[论文解读] Applying Machine Learning in Self-Adaptive Systems: A Systematic Literature Review

Omid Gheibi, Danny Weyns+1 more|arXiv (Cornell University)|Mar 6, 2021

Advanced Software Engineering Methodologies参考文献 54被引用 41

一句话总结

一个对将 ML 应用于基于架构的自适应系统并且具有 MAPE 循环的109项研究的系统性文献综述，详述动机、方法和尚待解决的挑战。

ABSTRACT

Recently, we witness a rapid increase in the use of machine learning in self-adaptive systems. Machine learning has been used for a variety of reasons, ranging from learning a model of the environment of a system during operation to filtering large sets of possible configurations before analysing them. While a body of work on the use of machine learning in self-adaptive systems exists, there is currently no systematic overview of this area. Such overview is important for researchers to understand the state of the art and direct future research efforts. This paper reports the results of a systematic literature review that aims at providing such an overview. We focus on self-adaptive systems that are based on a traditional Monitor-Analyze-Plan-Execute feedback loop (MAPE). The research questions are centred on the problems that motivate the use of machine learning in self-adaptive systems, the key engineering aspects of learning in self-adaptation, and open challenges. The search resulted in 6709 papers, of which 109 were retained for data collection. Analysis of the collected data shows that machine learning is mostly used for updating adaptation rules and policies to improve system qualities, and managing resources to better balance qualities and resources. These problems are primarily solved using supervised and interactive learning with classification, regression and reinforcement learning as the dominant methods. Surprisingly, unsupervised learning that naturally fits automation is only applied in a small number of studies. Key open challenges in this area include the performance of learning, managing the effects of learning, and dealing with more complex types of goals. From the insights derived from this systematic literature review we outline an initial design process for applying machine learning in self-adaptive systems that are based on MAPE feedback loops.

研究动机与目标

• 理解促使在以 MAPE 为基础的反馈回路中的自适应系统中使用机器学习的问题。
• 识别将学习整合到自适应中的关键工程方面（MAPE 功能、学习维度、方法）。
• 表征学习问题及其在自适应问题中的作用。
• 突出未解决的挑战并提出在基于 MAPE 的 SAS 中应用 ML 的初步设计过程。

提出的方法

• 遵循预定义协议的系统文献综述（计划、执行、报告）。
• 在 IEEE Xplore、ACM DL 和 Springer Link 进行自动检索，并通过使用试点查询的手动优化进行补充。
• 纳入标准：2003–May 2020 的出版物，将 ML 应用于基于 MAPE 的自适应系统，并具有基本评估。
• 排除标准：综述、教程、短论文、社论。
• 数据提取包含 14 项（作者、年份、题名、场所、引用次数、质量分数、适应问题、学习问题、MAPE 函数、学习维度、学习方法、领域、局限性、挑战）。
• 通过描述性统计和对定性类别的开放编码进行分析。

实验结果

研究问题

• RQ1 RQ1：在自适应系统中，机器学习解决了哪些问题？
• RQ2 RQ2：在自适应中应用学习时，考虑的关键工程方面是什么？
• RQ3 RQ3：在自适应系统中使用机器学习存在哪些未解决的挑战？

主要发现

• 初步鉴定出 6709 篇论文，最终保留 109 篇用于数据收集。
• 所选论文跨越 75 个刊物。
• 大多数研究发表于 2015–2019 年（72%），其中 2007–2014 年占 28%。
• 各研究的报告质量通常足以描述问题和背景，且有结构化的评估。
• ML 主要用于更新自适应规则/策略，并管理资源以实现更好的质量-资源平衡。
• 监督学习和交互学习，结合分类、回归和强化学习为主导；无监督学习相对较少。
• 学习通常用于协助分析器（如减少自适应选项）并在 MAPE 循环中支持运行时决策。
• 未解决的挑战包括学习性能、处理学习引起的效应以及处理更复杂的目标。