Node failures are very common in distributed storage systems. Regenerating codes can minimize the network bandwidth required to recover the data lost on the failed nodes. Minimum Storage Regenerating (MSR) code is a class of regenerating codes that can maximize the storage efficiency, meanwhile minimizing the repair bandwidth. The original MSR code via Product Matrix (PM) provides a means for single failed node recovery. In this work, an algorithm of recovering multiple failed nodes concurrently with the minimum feasible bandwidth will be proposed, extending the framework of the original PM MSR code. Based on the proposed strategy, the needed bandwidth for centralized and distributed recovery policies, which are the two major categories of repairing policies, will be explicitly expressed against the coding parameters and the number of failed nodes, hence numerical comparison can be made between them. Moreover, the impact of Repairing Degree (the number of surviving nodes from which the assistant data are downloaded ) on the bandwidth cost will be studied to help make optimal decision in practical storage systems.
{"title":"Concurrent Failure Recovery for MSR Regenerating Code via Product Matrix Construction","authors":"Jingyao Zhang","doi":"10.1145/3368235.3368871","DOIUrl":"https://doi.org/10.1145/3368235.3368871","url":null,"abstract":"Node failures are very common in distributed storage systems. Regenerating codes can minimize the network bandwidth required to recover the data lost on the failed nodes. Minimum Storage Regenerating (MSR) code is a class of regenerating codes that can maximize the storage efficiency, meanwhile minimizing the repair bandwidth. The original MSR code via Product Matrix (PM) provides a means for single failed node recovery. In this work, an algorithm of recovering multiple failed nodes concurrently with the minimum feasible bandwidth will be proposed, extending the framework of the original PM MSR code. Based on the proposed strategy, the needed bandwidth for centralized and distributed recovery policies, which are the two major categories of repairing policies, will be explicitly expressed against the coding parameters and the number of failed nodes, hence numerical comparison can be made between them. Moreover, the impact of Repairing Degree (the number of surviving nodes from which the assistant data are downloaded ) on the bandwidth cost will be studied to help make optimal decision in practical storage systems.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114955398","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}
{"title":"12th IEEE/ACM International UCC/BDCAT'19 Doctoral Symposium Chairs' Welcome Message","authors":"L. Bittencourt, Diego Perez-Palacin","doi":"10.1145/3368235.3368882","DOIUrl":"https://doi.org/10.1145/3368235.3368882","url":null,"abstract":"","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132837198","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}
Knowledge discovery is a process that seeks new knowledge about an application domain. It consists of many steps, one of which is data mining, each aiming to complete a discovery task, and accomplished by the application of a discovery method [1]. On this subject, the Semantic Web (SW) is an effort to interchange unstructured data over the Web into a structured format that is processable not only by human beings but also by computers [2]. The SW creates a distributed framework to publish, query, and reuse information [3]. The key backbones of SW are ontologies and annotations that provide semantics for raw data are known as Resource Description Framework (RDF) data [4]. The RDF data can also be published over Linked Open Data (LOD) cloud. To highlight the vision of SW, we would like to run a tutorial. The main goal of this tutorial is to provide background knowledge about SW, RDF, Web Ontology Language (OWL), SPARQL, knowledge graph, graph databases, and SW-based applications. This tutorial will show how SW provides explicit models of the terminology of a domain to improve information access.
{"title":"The Vision of Semantic Web","authors":"Molood Barati","doi":"10.1145/3368235.3370268","DOIUrl":"https://doi.org/10.1145/3368235.3370268","url":null,"abstract":"Knowledge discovery is a process that seeks new knowledge about an application domain. It consists of many steps, one of which is data mining, each aiming to complete a discovery task, and accomplished by the application of a discovery method [1]. On this subject, the Semantic Web (SW) is an effort to interchange unstructured data over the Web into a structured format that is processable not only by human beings but also by computers [2]. The SW creates a distributed framework to publish, query, and reuse information [3]. The key backbones of SW are ontologies and annotations that provide semantics for raw data are known as Resource Description Framework (RDF) data [4]. The RDF data can also be published over Linked Open Data (LOD) cloud. To highlight the vision of SW, we would like to run a tutorial. The main goal of this tutorial is to provide background knowledge about SW, RDF, Web Ontology Language (OWL), SPARQL, knowledge graph, graph databases, and SW-based applications. This tutorial will show how SW provides explicit models of the terminology of a domain to improve information access.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134441991","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}
Chunho Cho, Guan-Yi Lee, Yueh-Lin Tsai, Kun-Chan Lan
Three methods including LSTM, Seq2seq and WaveNet are implemented in this study. We compare the performance of different deep learning methods in predicting stock prices. We use the correlation between the predicted price and the actual price as the performance metric to evaluate the effectiveness of these methods.
