring edge devices. We prototype an implementation that we evaluate using multiple concurrent applications per device. Results show that our system provides more flexibility for on-the-fly re-configuration than existing works do, with 20 % improvement in latency and 3.9 X increase in throughput.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87439527","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}
Application latency requirements, privacy, and security concerns have naturally pushed computing onto smartphone and IoT devices in a decentralized manner. In response to these demands, researchers have developed micro-runtimes for WebAssembly (Wasm) on IoT devices to enable streaming applications to a runtime that can run the target binaries that are independent of the device. However, the migration of Wasm and the associated security research has neglected the urgent needs of access control on bare-metal, memory management unit (MMU)-less IoT devices that are sensing and actuating upon the physical environment. This paper presents Aerogel, an access control framework that addresses security gaps between the bare-metal IoT devices and the Wasm execution environment concerning access control for sensors, actuators, processor energy usage, and memory usage. In particular, we treat the runtime as a multi-tenant environment, where each Wasm-based application is a tenant. We leverage the inherent sandboxing mechanisms of Wasm to enforce the access control policies to sensors and actuators without trusting the bare-metal operating system. We evaluate our approach on a representative IoT development board: a cortexM4 based development board (nRF52840). Our results show that Aerogel can effectively enforce compute resource and peripheral access control policies while introducing as little as 0.19% to 1.04% runtime overhead and consuming only 18.8% to 45.9% extra energy.
{"title":"Aerogel: Lightweight Access Control Framework for WebAssembly-Based Bare-Metal IoT Devices","authors":"Renju Liu, Mani Srivastava","doi":"10.1145/3453142.3491282","DOIUrl":"https://doi.org/10.1145/3453142.3491282","url":null,"abstract":"Application latency requirements, privacy, and security concerns have naturally pushed computing onto smartphone and IoT devices in a decentralized manner. In response to these demands, researchers have developed micro-runtimes for WebAssembly (Wasm) on IoT devices to enable streaming applications to a runtime that can run the target binaries that are independent of the device. However, the migration of Wasm and the associated security research has neglected the urgent needs of access control on bare-metal, memory management unit (MMU)-less IoT devices that are sensing and actuating upon the physical environment. This paper presents Aerogel, an access control framework that addresses security gaps between the bare-metal IoT devices and the Wasm execution environment concerning access control for sensors, actuators, processor energy usage, and memory usage. In particular, we treat the runtime as a multi-tenant environment, where each Wasm-based application is a tenant. We leverage the inherent sandboxing mechanisms of Wasm to enforce the access control policies to sensors and actuators without trusting the bare-metal operating system. We evaluate our approach on a representative IoT development board: a cortexM4 based development board (nRF52840). Our results show that Aerogel can effectively enforce compute resource and peripheral access control policies while introducing as little as 0.19% to 1.04% runtime overhead and consuming only 18.8% to 45.9% extra energy.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91125645","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}
Modern mobile devices are increasingly used to store and process sensitive data. In order to prevent the sensitive data from being leaked, one of the best ways of protecting them and their owner is to hide the data with plausible deniability. Plausibly Deniable Encryption (PDE) has been designed for such purpose. The existing PDE systems for mobile devices however, have suffered from significant drawbacks as they either ignore the deniability compromises present in the special underlying storage media of mobile devices or are vulnerable to various new attacks such as side-channel attacks. In this work, we propose a new PDE system design for mobile devices which takes advantage of the hardware features equipped in the mainstream mobile devices. Our preliminary design has two major component: First, we strictly isolate the hidden and the public data in the flash layer, so that a multi-snapshot adversary is not able to identify the existence of the hidden sensitive data when having access to the low layer storage medium of the device. Second, we incorporate software and operating system level deniability into ARM TrustZone. With this TrustZone-enhanced isolation, our PDE system is immune to side-channel attacks at the operating system layer.
{"title":"TrustZone Enhanced Plausibly Deniable Encryption System for Mobile Devices","authors":"Jinghui Liao, Bo Chen, Weisong Shi","doi":"10.1145/3453142.3493512","DOIUrl":"https://doi.org/10.1145/3453142.3493512","url":null,"abstract":"Modern mobile devices are increasingly used to store and process sensitive data. In order to prevent the sensitive data from being leaked, one of the best ways of protecting them and their owner is to hide the data with plausible deniability. Plausibly Deniable Encryption (PDE) has been designed for such purpose. The existing PDE systems for mobile devices however, have suffered from significant drawbacks as they either ignore the deniability compromises present in the special underlying storage media of mobile devices or are vulnerable to various new attacks such as side-channel attacks. In this work, we propose a new PDE system design for mobile devices which takes advantage of the hardware features equipped in the mainstream mobile devices. Our preliminary design has two major component: First, we strictly isolate the hidden and the public data in the flash layer, so that a multi-snapshot adversary is not able to identify the existence of the hidden sensitive data when having access to the low layer storage medium of the device. Second, we incorporate software and operating system level deniability into ARM TrustZone. With this TrustZone-enhanced isolation, our PDE system is immune to side-channel attacks at the operating system layer.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86747550","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}
Edge computing is proposed to be a promising paradigm to bridge the gap between the stringent computation requirement of realtime mobile augmented reality (MAR) and the constrained computation capacity on our mobile devices. However, prior work on edge-assisted MAR may fail to achieve expected performance in multiple practical cases, e.g., irreparable network disruptions caused by wireless link instability and user-mobility which is a critical characteristic of popular MAR applications. In this paper, we design a new edge-based MAR system named Explorer that enables mobile users to acquire guaranteed MAR offloading performance even under network instability and frequent user-mobility. Additionally, analytical models are developed to provide timely estimation of the sources of object detection staleness. Furthermore, we implement the proposed Explorer in an end-to-end testbed.
