Sidharth Sharma, Aniruddha Kushwaha, Mohammad Alizadeh, G. Varghese, Ashwin Gumaste
We examine how to provide applications with dedicated bandwidth and guaranteed latency in a programmable mission-critical network. Unlike other SDN approaches such as B4 or SWAN, our system Tuneman optimizes both routes and packet schedules at each node to provide flows with sub-second bandwidth changes. Tuneman uses node-level optimization to compute node schedules in a slotted switch and does dynamic routing using a search procedure with Quality of Service– (QoS) based weights. This allows Tuneman to provide an efficient solution for mission-critical networks that have stringent QoS requirements. We evaluate Tuneman on a telesurgery network using a switch prototype built using FPGAs and also via simulations on India’s Tata Network. For mission-critical networks with multiple QoS levels, Tuneman has comparable or better utilization than SWAN while providing delay bounds guarantees.
{"title":"Tuneman: Customizing Networks to Guarantee Application Bandwidth and Latency","authors":"Sidharth Sharma, Aniruddha Kushwaha, Mohammad Alizadeh, G. Varghese, Ashwin Gumaste","doi":"10.1145/3575657","DOIUrl":"https://doi.org/10.1145/3575657","url":null,"abstract":"We examine how to provide applications with dedicated bandwidth and guaranteed latency in a programmable mission-critical network. Unlike other SDN approaches such as B4 or SWAN, our system Tuneman optimizes both routes and packet schedules at each node to provide flows with sub-second bandwidth changes. Tuneman uses node-level optimization to compute node schedules in a slotted switch and does dynamic routing using a search procedure with Quality of Service– (QoS) based weights. This allows Tuneman to provide an efficient solution for mission-critical networks that have stringent QoS requirements. We evaluate Tuneman on a telesurgery network using a switch prototype built using FPGAs and also via simulations on India’s Tata Network. For mission-critical networks with multiple QoS levels, Tuneman has comparable or better utilization than SWAN while providing delay bounds guarantees.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49063778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The outbreak of Covid-19 has exposed the lack of medical resources, especially the lack of medical personnel. This results in time and space restrictions for medical services, and patients cannot obtain health information all the time and everywhere. Based on the medical knowledge graph, healthcare bots alleviate this burden effectively by providing patients with diagnosis guidance, pre-diagnosis, and post-diagnosis consultation services in the way of human-machine dialogue. However, the medical utterance is more complicated in language structure, and there are complex intention phenomena in semantics. It is a challenge to detect the single intent, multi-intent, and implicit intent of a patient’s utterance. To this end, we create a high-quality annotated Chinese Medical query (utterance) dataset, CMedQ (about 16.8k queries in medical domain which includes single, multiple, and implicit intents). It is hard to detect intent on such a complex dataset through traditional text classification models. Thus, we propose a novel detect model Conco-ERNIE, using concept co-occurrence patterns to enhance the representation of pre-trained model ERNIE. These patterns are mined using Apriori algorithm and will be embedded via Node2Vec. Their features will be aggregated with semantic features into Conco-ERNIE by using an attention module, which can catch user explicit intents and also predict user implicit intents. Experiments on CMedQ demonstrates that Conco-ERNIE achieves outstanding performance over baseline. Based on Conco-ERNIE, we develop an intelligent healthcare bot, MedicalBot. To provide knowledge support for MedicalBot, we also build a Chinese medical graph, CMedKG (about 45k entities and 283k relationships).
