ML-FaaS: Toward Exploiting the Serverless Paradigm to Facilitate Machine Learning Functions as a Service

Paraskevoulakou, Efterpi; Kyriazis, Dimosthenis

doi:10.1109/tnsm.2023.3239672

Cited by 10 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paraskevoulakou et al [22] proposed an extensible generalized approach to deploy Machine Learning Functions as a Service (MLFaaS). Their approach exceeds the traditional isolated and atomic services by offering composite services such as workflows and pipelines ML operations.…”

Section: Related Workmentioning

confidence: 99%

An Optimized Intelligent Open-Source MLaaS Framework for User-Friendly Clustering and Anomaly Detection

ElDahshan,

Abutaleb,

Elemary

et al. 2024

Preprint

View full text Add to dashboard Cite

In the big data era, businesses are in dire need of intelligent solutions to rapidly extract valuable insights. However, not all companies possess the specialized expertise required to operate machine learning algorithms. To bridge this gap, this paper introduces a cost-effective, user-friendly, dependable, adaptable, and scalable solution for visualizing, analyzing, processing, and extracting valuable insights from data. The proposed solution is an optimized open-source unsupervised machine learning as a service (MLaaS) framework that caters to both experts and non-experts in machine learning. The framework aims to assist companies and organizations in solving problems related to clustering and anomaly detection, even without prior experience or internal infrastructure. With a focus on several clustering and anomaly detection techniques, the proposed framework automates data processing while allowing user intervention. Furthermore, the proposed solution is expandable; it may include additional algorithms. It is versatile and capable of handling diverse datasets by generating separate rapid artificial intelligence (AI) models for each dataset and facilitating their comparison rapidly. The proposed framework provides a solution through a Representational State Transfer (RESTful) Application Programming Interface (API), enabling seamless integration with various systems. Real-world testing of the proposed framework on customer segmentation and fraud detection data demonstrates that it is reliable, efficient, cost-effective, and time-saving. With this innovative MLaaS framework, companies may harness the full potential of business analysis.

show abstract

Section: Related Workmentioning

confidence: 99%

An Optimized Intelligent Open-Source MLaaS Framework for User-Friendly Clustering and Anomaly Detection

ElDahshan,

Abutaleb,

Elemary

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…AI applications have also exploited event-driven architecture approaches to enable real-time decision-making. For instance, Paraskevoulakou et al [15] propose a Machine Learning Function as a Service platform that enables the development of edge AI workflows, overcoming the constraints of serverless environments. Similarly, "A serverless gateway for event-driven machine learning inference in multiple clouds" paper [16] outlines how a serverless architecture can be utilized for machine learning inference with AI models deployed on serverless platforms.…”

Section: Related Workmentioning

confidence: 99%

Event-Driven AI Workflows in Serverless Computing: Enabling Real-Time Data Processing and Decision-Making

Donati,

Macario,

Karim

2024

Preprint

View full text Add to dashboard Cite

Real-time data processing and decision-making are increasingly crucial in various applications, driven by the continuous influx of data streams. Event-driven AI workflows within serverless computing environments offer a promising approach to handle these real-time demands efficiently. This paper presents a framework for simulating and analyzing the performance characteristics of such workflows. Our proposed approach utilizes simulated data with varying event rates and durations to investigate the impact on key performance metrics like latency, throughput, and resource utilization. This enables a comprehensive evaluation of the inherent trade-offs within event-driven AI systems. The key findings reveal a trade-off between latency and throughput. As the event rate increases, average processing latency generally increases while average throughput increases. Resource utilization remains relatively stable across different event rates in the simulated scenarios (e.g., 75.55\% at 2 events/second, 74.51\% at 10 events/second). This framework provides a valuable tool for understanding the performance characteristics of event-driven AI workflows and optimizing resource allocation strategies.

show abstract

“…In contrast to serverful computing models, developers employing serverless do not need to worry about managing infrastructure resources because platforms manage such things on their behalf. The heart of serverless computing is the cloud functions which are written by developers and invoked as units of execution via the Internet [56]. Serverless computing may also be seen from the perspective of developers as Functionas-a-Service (FaaS), which enables developers to create and execute their applications (or functions) without having to deal with the complexity of creating and managing the underlying infrastructure [57].…”

Section: Introductionmentioning

confidence: 99%

Efficient Security for Resource-Constrained Devices with LPM: A Lightweight Protocol Utilizing Chaotic Map-Based S-Box

Ramesh,

Ramesh

2024

Preprint

View full text Add to dashboard Cite

Serverless computing has become a very popular cloud-based solution for designing, testing and deploying the applications as serverless functions. Serverless computing has become a buzzword in both industry and academia as many large IT giants have rolled out their own serverless platforms. Independent design, deployment and auto scalability are its major features with Function-as-a-Service (FaaS) as its popular implementation. On the other hand, microservices are an emerging trend for design of large enterprise applications as many companies like Amazon, Uber and Spotify have already migrated their existing applications to microservices style. However, with the advent of serverless platforms, to design efficient applications with simpler infrastructure management, reduced operational overhead and cost factor, migrating microservices to serverless has become inevitable. Additionally, existing studies report that serverless platforms suffer from cold start latency. Therefore, in this paper, a framework is proposed which has two phases: (i) an empirical investigation to find out the impact of programming language on the cold start of serverless functions and (ii) an approach for migration of microservices to serverless platforms. The evaluation results help us to identify the platform with low cold start latency and also recommend the choice of programming language with lower latency. After migrating the containerized microservices to serverless, a comparison in terms of performance is conducted. The applications designed as serverless functions exhibit better response time and throughput compared to containerized microservices.

show abstract

ML-FaaS: Toward Exploiting the Serverless Paradigm to Facilitate Machine Learning Functions as a Service

Cited by 10 publications

References 36 publications

An Optimized Intelligent Open-Source MLaaS Framework for User-Friendly Clustering and Anomaly Detection

An Optimized Intelligent Open-Source MLaaS Framework for User-Friendly Clustering and Anomaly Detection

Event-Driven AI Workflows in Serverless Computing: Enabling Real-Time Data Processing and Decision-Making

Efficient Security for Resource-Constrained Devices with LPM: A Lightweight Protocol Utilizing Chaotic Map-Based S-Box

Contact Info

Product

Resources

About