{"title":"Toward Stock Price Prediction using Deep Learning","authors":"Chunho Cho, Guan-Yi Lee, Yueh-Lin Tsai, Kun-Chan Lan","doi":"10.1145/3368235.3369367","DOIUrl":"https://doi.org/10.1145/3368235.3369367","url":null,"abstract":"Three methods including LSTM, Seq2seq and WaveNet are implemented in this study. We compare the performance of different deep learning methods in predicting stock prices. We use the correlation between the predicted price and the actual price as the performance metric to evaluate the effectiveness of these methods.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114183862","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}
Cloud computing owes much of its success to the ease and cost effectiveness with which new systems can be built using remote third-party services. However, the response time, reliability and other quality-of-service (QoS) properties of these services are often uncertain. As such, ensuring that service-based systems achieve their QoS requirements is very challenging. This talk will describe how recent advances in probabilistic model learning, analysis and synthesis can help address this challenge both during service-based system design and verification, and at runtime.
{"title":"Taming Service Uncertainty through Probabilistic Model Learning, Analysis and Synthesis","authors":"R. Calinescu","doi":"10.1145/3368235.3369375","DOIUrl":"https://doi.org/10.1145/3368235.3369375","url":null,"abstract":"Cloud computing owes much of its success to the ease and cost effectiveness with which new systems can be built using remote third-party services. However, the response time, reliability and other quality-of-service (QoS) properties of these services are often uncertain. As such, ensuring that service-based systems achieve their QoS requirements is very challenging. This talk will describe how recent advances in probabilistic model learning, analysis and synthesis can help address this challenge both during service-based system design and verification, and at runtime.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129099679","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}
Constant innovations in the Internet of Things (IoT) in latest years have generated large amounts of data, putting pressure on the infrastructure of cloud computing. Fog computing has recently become a popular computing paradigm that can provide computing resources close to the end users and solve multiple issues with the current cloud-only systems. However, the scheduling of workflow applications in the cloud-fog environment to find the best tradeoff between makespan and price is facing enormous challenges. To address such a challenge, this paper presents an adaptation of the Path-Clustering Heuristic to the cloud-fog environment for multiple workflows. Firstly, we define the models for workflow execution time and resource cost in fog computing.Afterwards, we describe the newly proposed algorithms. We validate the efficiency of the algorithms with extensive simulation. Experimental results show that our scheduling adaptation achieves better performance while keeping similar costs compared to others.
{"title":"Resource Allocation for Multiple Workflows in Cloud-Fog Computing Systems","authors":"Jean Lucas de Souza Toniolli, B. Jaumard","doi":"10.1145/3368235.3368846","DOIUrl":"https://doi.org/10.1145/3368235.3368846","url":null,"abstract":"Constant innovations in the Internet of Things (IoT) in latest years have generated large amounts of data, putting pressure on the infrastructure of cloud computing. Fog computing has recently become a popular computing paradigm that can provide computing resources close to the end users and solve multiple issues with the current cloud-only systems. However, the scheduling of workflow applications in the cloud-fog environment to find the best tradeoff between makespan and price is facing enormous challenges. To address such a challenge, this paper presents an adaptation of the Path-Clustering Heuristic to the cloud-fog environment for multiple workflows. Firstly, we define the models for workflow execution time and resource cost in fog computing.Afterwards, we describe the newly proposed algorithms. We validate the efficiency of the algorithms with extensive simulation. Experimental results show that our scheduling adaptation achieves better performance while keeping similar costs compared to others.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130402102","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}
Fog computing offloads latency critical services of a Cloud application onto resources located at the edge of the network that are in close proximity to end-user devices. The research in this paper is motivated towards characterising and estimating the time taken to offload a service using containers, which is investigated in the context of the 'Save and Load' container migration technique. To this end, the research addresses questions such as whether fog offloading can be accurately modelled and which system and network related parameters influence offloading. These are addressed by exploring a catalogue of 21 different metrics both at the system and process levels that is used as input to four estimation techniques using a collective model and individual models to predict the time taken for offloading. The study is pursued by collecting over 1.1 million data points and the preliminary results indicate that offloading can be modelled accurately.
{"title":"Performance Estimation of Container-Based Cloud-to-Fog Offloading","authors":"A. Majeed, P. Kilpatrick, I. Spence, B. Varghese","doi":"10.1145/3368235.3368847","DOIUrl":"https://doi.org/10.1145/3368235.3368847","url":null,"abstract":"Fog computing offloads latency critical services of a Cloud application onto resources located at the edge of the network that are in close proximity to end-user devices. The research in this paper is motivated towards characterising and estimating the time taken to offload a service using containers, which is investigated in the context of the 'Save and Load' container migration technique. To this end, the research addresses questions such as whether fog offloading can be accurately modelled and which system and network related parameters influence offloading. These are addressed by exploring a catalogue of 21 different metrics both at the system and process levels that is used as input to four estimation techniques using a collective model and individual models to predict the time taken for offloading. The study is pursued by collecting over 1.1 million data points and the preliminary results indicate that offloading can be modelled accurately.","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131025774","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}
{"title":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","authors":"","doi":"10.1145/3368235","DOIUrl":"https://doi.org/10.1145/3368235","url":null,"abstract":"","PeriodicalId":166357,"journal":{"name":"Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133681987","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：