Understanding Cost Dynamics of Serverless Computing: An Empirical Study

• URL: http://arxiv.org/abs/2311.13242v1
• Date: Wed, 22 Nov 2023 09:01:23 GMT
• Title: Understanding Cost Dynamics of Serverless Computing: An Empirical Study
• Authors: Muhammad Hamza, Muhammad Azeem Akbar, Rafael Capilla
• Abstract summary: This study delves into how organizations anticipate the costs of adopting serverless. It also aims to com-prehend workload suitability and identify best practices for cost optimization of serverless applications.
• Score: 1.2905826135573395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The advent of serverless computing has revolutionized the landscape of cloud computing, offering a new paradigm that enables developers to focus solely on their applications rather than managing and provisioning the underlying infrastructure. These applications involve integrating individual functions into a cohesive workflow for complex tasks. The pay-per-use model and nontransparent reporting by cloud providers make it difficult to estimate serverless costs, imped-ing informed business decisions. Existing research studies on serverless compu-ting focus on performance optimization and state management, both from empir-ical and technical perspectives. However, the state-of-the-art shows a lack of em-pirical investigations on the understanding of the cost dynamics of serverless computing over traditional cloud computing. Therefore, this study delves into how organizations anticipate the costs of adopting serverless. It also aims to com-prehend workload suitability and identify best practices for cost optimization of serverless applications. To this end, we conducted a qualitative (interviews) study with 15 experts from 8 companies involved in the migration and development of serverless systems. The findings revealed that, while serverless computing is highly suitable for unpredictable workloads, it may not be cost-effective for cer-tain high-scale applications. The study also introduces a taxonomy for comparing the cost of adopting serverless versus traditional cloud.

Related papers

• A Penny a Function: Towards Cost Transparent Cloud Programming [3.858859576352153]
  Existing tools for understanding cost factors are often detached from source code. Existing cost models for cloud applications focus on specific factors such as compute resources. This paper presents initial work toward a cost model based on a directed graph that allows deriving monetary cost estimations directly from code.
  arXiv  Detail & Related papers  (2023-09-10T08:02:12Z)
• How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study [57.97785297481162]
  We evaluate the cost and throughput implications of training in different zones, continents, and clouds for representative CV, NLP, and ASR models. We show how leveraging spot pricing enables a new cost-efficient way to train models with multiple cheap instance, trumping both more centralized and powerful hardware and even on-demand cloud offerings at competitive prices.
  arXiv  Detail & Related papers  (2023-06-05T18:17:37Z)
• Mining for Cost Awareness in the Infrastructure as Code Artifacts of Cloud-based Applications: an Exploratory Study [1.5612101323427952]
  This study aims to provide empirical evidence of cost awareness by mining open source repositories of cloud-based applications. A systematic search through 152,735 repositories resulted in the selection of 2,010 relevant ones. The findings indicate that developers are not only concerned with the cost of their application deployments but also take actions to reduce these costs.
  arXiv  Detail & Related papers  (2023-04-15T10:49:35Z)
• CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing Environments [13.864161788250856]
  Key challenge for latency-critical tasks is to predict future workload demands to provision proactively. Existing AI-based solutions tend to not holistically consider all crucial aspects such as provision overheads, heterogeneous VM costs and Quality of Service (QoS) of the cloud system. We propose a novel method, called CILP, that formulates the VM provisioning problem as two sub-problems of prediction and optimization.
  arXiv  Detail & Related papers  (2023-02-11T09:15:34Z)
• Edge-Cloud Polarization and Collaboration: A Comprehensive Survey [61.05059817550049]
  We conduct a systematic review for both cloud and edge AI. We are the first to set up the collaborative learning mechanism for cloud and edge modeling. We discuss potentials and practical experiences of some on-going advanced edge AI topics.
  arXiv  Detail & Related papers  (2021-11-11T05:58:23Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)
• Distributed Deep Learning in Open Collaborations [49.240611132653456]
  We propose a novel algorithmic framework designed specifically for collaborative training. We demonstrate the effectiveness of our approach for SwAV and ALBERT pretraining in realistic conditions and achieve performance comparable to traditional setups at a fraction of the cost.
  arXiv  Detail & Related papers  (2021-06-18T16:23:13Z)
• Machine Learning (ML)-Centric Resource Management in Cloud Computing: A Review and Future Directions [22.779373079539713]
  Infrastructure as a Service (I) is one of the most important and rapidly growing fields. One of the most important aspects of cloud computing for I is resource management. Machine learning is being used to handle a variety of resource management tasks.
  arXiv  Detail & Related papers  (2021-05-09T08:03:58Z)
• AI-based Resource Allocation: Reinforcement Learning for Adaptive Auto-scaling in Serverless Environments [0.0]
  Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. A common approach among both commercial and open source serverless computing platforms is workload-based auto-scaling. In this paper we investigate the applicability of a reinforcement learning approach to request-based auto-scaling in a serverless framework.
  arXiv  Detail & Related papers  (2020-05-29T06:18:39Z)
• Budget Learning via Bracketing [50.085728094234476]
  The budget learning problem poses the learner's goal as minimising use of the cloud while suffering no discernible loss in accuracy. We propose a new formulation for the BL problem via the concept of bracketings. We empirically validate our theory on real-world datasets, demonstrating improved performance over prior gating based methods.
  arXiv  Detail & Related papers  (2020-04-14T04:38:14Z)
• A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service [68.84245063902908]
  This paper introduces a novel distributed architecture for deep-learning-as-a-service. It is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services.
  arXiv  Detail & Related papers  (2020-03-30T15:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.