寻找基础设施即代码部署配置的多目标优化分析
Multiobjective Optimization Analysis for Finding Infrastructure-as-Code Deployment Configurations
AI总结：
本文针对 IaC 部署配置优化问题，比较九种进化多目标算法在 12 个真实实例上的表现，并据此构建可按用户需求选择算法的 IOP 多算法系统。
摘要：
多目标优化是人工智能和运筹学领域的热门话题。多目标方法的设计与开发是研究人员和从业者经常承担的任务。由于这一活跃的研究活动，迄今为止文献中已经提出了大量技术，证明了其在处理来自广泛现实领域的情况时具有显著有效性。本文聚焦于一个与优化基础设施即代码（Infrastructure-as-Code）部署配置相关的多目标问题。为解决该问题而实现的系统被命名为 IaC Optimizer Platform（IOP）。尽管 IOP 的原型版本此前已在文献中介绍过，但仍需要围绕问题求解开展更深入的分析，以确定哪种多目标方法最适合嵌入 IOP。本文所进行分析的主要动机是尽可能提升 IOP 的性能。鉴于该系统正作为 H2020 欧洲项目的一部分进行开发，并将部署在真实环境中，这是系统的一个关键方面。进一步而言，本文采用了九种不同的基于进化计算的多目标算法。为评估所考察求解器的质量，基于现实场景生成了 12 个不同的问题实例。每种方法在 10 次独立运行后获得的结果均使用 Friedman 非参数检验进行比较。由所执行检验得出的发现促成了一个多算法系统的创建，该系统能够根据用户需求应用不同技术。
英文摘要：
Multiobjective optimization is a hot topic in the artificial intelligence and operations research communities. The design and development of multiobjective methods is a frequent task for researchers and practitioners. As a result of this vibrant activity, a myriad of techniques have been proposed in the literature to date, demonstrating a significant effectiveness for dealing with situations coming from a wide range of real-world areas. This paper is focused on a multiobjective problem related to optimizing Infrastructure-as-Code deployment configurations. The system implemented for solving this problem has been coined as IaC Optimizer Platform (IOP). Despite the fact that a prototypical version of the IOP has been introduced in the literature before, a deeper analysis focused on the resolution of the problem is needed, in order to determine which is the most appropriate multiobjective method for embedding in the IOP. The main motivation behind the analysis conducted in this work is to enhance the IOP performance as much as possible. This is a crucial aspect of this system, deeming that it will be deployed in a real environment, as it is being developed as part of a H2020 European project. Going deeper, we resort in this paper to nine different evolutionary computation-based multiobjective algorithms. For assessing the quality of the considered solvers, 12 different problem instances have been generated based on real-world settings. Results obtained by each method after 10 independent runs have been compared using Friedman's non-parametric tests. Findings reached from the tests carried out lad to the creation of a multi-algorithm system, capable of applying different techniques according to the user's needs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