{"title":"Conco-ERNIE: Complex User Intent Detect Model for Smart Healthcare Cognitive Bot","authors":"Bolin Zhang, Zhiying Tu, Shaoshi Hang, Dian-Hui Chu, Xiaofei Xu","doi":"10.1145/3574135","DOIUrl":"https://doi.org/10.1145/3574135","url":null,"abstract":"The outbreak of Covid-19 has exposed the lack of medical resources, especially the lack of medical personnel. This results in time and space restrictions for medical services, and patients cannot obtain health information all the time and everywhere. Based on the medical knowledge graph, healthcare bots alleviate this burden effectively by providing patients with diagnosis guidance, pre-diagnosis, and post-diagnosis consultation services in the way of human-machine dialogue. However, the medical utterance is more complicated in language structure, and there are complex intention phenomena in semantics. It is a challenge to detect the single intent, multi-intent, and implicit intent of a patient’s utterance. To this end, we create a high-quality annotated Chinese Medical query (utterance) dataset, CMedQ (about 16.8k queries in medical domain which includes single, multiple, and implicit intents). It is hard to detect intent on such a complex dataset through traditional text classification models. Thus, we propose a novel detect model Conco-ERNIE, using concept co-occurrence patterns to enhance the representation of pre-trained model ERNIE. These patterns are mined using Apriori algorithm and will be embedded via Node2Vec. Their features will be aggregated with semantic features into Conco-ERNIE by using an attention module, which can catch user explicit intents and also predict user implicit intents. Experiments on CMedQ demonstrates that Conco-ERNIE achieves outstanding performance over baseline. Based on Conco-ERNIE, we develop an intelligent healthcare bot, MedicalBot. To provide knowledge support for MedicalBot, we also build a Chinese medical graph, CMedKG (about 45k entities and 283k relationships).","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44518505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mathias Fischer, W. Lamersdorf, J. Liebeherr, M. Mühlhäuser
The history of research and development for the Internet has alternated between time periods of grand new visions and time periods concerned with integrating new advances in information and communication technology. As we entered the 21st century, many voices called for a redesign of the Internet architecture. The Internet was said to be ossified in the sense that its ability to incorporate major upgrades had been largely lost. Viewed as being in a state beyond repair, the era saw calls for and many efforts on a clean-slate design of the Internet architecture. A decade on – and with the Internet architecture largely unchanged – the appetite for big solutions has largely waned, and been replaced by efforts that seek to adapt networks and distributed systems to challenges posed by the advent of the Internet-of-Things, network softwarization, mission-critical applications, and artificial intelligence: IoT. The Internet-of-Things (IoT) will boost the number of Internet nodes well beyond the billions, which will lead to new traffic patterns (e.g., high-frequency low-volume) and resource requirements. SDN++. Softwarization is ‘conquering’ the net. Technologies such as software-defined networking (SDN) and network function virtualization (NFV) will continue to deliver increased flexibility for providing network services. As this softwarization significantly increases the complexity of today’s networks, new security problems will emerge. MCA. Mission-critical applications (MCA), which used to be confined to dedicated real-time systems and networks, such as time-sensitive networks (TSN), industrial Ethernet, and so on, are migrating to public and wide area networks. This impacts technologies and protocols, such as ultrareliable low latency communications (URLLC) in 5G networks. Moreover, delay requirements of real-time applications create a need to move cloud functionality closer to the action scene, e.g., via fog and edge computing. AI. The resurgence of artificial intelligence (AI), evoked by stunning successes of machine learning, boosts the need for computing resources that cannot be embedded in IoT devices and
{"title":"Introduction to the Special Section on Recent Advances in Networks and Distributed Systems","authors":"Mathias Fischer, W. Lamersdorf, J. Liebeherr, M. Mühlhäuser","doi":"10.1145/3584743","DOIUrl":"https://doi.org/10.1145/3584743","url":null,"abstract":"The history of research and development for the Internet has alternated between time periods of grand new visions and time periods concerned with integrating new advances in information and communication technology. As we entered the 21st century, many voices called for a redesign of the Internet architecture. The Internet was said to be ossified in the sense that its ability to incorporate major upgrades had been largely lost. Viewed as being in a state beyond repair, the era saw calls for and many efforts on a clean-slate design of the Internet architecture. A decade on – and with the Internet architecture largely unchanged – the appetite for big solutions has largely waned, and been replaced by efforts that seek to adapt networks and distributed systems to challenges posed by the advent of the Internet-of-Things, network softwarization, mission-critical applications, and artificial intelligence: IoT. The Internet-of-Things (IoT) will boost the number of Internet nodes well beyond the billions, which will lead to new traffic patterns (e.g., high-frequency low-volume) and resource requirements. SDN++. Softwarization is ‘conquering’ the net. Technologies such as software-defined networking (SDN) and network function virtualization (NFV) will continue to deliver increased flexibility for providing network services. As this softwarization significantly increases the complexity of today’s networks, new security problems will emerge. MCA. Mission-critical applications (MCA), which used to be confined to dedicated real-time systems and networks, such as time-sensitive networks (TSN), industrial Ethernet, and so on, are migrating to public and wide area networks. This impacts technologies and protocols, such as ultrareliable low latency communications (URLLC) in 5G networks. Moreover, delay requirements of real-time applications create a need to move cloud functionality closer to the action scene, e.g., via fog and edge computing. AI. The resurgence of artificial intelligence (AI), evoked by stunning successes of machine learning, boosts the need for computing resources that cannot be embedded in IoT devices and","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41869274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vicente García Díaz, Jerry Chun‐wei Lin, Juan Antonio Morente Molinera
