Current blockchain systems face the problems of poor scalability, low performance, and high cost. To address the previous bottlenecks, we plan to employ the DAG-based structure as the primary method and propose a concrete model, called 3D-DAG, to improve the scalability. The model consists of two layers: mainchain and sidechain, which separately severs for maintaining the pivot sequence and improving the parallelism. Our expecting results should significantly improve the performance and scalability without compromising the security.
{"title":"Improving the scalability of blockchain through DAG","authors":"Qin Wang","doi":"10.1145/3366624.3368165","DOIUrl":"https://doi.org/10.1145/3366624.3368165","url":null,"abstract":"Current blockchain systems face the problems of poor scalability, low performance, and high cost. To address the previous bottlenecks, we plan to employ the DAG-based structure as the primary method and propose a concrete model, called 3D-DAG, to improve the scalability. The model consists of two layers: mainchain and sidechain, which separately severs for maintaining the pivot sequence and improving the parallelism. Our expecting results should significantly improve the performance and scalability without compromising the security.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130590649","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}
IoT applications with massive generation of data have different service requirements in terms of performance, security, privacy, availability and price. Relying on a single cloud storage puts limits on the applications, which could be alleviated by another storage solution. Moreover multi-cloud storage architecture has limited impact due to the lack of differentiation between competing cloud solutions. Recently, decentralized storage solutions are gaining attraction as an alternative to cloud storage. In this work, we propose a blockchain-based adaptive middleware for intelligent selection of storage technology for IoT applications and explore the open questions regarding the integration of middleware with IoT applications, storage technologies and blockchain network.
{"title":"A blockchain-based adaptive middleware for large scale internet of things data storage selection","authors":"S. Danish","doi":"10.1145/3366624.3368159","DOIUrl":"https://doi.org/10.1145/3366624.3368159","url":null,"abstract":"IoT applications with massive generation of data have different service requirements in terms of performance, security, privacy, availability and price. Relying on a single cloud storage puts limits on the applications, which could be alleviated by another storage solution. Moreover multi-cloud storage architecture has limited impact due to the lack of differentiation between competing cloud solutions. Recently, decentralized storage solutions are gaining attraction as an alternative to cloud storage. In this work, we propose a blockchain-based adaptive middleware for intelligent selection of storage technology for IoT applications and explore the open questions regarding the integration of middleware with IoT applications, storage technologies and blockchain network.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124928670","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 rapid generation of data from distributed IoT devices, scientific instruments, and compute clusters presents unique data management challenges. The influx of large, heterogeneous, and complex data causes repositories to become siloed or generally unsearchable---both problems not currently well-addressed by distributed file systems. In this work, we propose Xtract, a serverless middleware to extract metadata from files spread across heterogeneous edge computing resources. In my future work, we intend to study how Xtract can automatically construct file extraction workflows subject to users' cost, time, security, and compute allocation constraints. To this end, Xtract will enable the creation of a searchable centralized index across distributed data collections.
{"title":"Dredging a data lake: decentralized metadata extraction","authors":"Tyler J. Skluzacek","doi":"10.1145/3366624.3368170","DOIUrl":"https://doi.org/10.1145/3366624.3368170","url":null,"abstract":"The rapid generation of data from distributed IoT devices, scientific instruments, and compute clusters presents unique data management challenges. The influx of large, heterogeneous, and complex data causes repositories to become siloed or generally unsearchable---both problems not currently well-addressed by distributed file systems. In this work, we propose Xtract, a serverless middleware to extract metadata from files spread across heterogeneous edge computing resources. In my future work, we intend to study how Xtract can automatically construct file extraction workflows subject to users' cost, time, security, and compute allocation constraints. To this end, Xtract will enable the creation of a searchable centralized index across distributed data collections.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132003772","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}
Proxies provide the networking infrastructure to the microservices architecture which has become ubiquitous in the cloud today. However, these proxies either cannot operate at line rate or are unsuitable for generic deployments. Furthermore, state-of-the-art autoscaling algorithms are still unable to account for quality of service the applications need to provide. In my dissertation I plan to explore a split proxy architecture that would be able to operate at line rate and provide autoscaling services that take into account QoS. Furthermore, such disaggregated L4/L7 processing provides a unique opportunity to embed DDoS mitigation like security features within the proxy framework.
