793 Hits in 5.4 sec

Proactive Container Auto-scaling for Cloud Native Machine Learning Services

David Buchaca, Josep LLuis Berral, Chen Wang, Alaa Youssef
2020 2020 IEEE 13th International Conference on Cloud Computing (CLOUD)  
Understanding the resource usage behaviors of the ever-increasing machine learning workloads are critical to cloud providers offering Machine Learning (ML) services.  ...  Capable of auto-scaling resources for customer workloads can significantly improve resource utilization, thus greatly reducing the cost.  ...  The container-based environment, namely cloud-native, is becoming the de facto standard for deploying services in the cloud, especially for Cloud Machine Learning Services [2] , [3] , [4] .  ... 
doi:10.1109/cloud49709.2020.00070 fatcat:nylyu5iz3nhsvpk6rv7y25wype

When Less is More: Core-Restricted Container Provisioning for Serverless Computing

Gaetano Somma, Constantine Ayimba, Paolo Casari, Simon Pietro Romano, Vincenzo Mancuso
2020 Zenodo  
We propose to drive auto-scaling decisions through a Q-learning algorithm, which is agnostic to the specific computing environment, and proceeds based only on the load of the physical processors assigned  ...  Second, we devise a resource management mechanism leveraging on both admission control and auto-scaling techniques.  ...  Cloud Platform and Amazon Web Services (AWS) [3] .  ... 
doi:10.5281/zenodo.3637609 fatcat:sl3knveibfhtjiq4o77i2gmn34

HotCloudPerf 2019: The Second Workshop on Hot Topics in Cloud Computing Performance

2019 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W)  
Emerging architectures, techniques, and real-world systems include hybrid deployment, serverless operation, everything as a service, complex workflows, auto-scaling and -tiering, etc.  ...  Each year, the workshop chooses a focus theme to explore; for 2019, the theme is "Performance from the cloud datacenter to the edge."  ...  . : 800 -- 813 , 800813 April 2019, • Joel Reijonen and Miika Komu (Ericsson): Edge-Native Machine Learning Johannes Grohmann: The SPEC-RG Reference Architecture for FaaS: From Microservices and Containers  ... 
doi:10.1109/fas-w.2019.00007 fatcat:fc25hu2gprcrld3ntb6pfcybye

An Auto-Scaling Cloud Controller Using Fuzzy Q-Learning - Implementation in OpenStack [chapter]

Hamid Arabnejad, Pooyan Jamshidi, Giovani Estrada, Nabil El Ioini, Claus Pahl
2016 Lecture Notes in Computer Science  
Auto-scaling, i.e., acquiring and releasing resources automatically, is a central feature of cloud platforms.  ...  However, providing good thresholds for autoscaling is challenging. Recently, machine learning approaches have been used to complement and even replace expert knowledge.  ...  Heat along with ceilometer can create an auto-scaling service.  ... 
doi:10.1007/978-3-319-44482-6_10 fatcat:rgqvqs4strf6zidmrhisqwic5q

A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling

Hamid Arabnejad, Claus Pahl, Pooyan Jamshidi, Giovani Estrada
2017 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)  
A goal of cloud service management is to design self-adaptable auto-scaler to react to workload fluctuations and changing the resources assigned.  ...  In this paper, we compare two dynamic learning strategies based on a fuzzy logic system, which learns and modifies fuzzy scaling rules at runtime.  ...  We used our auto-scaling manager instead of the native auto-scaling tool in OpenStack, which is designed by setting alarms based on threshold evaluations for a collection of metrics from Ceilometer.  ... 
doi:10.1109/ccgrid.2017.15 dblp:conf/ccgrid/ArabnejadPJE17 fatcat:nh2rs5xknncxllwbtxh2xkge5q

Efficiency in the Serverless Cloud Computing Paradigm: A Survey Study [article]