Most countries around the world are trying to make the idea of “smart cities” a reality by building the basic infrastructure needed to use the technology. In this case, edge computing (EC) is very important for faster data processing and faster responses at the edges of the network. In recent years, smart cities have started using EC to improve building security, home automation, urban parking systems, and traffic and city management. Traditional IoT networks collect data and send it to a central cloud for further processing. EC devices, in contrast, can process and analyze the data themselves, as well as reduce the load on the network. In addition, mobile crowdsensing (MCS) and mobile edge computing (MEC) provide the crowdsensing services needed for a smart city in a densely populated area. These techniques provide a specific service at a specific location and for a specific period of time. However, they are better suited to support technical communication services with static edges than the human side. This leads to a dynamic extension of MEC called human-enabled edge computing (HEC), which combines people, devices, the Internet, and information with the architecture of MEC and the ability to sense MCS. In general, a traditional sensor network does not take context into account as well as HEC because it uses smart devices such as smartphones and wearables that people carry with them. It also uses data from mobile devices to obtain crowd intelligence and provide services based on what people want. Edge computing involves both people and things and therefore requires intelligent methods for classification and decision making, such as machine learning, data mining, and cognitive intelligence. Edge intelligence is used in the smart city to leverage data from different parts of the smart city. This is done by running analytics algorithms at the edge of the city. This speeds up the time it takes networked devices to make decisions and improves the quality of the data. Smart cities are taking advantage of HEC and next-generation wireless technology to connect things to people and the Internet of Things (IoT), resulting in powerful services and automation in the creation of dense and changing data sets. A successful edge computing infrastructure requires a local server, AI, and connections to computing systems in mobile devices, cars, and the Internet of Things (IoT). The research community has responded with enthusiasm. Only research articles that meet the journal’s requirements are accepted for publication after peer review. In this special issue, we have received 34 articles, and we finally include only one article, which has been fairly peerreviewed and accepted for publication. The following points highlight the remarkable scientific achievements of the accepted article.
{"title":"Introduction to the Special Section on Edge Computing AI-IoT Integrated Energy Efficient Intelligent Transportation System for Smart Cities","authors":"Vicente García Díaz, Jerry Chun‐wei Lin, Juan Antonio Morente Molinera","doi":"10.1145/3584745","DOIUrl":"https://doi.org/10.1145/3584745","url":null,"abstract":"Most countries around the world are trying to make the idea of “smart cities” a reality by building the basic infrastructure needed to use the technology. In this case, edge computing (EC) is very important for faster data processing and faster responses at the edges of the network. In recent years, smart cities have started using EC to improve building security, home automation, urban parking systems, and traffic and city management. Traditional IoT networks collect data and send it to a central cloud for further processing. EC devices, in contrast, can process and analyze the data themselves, as well as reduce the load on the network. In addition, mobile crowdsensing (MCS) and mobile edge computing (MEC) provide the crowdsensing services needed for a smart city in a densely populated area. These techniques provide a specific service at a specific location and for a specific period of time. However, they are better suited to support technical communication services with static edges than the human side. This leads to a dynamic extension of MEC called human-enabled edge computing (HEC), which combines people, devices, the Internet, and information with the architecture of MEC and the ability to sense MCS. In general, a traditional sensor network does not take context into account as well as HEC because it uses smart devices such as smartphones and wearables that people carry with them. It also uses data from mobile devices to obtain crowd intelligence and provide services based on what people want. Edge computing involves both people and things and therefore requires intelligent methods for classification and decision making, such as machine learning, data mining, and cognitive intelligence. Edge intelligence is used in the smart city to leverage data from different parts of the smart city. This is done by running analytics algorithms at the edge of the city. This speeds up the time it takes networked devices to make decisions and improves the quality of the data. Smart cities are taking advantage of HEC and next-generation wireless technology to connect things to people and the Internet of Things (IoT), resulting in powerful services and automation in the creation of dense and changing data sets. A successful edge computing infrastructure requires a local server, AI, and connections to computing systems in mobile devices, cars, and the Internet of Things (IoT). The research community has responded with enthusiasm. Only research articles that meet the journal’s requirements are accepted for publication after peer review. In this special issue, we have received 34 articles, and we finally include only one article, which has been fairly peerreviewed and accepted for publication. The following points highlight the remarkable scientific achievements of the accepted article.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43272319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introduction to the Special Section on Cyber Security in Internet of Vehicles","authors":"Ching-Hsien Hsu, Amir H. Alavi, M. Dong","doi":"10.1145/3584746","DOIUrl":"https://doi.org/10.1145/3584746","url":null,"abstract":"a","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47228162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Ciortea, Xiao-Wan Zhu, C. Pu, Munindar P. Singh