{"title":"Smart proxying for microservices","authors":"Ratnadeep Bhattacharya","doi":"10.1145/3366624.3368164","DOIUrl":"https://doi.org/10.1145/3366624.3368164","url":null,"abstract":"Proxies provide the networking infrastructure to the microservices architecture which has become ubiquitous in the cloud today. However, these proxies either cannot operate at line rate or are unsuitable for generic deployments. Furthermore, state-of-the-art autoscaling algorithms are still unable to account for quality of service the applications need to provide. In my dissertation I plan to explore a split proxy architecture that would be able to operate at line rate and provide autoscaling services that take into account QoS. Furthermore, such disaggregated L4/L7 processing provides a unique opportunity to embed DDoS mitigation like security features within the proxy framework.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"2008 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132816101","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}
Complex Event Processing (CEP) is an event processing paradigm capable of detecting patterns over streaming data in real-time. Presently, CEP systems have key challenges to preform matching over video streams due to their unstructured data model and complex video patterns which occurs over time and space. In this paper, I introduce the design, implementation and optimization of the proposed CEP framework, which enables the pattern detection over video streams. The work first proposes a Video Event Query Language (VEQL) motivated from current event query languages to write expressive video queries in CEP scenario. The query discusses how to write event query rules for video patterns and encapsulate them as high-level operators. To perform matching over VEQL queries, Video Event Knowledge Graph (VEKG) is proposed, which is a graph-based structured model of video streams. A complex event matcher is then presented which enable spatiotemporal pattern matching over videos using VEQL and VEKG constructs. Finally, three optimization strategies: state summarization, data-driven windows, and tuning deep model cascades are discussed to improve the CEP system performance which I intend to follow in my ongoing PhD research.
{"title":"High-performance complex event processing framework to detect event patterns over video streams","authors":"Piyush Yadav","doi":"10.1145/3366624.3368169","DOIUrl":"https://doi.org/10.1145/3366624.3368169","url":null,"abstract":"Complex Event Processing (CEP) is an event processing paradigm capable of detecting patterns over streaming data in real-time. Presently, CEP systems have key challenges to preform matching over video streams due to their unstructured data model and complex video patterns which occurs over time and space. In this paper, I introduce the design, implementation and optimization of the proposed CEP framework, which enables the pattern detection over video streams. The work first proposes a Video Event Query Language (VEQL) motivated from current event query languages to write expressive video queries in CEP scenario. The query discusses how to write event query rules for video patterns and encapsulate them as high-level operators. To perform matching over VEQL queries, Video Event Knowledge Graph (VEKG) is proposed, which is a graph-based structured model of video streams. A complex event matcher is then presented which enable spatiotemporal pattern matching over videos using VEQL and VEKG constructs. Finally, three optimization strategies: state summarization, data-driven windows, and tuning deep model cascades are discussed to improve the CEP system performance which I intend to follow in my ongoing PhD research.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121748589","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}
System-level provenance is of widespread interest for applications such as security enforcement and information protection. However, testing the correctness or completeness of provenance systems is challenging. In some cases, there is not even a clear consensus about what behaviour is correct. This work presents the study of system behaviour through the analysis of system-level provenance and the provenance systems that collect them. Besides, an automated tool, ProvMark is presented for the automation of the process and provides an additional layer of expressiveness benchmarking on existing provenance systems and their provenance result. This helps to understand patterns of system behaviour for security and other applications. It also allows provenance system developers to verify their tools and allows end-users to compare the tools at the same level to choose a suitable one for their purposes.
{"title":"Analysing system behaviour by automatic benchmarking of system-level provenance","authors":"Sheung Chi Chan","doi":"10.1145/3366624.3368155","DOIUrl":"https://doi.org/10.1145/3366624.3368155","url":null,"abstract":"System-level provenance is of widespread interest for applications such as security enforcement and information protection. However, testing the correctness or completeness of provenance systems is challenging. In some cases, there is not even a clear consensus about what behaviour is correct. This work presents the study of system behaviour through the analysis of system-level provenance and the provenance systems that collect them. Besides, an automated tool, ProvMark is presented for the automation of the process and provides an additional layer of expressiveness benchmarking on existing provenance systems and their provenance result. This helps to understand patterns of system behaviour for security and other applications. It also allows provenance system developers to verify their tools and allows end-users to compare the tools at the same level to choose a suitable one for their purposes.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130090835","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}
Many Internet of Things (IoT) applications must perform their Big Data analytics tasks at the edge to meet their real-time needs and overcome the constraints on and reliability of network resources. Since traditional CPUs cannot meet these demands, solutions are sought by using accelerator hardware such as FPGAs, GPUs and TPUs to address these challenges. My doctoral research is focusing on ascertaining the feasibility of utilizing these accelerators for real-time IoT Big Data analytics, and in turn investigating dynamic resource management algorithms to schedule edge-based accelerator resources in the presence of highly dynamic IoT workloads.
