发布求助
文献互助 智能选刊 最新文献

2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)最新文献

筛选
英文 中文
A generic and decentralized approach to XAI for autonomic systems: application to the smart home 自主系统XAI的通用和分散方法:在智能家居中的应用
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00079
Étienne Houzé
{"title":"A generic and decentralized approach to XAI for autonomic systems: application to the smart home","authors":"Étienne Houzé","doi":"10.1109/ACSOS-C52956.2021.00079","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00079","url":null,"abstract":"How can a smart home system generate explanations to its user on unusual or unwanted situations? Despite the rise of Explainable AI in recent years, there is still no satisfying solution to this problem. Most of the challenge lies in the fact that explanations are most needed when facing unusual or strange situations, which is where standard statistical methods are less effective. When faced with similar problems, humans rely on sequential reasoning, examining causally related conflicts and solving them one after the other. The approach explored by this PhD thesis is to implement this kind of reasoning into a Cyber-Physical System such as a smart home. To do so, a generic and modular architecture is designed to account for the specificity of smart home systems (runtime adaptation, variety of components, importance and uniqueness of the context). The aim of the thesis is to build the base framework of an Explanatory Engine and to provide a proof-of-concept demonstrator.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132439252","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
Reflective Learning Classifier Systems for Self-Adaptive and Self-Organising Agents 自适应和自组织智能体的反思学习分类器系统
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00043
Anthony Stein, Sven Tomforde
{"title":"Reflective Learning Classifier Systems for Self-Adaptive and Self-Organising Agents","authors":"Anthony Stein, Sven Tomforde","doi":"10.1109/ACSOS-C52956.2021.00043","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00043","url":null,"abstract":"Learning is a key capability in self-adaptive and self-organising systems to deal with dynamically changing conditions, unanticipated operational incidences, and open system constellations. Learning Classifier Systems, especially variants of the X CS Classifier System, have been demonstrated to be successfully applicable to the self-adaptation task concerning condition-aware re-configuration of parameters of the productive system. Compared to recent alternatives such as control theoretic approaches or (deep) reinforcement learning, XCS has advantages in the interpretability and continual evolution of knowledge, rendering it particularly applicable to real-world control problems. In this paper, we argue that the algorithmic concept of X CS and its integration in cooperative system constellations needs to be augmented with concepts for self-reflection, flexibility and transferability of knowledge to cover still unsolved challenges of real-world control problems. We present a brief introduction to the field and derive core challenges leading to a research agenda to achieve extended, reflective XCS-based self-adaptive and self-organising agents.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126882153","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: 4
Learn to Sense vs. Sense to Learn: A System Self-Integration Approach 学会感知vs.感知学习:一种系统自集成方法
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00053
D. Guastella, Evangelos Pournaras
{"title":"Learn to Sense vs. Sense to Learn: A System Self-Integration Approach","authors":"D. Guastella, Evangelos Pournaras","doi":"10.1109/ACSOS-C52956.2021.00053","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00053","url":null,"abstract":"The diffusion of Internet of Things (IoT) devices has opened up new opportunities for decentralized data analytics. In this context, data transmission can be affected by both network issues and distance between devices and receivers. These factors can affect the ability to aggregate and analyze data from multiple IoT devices, resulting in noisy, partial, or incorrect information. To this end, self-healing techniques pursue corrective actions when information acquired from sensors is not reliable. In this paper, we propose a new self-integration approach to improve the performance of decentralized self-healing techniques.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126528391","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
How to Coordinate Decisions at Large Scale? A Hands-on Tutorial on Collective Learning for Smart Cities and Beyond 如何大规模协调决策?智慧城市及其他领域的集体学习实践教程
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00084
Evangelos Pournaras
