Adaptive Microservice Scaling for Elastic Applications

Coulson, Nathan Cruz; Sotiriadis, Stelios; Bessis, Nik

doi:10.1109/jiot.2020.2964405

Cited by 37 publications

(16 citation statements)

References 23 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coulson et al [6] developed a prototype based on micro-service for web application by autoscaling process and evaluated it for prediction using supervised machine learning. Wang et al [7] mentioned an elastic scheduling model that can solve task scheduling of different micro-services in cloud-based computing resources.…”

Section: A Microservices In Various Sectors and Cia Security Strategymentioning

confidence: 99%

EduChain: CIA-Compliant Blockchain for Intelligent Cyber Defense of Microservices in Education Industry 4.0

Rahman

Abuludin²,

Yuan³

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Massive data handling requirement in education industry 4.0 has attracted interests in the research of microservice architectures due to their scalability, resilience and elasticity characteristics. This development has been challenged by extensive data exchange required by a set of independent microservices to build a complete application, which could result in increasing risks and exposure to the security and privacy breaches of the data. It is imperative to see that educational data are highly sensitive, critical for ascertaining educational attainment and facilitating credentials for qualifcation verifcations. This paper puts forward a new proposal of devising a security and privacy-preserving design mechanism of data transactions in educational microservices leveraging the blockchain technology. The design comprises three phases, namely the blockchain framework, data sending-receiving and confdentialityintegrity-availability over a secured platform with each phase having detailed mechanisms for algorithm implementation. The proposal is shown to exhibit favourable performance in terms of time cost of publishing, throughput and latency, and shown to have high survey acceptance in terms of confdentiality, integrity and availability with approximately 10% improvement from prior blockchain adoption.

show abstract

Section: A Microservices In Various Sectors and Cia Security Strategymentioning

confidence: 99%

EduChain: CIA-Compliant Blockchain for Intelligent Cyber Defense of Microservices in Education Industry 4.0

Rahman

Abuludin²,

Yuan³

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…For microservices, request processing typically follows a deterministic dataflow-graph, instead of one with conditional execution paths as in inference serving systems. Machine learning methods are also employed for workload prediction in microservice systems for better autoscaling [51], [52]. Recently, DAGOR [14] provided overloading detection and collaborative load shedding in microservice systems.…”

Section: Related Workmentioning

confidence: 99%

FA2: Fast, Accurate Autoscaling for Serving Deep Learning Inference with SLA Guarantees

Razavi

Luthra

Koldehofe

et al. 2022

2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS)

View full text Add to dashboard Cite

Deep learning (DL) inference has become an essential building block in modern intelligent applications. Due to the high computational intensity of DL, it is critical to scale DL inference serving systems in response to fluctuating workloads to achieve resource efficiency. Meanwhile, intelligent applications often require strict service level agreements (SLAs), which need to be guaranteed when the system is scaled. The problem is complex and has been tackled only in simple scenarios so far.This paper describes FA2, a fast and accurate autoscaler concept for DL inference serving systems. In contrast to related works, FA2 adopts a general, contrived two-phase approach. Specifically, it starts by capturing the autoscaling challenges in a comprehensive graph-based model. Then, FA2 applies targeted graph transformation and makes autoscaling decisions with an efficient algorithm based on dynamic programming. We implemented FA2 and built and evaluated a prototype. Compared with state-of-the-art autoscaling solutions, our experiments showed FA2 to achieve significant resource reduction (19% under CPUs and 25% under GPUs, on average) in combination with low SLA violations (less than 1.5%). FA2 performed close to the theoretical optimum, matching exactly the optimal decisions (with the least required resources) in 96.8% of all the cases in our evaluation.

show abstract

“…By leveraging Docker containers, instant services can be implemented with lower overhead than through operating-system virtualization [19]. These containers run on a cluster-management infrastructure such as Apache Mesos to manage load balancing between containers in the cluster [20].…”

Section: A Microservices Architecturementioning

confidence: 99%

Implementation of Asynchronous Microservices Architecture on Smart Village Application

Asri¹,

Astawa²,

Sunaya³

et al. 2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

This paper discusses the implementation of microservices architecture in smart village applications. The smart village application is a village-based online marketplace that facilitates various business actors' buying and selling process in a village. This application manages five types of products: lodging reservations, tourist attraction tickets, culinary purchases, and purchasing knickknacks show tickets. The complexity of processes, data, and high potential users requires that the system architecture is designed to produce a scalable, fault-tolerant system and easy to develop. Microservices architecture is one of the recommended architectures for building a scalable, fault-tolerant, and maintainable application. This architecture has several variations, ranging from variations in communication between services to the technology used. The suitability of applications with architectural variations and the complexity is a challenge in implementing this architecture. This paper describes how to implement the microservices architecture in smart village applications. Design and implementation of the microservices architecture in the smart village application was followed the WSIM or Web Services Implementation Methodology stage. The implementation results show that the application is easier to manage because it is divided into independent microservices. Implementing asynchronous communication and a choreographic approach to each service makes the client application response faster; besides, it did not affect other services if there is a problematic service.

show abstract

Adaptive Microservice Scaling for Elastic Applications

Cited by 37 publications

References 23 publications

EduChain: CIA-Compliant Blockchain for Intelligent Cyber Defense of Microservices in Education Industry 4.0

EduChain: CIA-Compliant Blockchain for Intelligent Cyber Defense of Microservices in Education Industry 4.0

FA2: Fast, Accurate Autoscaling for Serving Deep Learning Inference with SLA Guarantees

Implementation of Asynchronous Microservices Architecture on Smart Village Application

Contact Info

Product

Resources

About