Over the past two decades, the Internet of Things (IoT) has evolved from silos built around custom protocol stacks into a system of systems built around standards—and the recent standardization of the Web of Things (WoT) at the IETF and the W3C further facilitates application-layer interoperability in the IoT. Constrained Web servers now target devices with as little as 10 KiB of RAM and 100 KiB of ROM, which means sensors and actuators can be abstracted behind embedded Web services. Going further, the WoT aims to provide uniform access to IoT devices through the Web—by hiding the protocols and interfaces used to access the devices behind abstract interaction patterns and hypermedia controls. From the edge of the network to the cloud, the Web is now emerging as a uniform hypermedia fabric that interconnects IoT devices and digital services. Still, many research questions remain open. IoT systems are not only inherently complex and heterogeneous, but also highly dynamic as the availability of devices (and their services) changes continually. Moreover, the IoT is inherently decentralized because it is not under the control of a single entity. In such settings, traditional engineering paradigms become impractical. Researchers and practitioners in the IoT community therefore require means to build sophisticated software agents that can achieve their design objectives through flexible interaction with other entities in their system. Many of the underlying research questions the IoT community is now confronted with—such as how to balance goal-directed and reactive behavior in software agents, or how to design and govern interactions in a decentralized IoT—have been investigated in the scientific literature on multiagent systems. At the same time, the IoT unlocks new practical use cases for multiagent systems.
{"title":"Introduction to the Special Issue on Multiagent Systems and Services in the Internet of Things","authors":"A. Ciortea, Xiao-Wan Zhu, C. Pu, Munindar P. Singh","doi":"10.1145/3584744","DOIUrl":"https://doi.org/10.1145/3584744","url":null,"abstract":"Over the past two decades, the Internet of Things (IoT) has evolved from silos built around custom protocol stacks into a system of systems built around standards—and the recent standardization of the Web of Things (WoT) at the IETF and the W3C further facilitates application-layer interoperability in the IoT. Constrained Web servers now target devices with as little as 10 KiB of RAM and 100 KiB of ROM, which means sensors and actuators can be abstracted behind embedded Web services. Going further, the WoT aims to provide uniform access to IoT devices through the Web—by hiding the protocols and interfaces used to access the devices behind abstract interaction patterns and hypermedia controls. From the edge of the network to the cloud, the Web is now emerging as a uniform hypermedia fabric that interconnects IoT devices and digital services. Still, many research questions remain open. IoT systems are not only inherently complex and heterogeneous, but also highly dynamic as the availability of devices (and their services) changes continually. Moreover, the IoT is inherently decentralized because it is not under the control of a single entity. In such settings, traditional engineering paradigms become impractical. Researchers and practitioners in the IoT community therefore require means to build sophisticated software agents that can achieve their design objectives through flexible interaction with other entities in their system. Many of the underlying research questions the IoT community is now confronted with—such as how to balance goal-directed and reactive behavior in software agents, or how to design and govern interactions in a decentralized IoT—have been investigated in the scientific literature on multiagent systems. At the same time, the IoT unlocks new practical use cases for multiagent systems.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42518489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ramesh Sekaran, Fadi M. Al-Turjman, Rizwan Patan, V. Ramasamy
Mobile network is a collection of devices with dynamic behavior where devices keep moving, which may lead to the network track to be connected or disconnected. This type of network is called Intermittently Connected Mobile Network (ICMN). The ICMN network is designed by splitting the region into `n' regions, ensuring it is a disconnected network. This network holds the same topological structure with mobile devices in it. This type of network routing is a challenging task. Though research keeps deriving techniques to achieve efficient routing in ICMN such as Epidemic, Flooding, Spray, copy case, Probabilistic, and Wait, these derived techniques for routing in ICMN are wise with higher packet delivery ratio, minimum latency, lesser overhead, and so on. A new routing schedule has been enacted comprising three optimization techniques such as Privacy-Preserving Ant Routing Protocol (PPARP), Privacy-Preserving Routing Protocol (PPRP), and Privacy-Preserving Bee Routing Protocol (PPBRP). In this paper, the enacted technique gives an optimal result following various network characteristics. Algorithms embedded with productive routing provide maximum security. Results are pointed out by analysis taken from spreading false devices into the network and its effectiveness at worst case. This paper also aids with the comparative results of enacted algorithms for secure routing in ICMN.