{"title":"How to Coordinate Decisions at Large Scale? A Hands-on Tutorial on Collective Learning for Smart Cities and Beyond","authors":"Evangelos Pournaras","doi":"10.1109/ACSOS-C52956.2021.00084","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00084","url":null,"abstract":"This 1.5-hour tutorial will provide an introduction to the theory and practice of multi-agent collective learning for coordinating distributed decisions at large scale. You will develop the required skills to work with the EPOS software artifact to solve distributed optimization problems in Smart Cities. The tutorial will also promote collaborations within the ACSOS community. PhD students and more senior colleagues are particularly encouraged to participate. No programming experience is required. You are also encouraged to bring in your own multi-agent optimization problem to explore a potential solution using collective learning.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121507541","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
Development of QoS-aware agents with reinforcement learning for autoscaling of microservices on the cloud 基于强化学习的qos感知代理的开发，用于云上微服务的自动扩展
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00025
Abeer Abdel Khaleq, Ilkyeun Ra
{"title":"Development of QoS-aware agents with reinforcement learning for autoscaling of microservices on the cloud","authors":"Abeer Abdel Khaleq, Ilkyeun Ra","doi":"10.1109/ACSOS-C52956.2021.00025","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00025","url":null,"abstract":"Microservices play an essential role in cloud application scalability. When demand increases on a microservice-based application, the microservices need to be scaled to sustain the demand without degrading the application performance. At the same time, cloud platforms need to maintain Quality of Service (QoS) for deployed cloud applications. Current microservices autoscaling technologies such as Kubernetes Horizontal Pod Autoscaler (HPA) require identifying specific scaling metrics in addition to very good knowledge of the application resource usage. Those technologies do not provide a built-in auto scaling based on QoS constraints. In this work, we present an intelligent micro services auto scaling module using Reinforcement Learning (RL) agents. The RL agents are trained and validated on microservices for disaster management real time systems with response time as QoS constraint. Our RL agents deployed on Google cloud can identify the scaling metrics, provide microservices auto scaling, and enhance the response time compared to the default Kubernetes intelligently and autonomously. The RL agents serve as an extendible plug-in module to Kubernetes HP A for auto scaling micro services in the cloud while adhering to QoS constraints autonomously. The intelligent module is flexible to accommodate other types of QoS and provides a cost-effective solution to cloud applications auto scaling in areas of limited resources.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131504723","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: 4
Stigmergic, Diegetic Guidance of Swarm Construction 群体建构的柱头化、叙事化导向
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00062
Samuel Truman, Jakob Seitz, S. Mammen
{"title":"Stigmergic, Diegetic Guidance of Swarm Construction","authors":"Samuel Truman, Jakob Seitz, S. Mammen","doi":"10.1109/ACSOS-C52956.2021.00062","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00062","url":null,"abstract":"No matter how autonomous a technical system is, in the end, the goals it is meant to serve are specified by humans. This also applies to systems implementing self-organized construction. In this paper, we present an approach to guide such systems by means of an accessible spatial user interface. We inferred its basic requirements from a previously published taxonomy on interactive self-organizing systems. We found solutions to these requirements that we could all realize based on the very simple idea to instruct all aspects of a swarm by means of spatially placed control points, innovating preceding virtual pheromone approaches. We implemented a very simple, yet effective model of a terrain-shaping swarm to test the guidance approach and to manually explore the generative space.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123457474","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
An anytime algorithm for dynamic multi-agent task allocation problems 动态多智能体任务分配问题的任意时间算法
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00065
Qinyuan Li, Minyi Li, Bao Quoc Vo, R. Kowalczyk
{"title":"An anytime algorithm for dynamic multi-agent task allocation problems","authors":"Qinyuan Li, Minyi Li, Bao Quoc Vo, R. Kowalczyk","doi":"10.1109/ACSOS-C52956.2021.00065","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00065","url":null,"abstract":"This paper explores the dynamic multi-agent task allocation problem in an open and dynamic environment. Some existing works on task allocation have not been able to cater for the extra needs of scalability and robustness in large scale complex systems. Furthermore, some algorithms highly rely on the agents' organisation structure. We proposes a novel algorithm based on the notions of potential contributions, values and utilities of the individual agents and the system. A game structure is constructed to model the task allocation problem, based on which a novel algorithm POT is then proposed to search for a Nash equilibrium solution that maximises the system's potential utility. We carry out comprehensive empirical studies to demonstrate that POT achieves a higher system utility compared with the state-of-the-art GreedyNE algorithm.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124889306","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
