2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)最新文献_第2页

Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems 解释自适应系统的在线强化学习决策

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00023

Felix Feit, Andreas Metzger, K. Pohl

{"title":"Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems","authors":"Felix Feit, Andreas Metzger, K. Pohl","doi":"10.1109/ACSOS55765.2022.00023","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00023","url":null,"abstract":"Design time uncertainty poses an important challenge when developing a self-adaptive system. As an example, defining how the system should adapt when facing a new environment state, requires understanding the precise effect of an adaptation, which may not be known at design time. Online reinforcement learning, i.e., employing reinforcement learning (RL) at runtime, is an emerging approach to realizing self-adaptive systems in the presence of design time uncertainty. By using Online RL, the self-adaptive system can learn from actual operational data and leverage feedback only available at runtime. Recently, Deep RL is gaining interest. Deep RL represents learned knowledge as a neural network whereby it can generalize over unseen inputs, as well as handle continuous environment states and adaptation actions. A fundamental problem of Deep RL is that learned knowledge is not explicitly represented. For a human, it is practically impossible to relate the parametrization of the neural network to concrete RL decisions and thus Deep RL essentially appears as a black box. Yet, understanding the decisions made by Deep RL is key to (1) increasing trust, and (2) facilitating debugging. Such debugging is especially relevant for self-adaptive systems, because the reward function, which quantifies the feedback to the RL algorithm, must be defined by developers. The reward function must be explicitly defined by developers, thus introducing a potential for human error. To explain Deep RL for self-adaptive systems, we enhance and combine two existing explainable RL techniques from the machine learning literature. The combined technique, XRL-DINE, overcomes the respective limitations of the individual techniques. We present a proof-of-concept implementation of XRL-DINE, as well as qualitative and quantitative results of applying XRL-DINE to a self-adaptive system exemplar.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134163310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Addressing Collective Computations Efficiency: Towards a Platform-level Reinforcement Learning Approach 解决集体计算效率:迈向平台级强化学习方法

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00019

Gianluca Aguzzi, Roberto Casadei, Mirko Viroli

{"title":"Addressing Collective Computations Efficiency: Towards a Platform-level Reinforcement Learning Approach","authors":"Gianluca Aguzzi, Roberto Casadei, Mirko Viroli","doi":"10.1109/ACSOS55765.2022.00019","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00019","url":null,"abstract":"Aggregate Computing is a macro-level approach for programming collective intelligence and self-organisation in distributed systems. In this paradigm, system behaviour unfolds as a combination of a system-wide program, functionally manipulating distributed data structures called computational fields, and a distributed protocol where devices work at asynchronous rounds comprising sense-compute-interact steps. Interestingly, there exists a large amount of flexibility in how aggregate systems could actually execute while preserving the desired functionality. The ideal place for making choices about execution is the aggregate computing platform (or middleware), which can be engineered with the goal of promoting efficiency and other non-functional goals. In this work, we explore the possibility of applying Reinforcement Learning at the platform level in order to optimise aspects of a collective computation while achieving coherent functional goals. This idea is substantiated through synthetic experiments of data propagation and collection, where we show how Q-Learning could reduce the power consumption of aggregate computations.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124243263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Message from the Artifact Evaluation Chairs 来自工件评估主席的消息

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/acsos55765.2022.00011

引用次数: 0

FedACA: An Adaptive Communication-Efficient Asynchronous Framework for Federated Learning FedACA:用于联邦学习的自适应通信高效异步框架