{"title":"You Can Enjoy Augmented Reality While Running Around: An Edge-based Mobile AR System","authors":"Haoxin Wang, Jiang Xie","doi":"10.1145/3453142.3491416","DOIUrl":"https://doi.org/10.1145/3453142.3491416","url":null,"abstract":"Edge computing is proposed to be a promising paradigm to bridge the gap between the stringent computation requirement of realtime mobile augmented reality (MAR) and the constrained computation capacity on our mobile devices. However, prior work on edge-assisted MAR may fail to achieve expected performance in multiple practical cases, e.g., irreparable network disruptions caused by wireless link instability and user-mobility which is a critical characteristic of popular MAR applications. In this paper, we design a new edge-based MAR system named Explorer that enables mobile users to acquire guaranteed MAR offloading performance even under network instability and frequent user-mobility. Additionally, analytical models are developed to provide timely estimation of the sources of object detection staleness. Furthermore, we implement the proposed Explorer in an end-to-end testbed.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86290687","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}
Federated Learning (FL) is a fast-growing distributed learning paradigm with widespread applications especially over mobile devices, since it trains high-quality deep learning models while keeping the data private. This aspect is most suitable in multi-access edge computing settings where FL leverages distributed data from numerous mobile edge devices for training. However, FL involves frequent global synchronization of periodic updates over links often with transmission rate limits, inflicting communication burdens. Moreover, the intensive on-device computation of local updates results in computation and memory overhead on resource constricted mobile devices. To address these challenges, in this paper, we introduce SQuaFL, a sketched quantization based novel FL method which aims at communication efficiency while preserving privacy. In particular, we compress the accumulation of local gradients using quantization and Count Sketches without adding explicit noise, sacrificing the learning performance, or introducing a computation overhead. We provide theoretical guarantees of convergence of our proposed scheme and perform extensive simulations to demonstrate its efficacy over baseline methods.
{"title":"SQuaFL: Sketch-Quantization Inspired Communication Efficient Federated Learning","authors":"Pavana Prakash, Jiahao Ding, Minglei Shu, Junyi Wang, Wenjun Xu, Miao Pan","doi":"10.1145/3453142.3491415","DOIUrl":"https://doi.org/10.1145/3453142.3491415","url":null,"abstract":"Federated Learning (FL) is a fast-growing distributed learning paradigm with widespread applications especially over mobile devices, since it trains high-quality deep learning models while keeping the data private. This aspect is most suitable in multi-access edge computing settings where FL leverages distributed data from numerous mobile edge devices for training. However, FL involves frequent global synchronization of periodic updates over links often with transmission rate limits, inflicting communication burdens. Moreover, the intensive on-device computation of local updates results in computation and memory overhead on resource constricted mobile devices. To address these challenges, in this paper, we introduce SQuaFL, a sketched quantization based novel FL method which aims at communication efficiency while preserving privacy. In particular, we compress the accumulation of local gradients using quantization and Count Sketches without adding explicit noise, sacrificing the learning performance, or introducing a computation overhead. We provide theoretical guarantees of convergence of our proposed scheme and perform extensive simulations to demonstrate its efficacy over baseline methods.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84894653","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}
The Domain Name System (DNS,) a standard way of looking up IP addresses of Internet services, has served the Internet ecosystem well. However with the advent of edge computing, it falls short of many desirable properties. These include accurate fine-grained geographic localization of edge services, fast look-ups, and ensuring record freshness and cache integrity for end users. To satisfy these properties we consider blockchain-based solutions, a counter-intuitive approach as blockchain is not often associated with performance or the latency requirements of the edge. Despite this, we argue blockchain can address the shortcomings we've identified in DNS specifically in the edge context. We've found blockchain-based solutions are not sufficient as is, thus we present GeoENS - a prototype based on the Ethereum blockchain suitable for, and enabled by, the edge. It achieves these goals via novel record organization for smart contract, push-based record invalidation, and a look through cache. Given the skepticism of blockchain to out-perform DNS, we provide preliminary results which show GeoENS achieves its goals of fine-grained geo-localization accurate to ±20 meters, fast query latency for non-cached records under 50 ms, and cache freshness at edge scale of 10 minutes (vs. 3 hour DNS TTLs.) GeoENS does this with negligible bandwidth and CPU load overhead and reasonable storage requirements in the proposed deployment scenario.