{"title":"Tripartite Transmitting Methodology for Intermittently Connected Mobile Network (ICMN)","authors":"Ramesh Sekaran, Fadi M. Al-Turjman, Rizwan Patan, V. Ramasamy","doi":"10.1145/3433545","DOIUrl":"https://doi.org/10.1145/3433545","url":null,"abstract":"Mobile network is a collection of devices with dynamic behavior where devices keep moving, which may lead to the network track to be connected or disconnected. This type of network is called Intermittently Connected Mobile Network (ICMN). The ICMN network is designed by splitting the region into `n' regions, ensuring it is a disconnected network. This network holds the same topological structure with mobile devices in it. This type of network routing is a challenging task. Though research keeps deriving techniques to achieve efficient routing in ICMN such as Epidemic, Flooding, Spray, copy case, Probabilistic, and Wait, these derived techniques for routing in ICMN are wise with higher packet delivery ratio, minimum latency, lesser overhead, and so on. A new routing schedule has been enacted comprising three optimization techniques such as Privacy-Preserving Ant Routing Protocol (PPARP), Privacy-Preserving Routing Protocol (PPRP), and Privacy-Preserving Bee Routing Protocol (PPBRP). In this paper, the enacted technique gives an optimal result following various network characteristics. Algorithms embedded with productive routing provide maximum security. Results are pointed out by analysis taken from spreading false devices into the network and its effectiveness at worst case. This paper also aids with the comparative results of enacted algorithms for secure routing in ICMN.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46702566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yirui Wu, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan
With the remarkable technological development in cyber-physical systems, industry 4.0 has evolved by a significant concept named as digital twin (DT). However, it’s still difficult to construct relationship between twin simulation and real scenario considering dynamic variations, especially when dealing with small surface defect detection tasks with high performance and computation resource requirement. In this paper, we aim to construct cyber-manufacturing systems to achieve a DT solution for small surface defect detection task. Focusing on DT based solution, the proposed system consists of an Edge-Cloud architecture and a surface defect detection algorithm. Considering dynamic characteristics and real-time response requirement, Edge-Cloud architecture is built to achieve smart manufacturing by efficiently collecting, processing, analyzing, and storing data produced by factory. A deep learning based algorithm is then constructed to detect surface defeats based on multi-modal data, i.e., imaging and depth data. Experiments show the proposed algorithm could achieve high accuracy and recall in small defeat detection task, thus constructing DT in cyber-manufacturing.
{"title":"Digital Twin of Intelligent Small Surface Defect Detection with Cyber-Manufacturing Systems","authors":"Yirui Wu, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan","doi":"10.1145/3571734","DOIUrl":"https://doi.org/10.1145/3571734","url":null,"abstract":"With the remarkable technological development in cyber-physical systems, industry 4.0 has evolved by a significant concept named as digital twin (DT). However, it’s still difficult to construct relationship between twin simulation and real scenario considering dynamic variations, especially when dealing with small surface defect detection tasks with high performance and computation resource requirement. In this paper, we aim to construct cyber-manufacturing systems to achieve a DT solution for small surface defect detection task. Focusing on DT based solution, the proposed system consists of an Edge-Cloud architecture and a surface defect detection algorithm. Considering dynamic characteristics and real-time response requirement, Edge-Cloud architecture is built to achieve smart manufacturing by efficiently collecting, processing, analyzing, and storing data produced by factory. A deep learning based algorithm is then constructed to detect surface defeats based on multi-modal data, i.e., imaging and depth data. Experiments show the proposed algorithm could achieve high accuracy and recall in small defeat detection task, thus constructing DT in cyber-manufacturing.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44237622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Desktop as a Service (DaaS) has become widely used by enterprises. In 2020, the use of DaaS increased dramatically due to the demand to work remotely from home during the COVID-19 pandemic. The DaaS market is expected to continue growing rapidly [1]. The quality of experience (QoE) of a DaaS service has been one of the main factors to enhance DaaS user satisfaction. To ensure user QoE, the amount of cloud computation resources for a DaaS service must be appropriately designed. We propose an Intent-driven DaaS Management (IDM) framework to autonomously determine the cloud-resource-amount configurations for a given DaaS QoE requirement. IDM enables autonomous resource design by abstracting the knowledge about the dependency between DaaS workload, resource configuration, and performance from previous DaaS performance log data. To ensure the IDM framework's applicability to actual DaaS services, we analyzed five main challenges in applying the IDM framework to actual DaaS services: identifying the resource-design objective, quantifying DaaS QoE, addressing low log data availability, designing performance-inference models, and addressing low resource variations in the log data. We addressed these challenges through detailed designing of IDM modules. The effectiveness of the IDM framework was assessed from the aspects of DaaS performance-inference precision, DaaS resource design, and time and human-resource cost reduction.