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00025

Shuang Zhou, Yuankai Huo, S. Bao, Bennett A. Landman, A. Gokhale

{"title":"FedACA: An Adaptive Communication-Efficient Asynchronous Framework for Federated Learning","authors":"Shuang Zhou, Yuankai Huo, S. Bao, Bennett A. Landman, A. Gokhale","doi":"10.1109/ACSOS55765.2022.00025","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00025","url":null,"abstract":"Federated Learning (FL) is a type of distributed machine learning, which avoids sharing privacy and sensitive data with a central server. Despite the advances in FL, current approaches cannot provide satisfactory performance when dealing with heterogeneity in data and unpredictability of system devices. First, straggler devices can adversely impact convergence speed of the global model training. Second, for model aggregation in traditional FL, edge devices communicate frequently with a central server using their local updates. However, this process may encounter communication bottleneck caused by substantial bandwidth usage. To address these challenges, this paper presents an adaptive, communication-efficient and asynchronous FL technique called FedACA comprising feedback loops at two levels. Our approach contains a self-adjusting local training step with active participant selection to accelerate the convergence of the global model. To reduce the communication overhead, FedACA supports an adaptive uploading policy at the edge devices, which leverages the model similarity and L2-norm differences between the current and previous local gradient. It also utilizes contrastive learning to tackle data heterogeneity by regularizing the local training if the local model has deviated from the global model and helps with the model similarity measurement in the uploading policy. Extensive experiments on a benchmark comprising three image datasets with non-independent and identically distributed (non-i.i.d) data show that FedACA adapts well to the straggler effect in asynchronous environments and also provides significant reductions in communication costs compared to other state-of-the-art FL algorithms.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125953031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Towards High-Quality Battery Life for Autonomous Mobile Robot Fleets 自主移动机器人车队迈向高质量电池寿命

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00024

Akshar Shravan Chavan, Marco Brocanelli

{"title":"Towards High-Quality Battery Life for Autonomous Mobile Robot Fleets","authors":"Akshar Shravan Chavan, Marco Brocanelli","doi":"10.1109/ACSOS55765.2022.00024","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00024","url":null,"abstract":"Autonomous Mobile Robots (AMRs) rely on rechargeable batteries to execute several objective tasks during navigation. Previous research has focused on minimizing task downtime by coordinating task allocation and/or charge scheduling across multiple AMRs. However, they do not jointly ensure low task downtime and high-quality battery life.In this paper, we present TCM, a Task allocation and Charging Manager for AMR fleets. TCM allocates objective tasks to AMRs and schedules their charging times at the available charging stations for minimized task downtime and maximized AMR batteries’ quality of life. We formulate the TCM problem as an MINLP problem and propose a polynomial-time multi-period TCM greedy algorithm that periodically adapts its decisions for high robustness to energy modeling errors. We experimentally show that, compared to the MINLP implementation in Gurobi solver, the designed algorithm provides solutions with a performance ratio of 1.15 at a fraction of the execution time. Furthermore, compared to representative baselines that only focus on task downtime, TCM achieves similar task allocation results while providing much higher battery quality of life.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115320291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A generic and modular reference architecture for self-explainable smart homes 一个通用和模块化的参考架构，用于自我解释的智能家居

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00028

Étienne Houzé, A. Diaconescu, J. Dessalles, D. Menga

{"title":"A generic and modular reference architecture for self-explainable smart homes","authors":"Étienne Houzé, A. Diaconescu, J. Dessalles, D. Menga","doi":"10.1109/ACSOS55765.2022.00028","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00028","url":null,"abstract":"Explainable AI (XAI) has become a major topic in Artificial Intelligence since the mid 2010s. While smart home explainability promises to improve user experience and trust, it is mostly left outside the scope of current AI research. We identify three main challenges that may cause this delay. First, smart device heterogeneity hinders the development of a system-wide vocabulary and communication medium required for end-to-end explanation. Second, smart home runtime changes – e.g. dynamic component additions, deletions and updates – require corresponding explanatory updates. Third, explanation context runtime changes: word meanings may vary with the end-user and the passing seasons – e.g. the notion of cold may vary, depending on the month. To tackle these challenges, we propose a generic, modular XAI reference architecture featuring: i) Local Explanatory Components (LECs) that provide resource-specific explanatory expertise and support runtime extensions; ii) mapping capabilities that allow LECs to translate resource-specific monitoring variables into resource-independent abstractions – predicates and events – which can then be used for generic inter-LEC communication; iii) a generic central component, called Spotlight, that coordinates LECs to generate system-wide explanations. We validate our proposal via a cyber-physical prototype of self-explainable smart home, implemented via a physical home maquette equipped with GrovePi sensors. We show how our prototype can handle several realistic scenarios highlighting the main issues identified above. This provides an initial stepping-stone towards a fully self-explanatory smart home solution. The genericity of our proposal opens the way for transferring it to similar application domains.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114303677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rango: An Intuitive Rule Language for Learning Classifier Systems in Cyber-Physical Systems 一种用于学习信息物理系统中分类器系统的直观规则语言

