this work explores the use of reinforcement learning to design a proactive cloud resource auto-scaler that is able to predict usage across a distributed microservice application. the focus is on serving time-sensitive...
详细信息
ISBN:
(纸本)9781665460873
this work explores the use of reinforcement learning to design a proactive cloud resource auto-scaler that is able to predict usage across a distributed microservice application. the focus is on serving time-sensitive workloads, e.g., industrial automation, connected XR/VR (eXtended Reality/Virtual Reality), etc., where each job has a deadline and there is some cost associated with missing a deadline. A simple workload model, as well as a microservice application model, is presented. A reinforcement learning agent is trained to identify workloads and predict needed utilization for identified service chains. the results are compared to standard purely reactive techniques.
Cloud-native as a style to build web applications embraces the potential of cloud computing. A possibility to evaluate software architectures of cloud-native applications according to quality aspects would be benefici...
详细信息
ISBN:
(纸本)9781665460873
Cloud-native as a style to build web applications embraces the potential of cloud computing. A possibility to evaluate software architectures of cloud-native applications according to quality aspects would be beneficial to developers, but is challenging due to the thematic breadth of cloud-native ranging from design to operation of applications. this work therefore evaluates existing architecture description languages according to their suitability for representing those architectural aspects specific to the cloud-native style. the evaluation is driven by a recently proposed quality model for which a suitable architectural modeling option is needed. We find that several existing languages are suitable as a basis for implementing an extension specific to the quality model. We choose TOSCA as an established standard to implement such an extension with corresponding tooling support.
Applications such as machine learning training systems or log collection generate and consume large amounts of data. Object storage systems provide a simple abstraction to store and access such large datasets. these d...
详细信息
ISBN:
(纸本)9781450392570
Applications such as machine learning training systems or log collection generate and consume large amounts of data. Object storage systems provide a simple abstraction to store and access such large datasets. these datasets are typically larger than the capacities of individual storage servers, and require fault tolerance through replication. In this paper, we present Kua, a distributed object storage system built over Named Data networking (NDN). the data-centric nature of NDN helps Kua maintain a simple design while catering to requirements of storing large objects, providing fault tolerance, low latency and strong consistency guarantees, along with data-centric security. Our prototype Kua implementation provides easy-to-use primitives to let applications store and access data securely, and our initial evaluation suggests that Kua can leverage NDN's capabilities of multicast data delivery and in-network caching to achieve higher efficiency than existing object storage systems.
Edge computing (EC) is an act of bringing computational and storage capability near data sources. It helps to reduce response times and bandwidth requirements. However, the rapid proliferation of edge devices has expa...
详细信息
In this paper, we introduce an information-centric service mesh for autonomous in-network computing. the information-centric service mesh offers service-centric networking, not connectivity-based networking provided b...
详细信息
ISBN:
(纸本)9781450392570
In this paper, we introduce an information-centric service mesh for autonomous in-network computing. the information-centric service mesh offers service-centric networking, not connectivity-based networking provided by the current container orchestration, like Kubernetes (K8s). We implement the information-centric service mesh by adopting an ambassador container style and using Cefore and Cefpyco which is the CCNx software implementation developed by NICT in Japan. For the proof-of-concept test, we demonstrate the end-to-end delay of more complex service chain models (up to 17 nodes) on our K8s cluster.
We conducted a literature review to draw a short roadmap of boththe drivers and challenges related to social networking in the banking industry. We extracted from the literature simple models based on drivers and cha...
详细信息
Edge to Cloud Continuum is a concept that integrates cloud computing and cellular networks that has been gaining popularity due to its potential to provide a seamless user experience and address the challenges of mana...