{"title":"Dynamic resource management algorithms for edge computing using hardware accelerators","authors":"Robert Canady","doi":"10.1145/3366624.3368167","DOIUrl":"https://doi.org/10.1145/3366624.3368167","url":null,"abstract":"Many Internet of Things (IoT) applications must perform their Big Data analytics tasks at the edge to meet their real-time needs and overcome the constraints on and reliability of network resources. Since traditional CPUs cannot meet these demands, solutions are sought by using accelerator hardware such as FPGAs, GPUs and TPUs to address these challenges. My doctoral research is focusing on ascertaining the feasibility of utilizing these accelerators for real-time IoT Big Data analytics, and in turn investigating dynamic resource management algorithms to schedule edge-based accelerator resources in the presence of highly dynamic IoT workloads.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"50 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120971454","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}
Quite recently, the community has adopted the Cloud-native concept, building application workflows based on microservices. The majority of these services are deployed as containers. Unikernels, which package applications within a single-address space library OS, have been proposed as a stronger isolation mechanism. However, due to different storage semantics between them, the state-of-the-art approaches for using unikernels in place of containers result in decreased performance, inefficient resource utilization and limited functionality. In this work we bridge the storage gap by designing a framework, which extends the Docker storage layer to support unikernel requirements. We show that our framework improves boot time while reducing storage space requirements.
{"title":"Efficient storage support for unikernels as containers","authors":"Orestis Lagkas Nikolos","doi":"10.1145/3366624.3368168","DOIUrl":"https://doi.org/10.1145/3366624.3368168","url":null,"abstract":"Quite recently, the community has adopted the Cloud-native concept, building application workflows based on microservices. The majority of these services are deployed as containers. Unikernels, which package applications within a single-address space library OS, have been proposed as a stronger isolation mechanism. However, due to different storage semantics between them, the state-of-the-art approaches for using unikernels in place of containers result in decreased performance, inefficient resource utilization and limited functionality. In this work we bridge the storage gap by designing a framework, which extends the Docker storage layer to support unikernel requirements. We show that our framework improves boot time while reducing storage space requirements.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"81 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124781705","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 recent rise of cloud applications, representing large complex modern distributed services, has made performance monitoring a major issue. In our research, we propose that the cloud infrastructure can provide Monitoring as a Service to cloud applications in a transparent manner without the need for software instrumentation and allowing for a flexible placement of logging functionality, by exploiting SDN and NVF. Our proposal consists of two major components: the first one is a prototype architecture design and implementation for non-intrusive application performance monitoring with a comprehensive performance evaluation to highlight the trade-offs. The second proposal is dynamic application topology detection which gives the cloud users a global view of how their application is executing across services.
{"title":"Monitoring as a service for SDN Based cloud data centers","authors":"Mona Elsaadawy","doi":"10.1145/3366624.3368166","DOIUrl":"https://doi.org/10.1145/3366624.3368166","url":null,"abstract":"The recent rise of cloud applications, representing large complex modern distributed services, has made performance monitoring a major issue. In our research, we propose that the cloud infrastructure can provide Monitoring as a Service to cloud applications in a transparent manner without the need for software instrumentation and allowing for a flexible placement of logging functionality, by exploiting SDN and NVF. Our proposal consists of two major components: the first one is a prototype architecture design and implementation for non-intrusive application performance monitoring with a comprehensive performance evaluation to highlight the trade-offs. The second proposal is dynamic application topology detection which gives the cloud users a global view of how their application is executing across services.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125958843","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}
Data analytics applications are deployed on large-scale distributed systems. In order to ensure high performance, troubleshooting for such applications and underlying systems is critical. In this thesis, we focus on efficient log analysis for troubleshooting distributed data analytics systems. We made the following contributions. 1) We designed a tool that collects logs and resource metrics of distributed data analytics systems to facilitate troubleshooting processes. 2) We designed a log analysis tool that is able to extract semantic meaning from logs and automatically report potential anomalies by leveraging natural language processing approaches.
{"title":"Troubleshooting distributed data analytics systems","authors":"Aidi Pi","doi":"10.1145/3366624.3368157","DOIUrl":"https://doi.org/10.1145/3366624.3368157","url":null,"abstract":"Data analytics applications are deployed on large-scale distributed systems. In order to ensure high performance, troubleshooting for such applications and underlying systems is critical. In this thesis, we focus on efficient log analysis for troubleshooting distributed data analytics systems. We made the following contributions. 1) We designed a tool that collects logs and resource metrics of distributed data analytics systems to facilitate troubleshooting processes. 2) We designed a log analysis tool that is able to extract semantic meaning from logs and automatically report potential anomalies by leveraging natural language processing approaches.","PeriodicalId":376496,"journal":{"name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124298827","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：