Chavit Denninnart, Mohsen Amini Salehi
2021 arXiv   pre-print
Serverless computing along with Function-as-a-Service (FaaS) are forming a new computing paradigm that is anticipated to found the next generation of cloud systems.  ...  The popularity of this paradigm is due to offering a highly transparent infrastructure that enables user applications to scale in the granularity of their functions.  ...  ., Tensorflow for machine learning tasks, FFmpeg [42] for multimedia processing tasks).  ... 
arXiv:2110.06508v1 fatcat:gp7dxqmmavfbhf7n5bssws2tje

A Resource Management Protocol for Mobile Cloud Using Auto-Scaling [article]

Chathura Sarathchandra Magurawalage, Kun Yang, Ritosa Patrik, Michael Georgiades, Kezhi Wang
2017 arXiv   pre-print
Experiments on resource management using cloud auto-scaling shows that resource (CPU, RAM, Storage) scaling times vary.  ...  In this paper, we propose a protocol for task offloading and for managing resources in both C-RAN and mobile cloud together using a centralised controller.  ...  Kernel Virtual Machine), cloud platforms (e.g. OpenStack) and cloud service providers (e.g. Amazon EC2 [29] ) [14] .  ... 
arXiv:1701.00384v3 fatcat:4hssrfgtvvazvlei77h2t33rtu

Cloud Robotics

Giovanni Toffetti, Tobias Lötscher, Saken Kenzhegulov, Josef Spillner, Thomas Michael Bohnert
2017 Companion Proceedings of the10th International Conference on Utility and Cloud Computing - UCC '17 Companion  
Robots are moving out of factories, service robotics is bringing them to our homes, work environments, cities, and outdoors.  ...  We relate on our experience building cloud robotics applications spanning heterogeneous hardware (i.e., robots and cloud servers) through a use case scenario.  ...  It has also been supported by an AWS Cloud Credits for Research grant, and a Google Cloud Platform Education grant which helped us run our experiments on public clouds.  ... 
doi:10.1145/3147234.3148100 dblp:conf/ucc/ToffettiLKSB17 fatcat:yqjnxznrsbfkviwj73h3bbxkxe

A study on performance measures for auto-scaling CPU-intensive containerized applications

Emiliano Casalicchio
2019 Cluster Computing  
Then, the performance of a variant of Kubernetes' auto-scaling algorithm, that transparently uses the absolute usage measures to scale-in/out containers, is evaluated through a wide set of experiments.  ...  The former account for the actual utilization of resources in the host system, while the latter account for the share that each container has of the resources used.  ...  Cloud service providers today offer container-based services and container development platforms [13] : Google container engine, Amazon Elastic Container Service and Microsoft Azure Container Service  ... 
doi:10.1007/s10586-018-02890-1 fatcat:oovaodu3cver5kwc37cv3edo4m

Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution [article]

Pooyan Jamshidi, Amir Sharifloo, Claus Pahl, Andreas Metzger, Giovani Estrada
2015 arXiv   pre-print
The experimental results indicate that FQL4KE outperforms our previously developed fuzzy controller without learning mechanisms and the native Azure auto-scaling.  ...  In this paper, we propose learning adaptation rules during runtime. To this end, we introduce FQL4KE, a self-learning fuzzy cloud controller.  ...  ACKNOWLEDGMENT The authors would like to thank Soodeh Farokhi and Saeid Masoumzadeh for their constructive comments on the final draft of the paper.  ... 
arXiv:1507.00567v1 fatcat:uyci4bfkwbbuzgypzzi63pqajy

A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it [article]

Viswanath Ganapathy, Sauptik Dhar, Olimpiya Saha, Pelin Kurt Garberson, Javad Heydari, Mohak Shah
2021 arXiv   pre-print
We highlight how such a step-wise approach can be advantageous for accurate model building and helpful for gaining insights into predictive maintenance of electromechanical appliances.  ...  Finally, we touch upon existing public data sources and provide a step-wise breakdown of an AI-driven proactive customer care (PCC) use-case, starting from generic anomaly detection to fault prediction  ...  We also acknowledge the Google Cloud Platform (GCP) team for providing us with the computing resources for the analyzing the Blackblaze dataset.  ... 
arXiv:2110.05015v1 fatcat:wjlrvk4hhbhkzlnkokz4pvwzn4