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00021

Melanie Feist, Martin Breitbach, Heiko Trötsch, C. Becker, Christian Krupitzer

{"title":"Rango: An Intuitive Rule Language for Learning Classifier Systems in Cyber-Physical Systems","authors":"Melanie Feist, Martin Breitbach, Heiko Trötsch, C. Becker, Christian Krupitzer","doi":"10.1109/ACSOS55765.2022.00021","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00021","url":null,"abstract":"Self-adaptation is crucial for cyber-physical systems (CPS) to meet their requirements in environments characterized by complexity and uncertainty. As many situations that CPS encounter at runtime are not foreseeable at design time, (online) learning approaches are attractive for such systems. Learning classifier systems (LCS) are a promising learning approach for CPS thanks to their rather low computational complexity. They operate on a set of rules that describe potential adaptation behavior. So far, specifying rules for a learning classifier system is a tedious task that requires expert knowledge. In this paper, we present Rango — an intuitive rule language for learning classifier systems — to overcome this challenge. Compared to existing approaches, Rango has a strong focus on CPS and provides a large variety of corresponding keywords. In addition, Rango rules are automatically transferred into a representation that is usable in a learning classifier system without any modifications. Rango therefore empowers system administrators to formulate rules and, hence, leverage an online learning approach for their use case without having prior experience with learning classifier systems. We evaluate Rango extensively with (i) a complexity analysis of parsing and rule evaluation, (ii) a usefulness study which shows that Rango facilitates both the writing of rules and the understanding of LCS output and (iii) a usability study, which proves that basic programming knowledge is sufficient to understand and formulate Rango rules.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122874655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Modular and Composable Approach to Develop Trusted Artificial Intelligence 开发可信人工智能的模块化和可组合方法

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-09-01 DOI: 10.1109/ACSOS55765.2022.00030

Michael Austin Langford, B. Cheng

{"title":"A Modular and Composable Approach to Develop Trusted Artificial Intelligence","authors":"Michael Austin Langford, B. Cheng","doi":"10.1109/ACSOS55765.2022.00030","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00030","url":null,"abstract":"Trustworthy artificial intelligence (Trusted AI) is of utmost importance when learning-enabled components (LECs) are used in autonomous, safety-critical systems. When reliant on deep learning, these systems need to address the reliability, robustness, and interpretability of learning models. In addition to developing specific strategies to address each of these concerns, appropriate software architectures are needed to coordinate LECs and ensure they deliver acceptable behavior under uncertain conditions. This work proposes a model-driven framework of loosely-coupled modular services designed to monitor and control LECs with respect to Trusted AI assurance concerns. The proposed framework is composable, deploying independent services to improve the resilience and robustness of AI systems. The overarching objective of this framework is to support software engineering principles focusing on modularity, composability, and reusability in order to facilitate development and maintenance tasks, while also increasing stakeholder confidence in Trusted AI systems. To demonstrate this framework, it has been implemented to manage the operation of an autonomous rover’s vision-based LEC while exposed to uncertain environmental conditions.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126558623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering 用混沌工程评价自适应自修复系统

2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) Pub Date : 2022-08-28 DOI: 10.1109/ACSOS55765.2022.00018

Moeen Ali Naqvi, Sehrish Malik, Merve Astekin, L. Moonen

{"title":"On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering","authors":"Moeen Ali Naqvi, Sehrish Malik, Merve Astekin, L. Moonen","doi":"10.1109/ACSOS55765.2022.00018","DOIUrl":"https://doi.org/10.1109/ACSOS55765.2022.00018","url":null,"abstract":"With the growing adoption of self-adaptive systems in various domains, there is an increasing need for strategies to assess their correct behavior. In particular self-healing systems, which aim to provide resilience and fault-tolerance, often deal with unanticipated failures in critical and highly dynamic environments. Their reactive and complex behavior makes it challenging to assess if these systems execute according to the desired goals. Recently, several studies have expressed concern about the lack of systematic evaluation methods for self-healing behavior.In this paper, we propose CHESS, an approach for the systematic evaluation of self-adaptive and self-healing systems that builds on chaos engineering. Chaos engineering is a methodology for subjecting a system to unexpected conditions and scenarios. It has shown great promise in helping developers build resilient microservice architectures and cyber-physical systems. CHESS turns this idea around by using chaos engineering to evaluate how well a self-healing system can withstand such perturbations. We investigate the viability of this approach through an exploratory study on a self-healing smart office environment. The study helps us explore the promises and limitations of the approach, as well as identify directions where additional work is needed. We conclude with a summary of lessons learned.","PeriodicalId":308147,"journal":{"name":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130901094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2