{"title":"An Intent-driven DaaS Management Framework to Enhance User Quality of Experience","authors":"Chaofeng Wu, Shingo Horiuchi, Kenji Murase, Hiroaki Kikushima, Kenichi Tayama","doi":"10.1145/3488586","DOIUrl":"https://doi.org/10.1145/3488586","url":null,"abstract":"Desktop as a Service (DaaS) has become widely used by enterprises. In 2020, the use of DaaS increased dramatically due to the demand to work remotely from home during the COVID-19 pandemic. The DaaS market is expected to continue growing rapidly [1]. The quality of experience (QoE) of a DaaS service has been one of the main factors to enhance DaaS user satisfaction. To ensure user QoE, the amount of cloud computation resources for a DaaS service must be appropriately designed. We propose an Intent-driven DaaS Management (IDM) framework to autonomously determine the cloud-resource-amount configurations for a given DaaS QoE requirement. IDM enables autonomous resource design by abstracting the knowledge about the dependency between DaaS workload, resource configuration, and performance from previous DaaS performance log data. To ensure the IDM framework's applicability to actual DaaS services, we analyzed five main challenges in applying the IDM framework to actual DaaS services: identifying the resource-design objective, quantifying DaaS QoE, addressing low log data availability, designing performance-inference models, and addressing low resource variations in the log data. We addressed these challenges through detailed designing of IDM modules. The effectiveness of the IDM framework was assessed from the aspects of DaaS performance-inference precision, DaaS resource design, and time and human-resource cost reduction.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44911688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Geographically distributed (geo-distributed) datacenters for stream data processing typically comprise multiple edges and core datacenters connected through Wide-Area Network (WAN) with a master node responsible for allocating tasks to worker nodes. Since WAN links significantly impact the performance of distributed task execution, the existing task assignment approach is unsuitable for distributed stream data processing with low latency and high throughput demand. In this paper, we propose SAFA, a resource provisioning framework using the Software-Defined Networking (SDN) concept with an SDN controller responsible for monitoring the WAN, selecting an appropriate subset of worker nodes, and assigning tasks to the designated worker nodes. We implemented the data plane of the framework in P4 and the control plane components in Python. We tested the performance of the proposed system on Apache Spark, Apache Storm, and Apache Flink using the Yahoo! streaming benchmark on a set of custom topologies. The results of the experiments validate that the proposed approach is viable for distributed stream processing and confirm that it can improve at least 1.64× the processing time of incoming events of the current stream processing systems.
{"title":"SDN-enabled Resource Provisioning Framework for Geo-Distributed Streaming Analytics","authors":"H. Mostafaei, Shafi Afridi","doi":"10.1145/3571158","DOIUrl":"https://doi.org/10.1145/3571158","url":null,"abstract":"Geographically distributed (geo-distributed) datacenters for stream data processing typically comprise multiple edges and core datacenters connected through Wide-Area Network (WAN) with a master node responsible for allocating tasks to worker nodes. Since WAN links significantly impact the performance of distributed task execution, the existing task assignment approach is unsuitable for distributed stream data processing with low latency and high throughput demand. In this paper, we propose SAFA, a resource provisioning framework using the Software-Defined Networking (SDN) concept with an SDN controller responsible for monitoring the WAN, selecting an appropriate subset of worker nodes, and assigning tasks to the designated worker nodes. We implemented the data plane of the framework in P4 and the control plane components in Python. We tested the performance of the proposed system on Apache Spark, Apache Storm, and Apache Flink using the Yahoo! streaming benchmark on a set of custom topologies. The results of the experiments validate that the proposed approach is viable for distributed stream processing and confirm that it can improve at least 1.64× the processing time of incoming events of the current stream processing systems.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41533278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：