Self-Awareness as a Prerequisite for Self-Adaptivity in Computing Systems 自我意识是计算系统自适应的先决条件
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00039
A. Petrovska
{"title":"Self-Awareness as a Prerequisite for Self-Adaptivity in Computing Systems","authors":"A. Petrovska","doi":"10.1109/ACSOS-C52956.2021.00039","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00039","url":null,"abstract":"Establishing a better understanding of self-aware and self-adaptive systems is the first step towards specifying, modelling, designing and engineering these systems in the future. Although there might be some intuition behind the notions of awareness and adaptivity, there is a lack of clear definition and differentiation of these terms. In particular, the notion of awareness has been extensively studied in psychology and philosophy; however, a more rigorous understanding of this terminology is necessary for scientific debates in engineering. In this paper, by giving insights into how self-adaptive systems differ from the ordinary systems that are considered as non-adaptive, we set the foundation for understanding and differentiating self-awareness and self-adaptivity as two correlated but still different terms. We identify the system's self-awareness as a prerequisite for self-adaptivity and define two levels of awareness in computing systems.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125088849","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
Effect of Monotonic Filtering on Graph Collection Dynamics 单调滤波对图集动态的影响
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00036
H. Zainab, Giorgio Audrito, S. Dasgupta, J. Beal
{"title":"Effect of Monotonic Filtering on Graph Collection Dynamics","authors":"H. Zainab, Giorgio Audrito, S. Dasgupta, J. Beal","doi":"10.1109/ACSOS-C52956.2021.00036","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00036","url":null,"abstract":"Distributed data collection is a fundamental task in open systems. In such networks, data is aggregated across a network to produce a single aggregated result at a source device. Though self-stabilizing, algorithms performing data collection can produce large overestimates of aggregates in the transient phase. For example, in [1] we demonstrated that in a line graph, a switch of sources after initial stabilization may produce overestimates that are quadratic in the network diameter. We also proposed monotonic filtering as a strategy for removing such large overestimates. Monotonic filtering prevents the transfer of data from device $A$ to device $B$ unless the distance estimate at $A$ is more than that at $B$ at the previous iteration. For a line graph, [1] shows that monotonic filtering prevents quadratic overestimates. This paper analyzes monotonic filtering for an arbitrary graph topology, showing that for an $N$ device network, the largest overestimate after switching sources is at most $2N$.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125223409","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
Performance Comparison of Simple Reflex Agents Using Stigmergy with Model-Based Agents in Self-Organizing Transportation 基于Stigmergy的简单反射因子与基于模型的因子在自组织运输中的性能比较
2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) Pub Date : 2021-09-01 DOI: 10.1109/ACSOS-C52956.2021.00071
Sebastian Schmid, Daniel Schraudner, A. Harth
{"title":"Performance Comparison of Simple Reflex Agents Using Stigmergy with Model-Based Agents in Self-Organizing Transportation","authors":"Sebastian Schmid, Daniel Schraudner, A. Harth","doi":"10.1109/ACSOS-C52956.2021.00071","DOIUrl":"https://doi.org/10.1109/ACSOS-C52956.2021.00071","url":null,"abstract":"Multi-agent systems utilizing simple reflex agents are assumed to have a significant competitive disadvantage when compared to more sophisticated agent-based approaches. However, in terms of resilience and adaptivity, this simple design turns out be an advantage when used together with stigmergy. In this paper we show that simple reflex agents that use stigmergy, are fit and flexible enough to outperform rivaling model-based agents in a disturbed transportation setting that simulates a dynamic, real-world industrial shop floor, and have a performance closer to a centralized, monolithic approach which we compare to as gold standard. This leads to opportunities for simpler, but nevertheless more robust agent design for self-organizing, decentralized multiagent approaches just by sharing knowledge of the world and exploiting their environment.","PeriodicalId":268224,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125296979","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: 4
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信