详细信息
ISBN:
(纸本)9798350399806
Edge to Cloud Continuum is a concept that integrates cloud computing and cellular networks that has been gaining popularity due to its potential to provide a seamless user experience and address the challenges of managing complex multi-domain networks involving massive IoT devices. Enabling intelligence in the Edge to Cloud Continuum can further enhance its capabilities, offering benefits such as reduced latency, improved scalability, enhanced resource utilization, and increased context awareness. this paper provides insights into the opportunities and challenges of enabling intelligence in Edge to Cloud Continuum, highlighting the potential of this technology. this study presents a comprehensive review of the existing literature on enabling intelligence in Edge to Cloud Continuum, to reach the research questions that will construct the PhD. Various tools and technologies that can be used to integrate intelligence into the Edge to Cloud Continuum system were explored and analyzed. In addition, this study provides a detailed work plan for the upcoming months of the project.
Serverless computing emerged as a promising cloud computing paradigm for deploying cloud-native applications but raises new performance challenges. Existing performance evaluation studies focus on micro-benchmarking t...
详细信息
ISBN:
(纸本)9781665460873
Serverless computing emerged as a promising cloud computing paradigm for deploying cloud-native applications but raises new performance challenges. Existing performance evaluation studies focus on micro-benchmarking to measure an individual aspect of serverless functions, such as CPU speed, but lack an in-depth analysis of differences in application performance across cloud providers. this paper presents CrossFit, an approach for detailed and fair cross-provider performance benchmarking of serverless applications based on a providerindependent tracing model. Our case study demonstrates how detailed distributed tracing enables drill-down analysis to explain performance differences between two leading cloud providers, AWS and Azure. the results for an asynchronous application show that trigger time contributes most delay to the end-to-end latency and explains the main performance difference between cloud providers. Our results further reveal how increasing and bursty workloads affect performance stability, median latency, and tail latency.
the proceedings contain 28 papers. the special focus in this conference is on Big Data and Social computing. the topics include: Network Analysis Reveals Regional Disparity in COVID-19 Policymaking;exploring Urba...
ISBN:
(纸本)9789819758029
the proceedings contain 28 papers. the special focus in this conference is on Big Data and Social computing. the topics include: Network Analysis Reveals Regional Disparity in COVID-19 Policymaking;exploring Urban Spatial-temporal Patterns via Large-scale Vehicle Travel Data: the Role of Geographical Attributes and Traveler Characteristics;mapping Gridded Wealth Index Using Open Geospatial Data in Zambia;bidirectional Multi-grain Graph Convolution Network for Origin-Destination Demand Prediction;the Prospects of Multi-modal Pre-trained Models in Epidemic Forecasting;deep Reinforcement Learning Based Dynamic Bus Timetable Scheduling with Bidirectional Constraints;modeling Knowledge Spillover Effects in High-Speed Rail Development: A Discrete Simulation Approach Using Cellular Automata;Educators’ networking Interacts with Digital Competence Heterogeneity to Enhance the Implementation of AIEd: A Mixed‐Methods Study;intelligent Fatigue Driving Detection Method Based on Fusion of Smartphone and Smartwatch Data;SCPM-R+ER: A R+ER-based Algorithm for Mining Spatial Co-location Patterns;extracting Spatial High Utility Co-location Patterns Based on Fuzzy Feature Clusters;incremental Network Traffic Category Models Based on Hybrid Learning Strategies;Modeling the BGP Prefix Hijack via Pollution and Recovery Processes;a Weakly Supervised Method for Encrypted Traffic Classification in the Dark Web;rumor Detection Based on Conflict and Bot Features;a Study of Digital Nomad Culture and Local Social Practices–Based on Fieldwork Research in a Certain Area of Southwest China;analysis of the Relationship Between Temperature and Insomnia Based on Social Media Text;do Gender Role Attitudes Affect Fertility Intentions ?—Evidence from international Data;Dynamic Shifts: the Rise of Unicorns in the AI Ecosystem;measurement and Analysis of China’s Fashion Events on Social Media: A Study of Shanghai Fashion Week;enhanced Product Embedding with Sememe for Product Search;temporal Knowledge Grap
To address the challenges of limited computing resources, complex data processing, and high security requirements in the editorial and publishing process, this paper proposes a collaborative platform that integrates c...
详细信息
暂无评论