{"title":"The Performance Argument for Blockchain-based Edge DNS Caching","authors":"James Choncholas, Ketan Bhardwaj, Ada Gavrilovska","doi":"10.1145/3453142.3491288","DOIUrl":"https://doi.org/10.1145/3453142.3491288","url":null,"abstract":"The Domain Name System (DNS,) a standard way of looking up IP addresses of Internet services, has served the Internet ecosystem well. However with the advent of edge computing, it falls short of many desirable properties. These include accurate fine-grained geographic localization of edge services, fast look-ups, and ensuring record freshness and cache integrity for end users. To satisfy these properties we consider blockchain-based solutions, a counter-intuitive approach as blockchain is not often associated with performance or the latency requirements of the edge. Despite this, we argue blockchain can address the shortcomings we've identified in DNS specifically in the edge context. We've found blockchain-based solutions are not sufficient as is, thus we present GeoENS - a prototype based on the Ethereum blockchain suitable for, and enabled by, the edge. It achieves these goals via novel record organization for smart contract, push-based record invalidation, and a look through cache. Given the skepticism of blockchain to out-perform DNS, we provide preliminary results which show GeoENS achieves its goals of fine-grained geo-localization accurate to ±20 meters, fast query latency for non-cached records under 50 ms, and cache freshness at edge scale of 10 minutes (vs. 3 hour DNS TTLs.) GeoENS does this with negligible bandwidth and CPU load overhead and reasonable storage requirements in the proposed deployment scenario.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72965777","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}
Zhuqi Li, Yuanchao Shu, G. Ananthanarayanan, Longfei Shangguan, K. Jamieson, P. Bahl
Massive video analytics systems, comprised of many densely-deployed cameras and supporting edge servers, are driving innovation in many areas including smart retail stores and security monitoring. To support such systems the challenge lies in collecting video footage in a way that maximizes end-to-end application goals, and scales this performance as camera density increases to meet application needs. This paper presents Spider, a multi-hop, millimeter-wave (mmWave) wireless relay network design that meets these needs. To mitigate physical mmWave link blockage, Spider integrates a low-latency Wi-Fi control plane with a mmWave relay data plane, allowing agile re-routing around blockages. Spider proposes a novel video bit-rate allocation algorithm coupled with a scalable routing algorithm that works hand-in-hand toward the application-level objective of maximizing video analytics accuracy, rather than simply maximizing data throughput. Our experimental evaluation uses a combination of testbed deployment and trace-driven simulation and compares against both Wi-Fi and mmWave mesh schemes that operate without Spider's algorithms. Results show that Spider is able to support camera densities up to 176% higher (gains of 2.76x) than the best-performing comparison scheme, allowing it alone to meet real-world camera density targets (4–250 cameras/1,000 sq. ft., depending on application). Further experiments demonstrate Spider's scalability in the presence of failures, with a 5.4-100x reduction in average failure recovery time.
{"title":"Spider: A Multi-Hop Millimeter-Wave Network for Live Video Analytics","authors":"Zhuqi Li, Yuanchao Shu, G. Ananthanarayanan, Longfei Shangguan, K. Jamieson, P. Bahl","doi":"10.1145/3453142.3491291","DOIUrl":"https://doi.org/10.1145/3453142.3491291","url":null,"abstract":"Massive video analytics systems, comprised of many densely-deployed cameras and supporting edge servers, are driving innovation in many areas including smart retail stores and security monitoring. To support such systems the challenge lies in collecting video footage in a way that maximizes end-to-end application goals, and scales this performance as camera density increases to meet application needs. This paper presents Spider, a multi-hop, millimeter-wave (mmWave) wireless relay network design that meets these needs. To mitigate physical mmWave link blockage, Spider integrates a low-latency Wi-Fi control plane with a mmWave relay data plane, allowing agile re-routing around blockages. Spider proposes a novel video bit-rate allocation algorithm coupled with a scalable routing algorithm that works hand-in-hand toward the application-level objective of maximizing video analytics accuracy, rather than simply maximizing data throughput. Our experimental evaluation uses a combination of testbed deployment and trace-driven simulation and compares against both Wi-Fi and mmWave mesh schemes that operate without Spider's algorithms. Results show that Spider is able to support camera densities up to 176% higher (gains of 2.76x) than the best-performing comparison scheme, allowing it alone to meet real-world camera density targets (4–250 cameras/1,000 sq. ft., depending on application). Further experiments demonstrate Spider's scalability in the presence of failures, with a 5.4-100x reduction in average failure recovery time.","PeriodicalId":6779,"journal":{"name":"2021 IEEE/ACM Symposium on Edge Computing (SEC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74624435","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：