Machine Learning-Enabled Data Rate Prediction for 5G NSA Vehicle-to-Cloud Communications [article]

Benjamin Sliwa and Hendrik Schippers and Christian Wietfeld
2021 arXiv   pre-print
For this purpose, novel methods for proactive prediction of the end-to-end behavior are seen as key enablers.  ...  Although this operation mode is characterized by massive fluctuations of the observed data rate, the results show that conventional machine learning methods can utilize locally acquirable measurements  ...  RF Max depth 100 100 31 100 Number of trees 406 203 406 203 SVM Regularization C 100 100 100 100 Kernel coefficient γ Scale Auto Auto Auto XGB Max depth 1 10 10 1 Number  ... 
arXiv:2109.04117v1 fatcat:2x6gbjyjfrekrmqo2nehsaf3bu

MEDAL: An AI-driven Data Fabric Concept for Elastic Cloud-to-Edge Intelligence [article]

Vasileios Theodorou, Ilias Gerostathopoulos, Iyad Alshabani, Alberto Abello, David Breitgand
2021 arXiv   pre-print
Current Cloud solutions for Edge Computing are inefficient for data-centric applications, as they focus on the IaaS/PaaS level and they miss the data modeling and operations perspective.  ...  MEDAL facilitates building and managing data workflows on top of existing flexible and composable data services, seamlessly exploiting and federating IaaS/PaaS/SaaS resources across different Cloud and  ...  prediction due to vital signs; (ii) for local model training in case of distributed machine learning data applications, e.g., collection of sensitive (DBA) data from thousands of drivers and federated  ... 
arXiv:2102.13125v1 fatcat:m5dzoeutjrh65ftymi5fkxreae

Hybrid Clouds for Data-Intensive, 5G-Enabled IoT Applications: An Overview, Key Issues and Relevant Architecture

Panagiotis Trakadas, Nikolaos Nomikos, Emmanouel T. Michailidis, Theodore Zahariadis, Federico M. Facca, David Breitgand, Stamatia Rizou, Xavi Masip, Panagiotis Gkonis
2019 Sensors  
Furthermore, a decentralized hybrid cloud MEC architecture, resulting in a Platform-as-a-Service (PaaS) is proposed and its main building blocks and layers are thoroughly described.  ...  In this paper, an overview on the area of hybrid clouds considering relevant research areas is given, providing technologies and mechanisms for the formation of such MEC deployments, as well as emphasizing  ...  edges; (4) the automated management of complex tasks in the machine learning edge-cloud flow, ensuring an optimized machine learning lifecycle, including model training, model configuration and model  ... 
doi:10.3390/s19163591 fatcat:qz6md7lbsfhejcrs3e7vqigsnu

A Manifesto for Future Generation Cloud Computing

Rajkumar Buyya, Marco A. S. Netto, Adel Nadjaran Toosi, Maria Alejandra Rodriguez, Ignacio M. Llorente, Sabrina De Capitani Di Vimercati, Pierangela Samarati, Dejan Milojicic, Carlos Varela, Rami Bahsoon, Marcos Dias De Assuncao, Satish Narayana Srirama (+13 others)
2018 ACM Computing Surveys  
for improving the paper.  ...  ACKNOWLEDGMENTS We thank anonymous reviewers, Sartaj Sahni (Editor-in-Chief) and Antonio Corradi (Associate Editor) for their constructive suggestions and guidance on improving the content and quality  ...  and auto-scaling.  ... 
doi:10.1145/3241737 fatcat:bgb4qjtm5zgcbbtyy6x6anfeju
« Previous Showing results 1 — 15 out of 793 results