{"title":"[Copyright notice]","authors":"","doi":"10.1109/acsos52086.2021.00003","DOIUrl":"https://doi.org/10.1109/acsos52086.2021.00003","url":null,"abstract":"","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"1 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":"128790310","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}
{"title":"SPS 2021 Committee","authors":"","doi":"10.1109/acsos52086.2021.00018","DOIUrl":"https://doi.org/10.1109/acsos52086.2021.00018","url":null,"abstract":"","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"67 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":"115951238","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}
{"title":"Runtime Equilibrium Verification for Resilient Cyber-Physical Systems","authors":"Matteo Camilli, R. Mirandola, P. Scandurra","doi":"10.1109/ACSOS52086.2021.00025","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00025","url":null,"abstract":"Cyber-Physical Systems are the basis of more and more activities in our modern society. Therefore, providing comprehensive, ideally provable, evidence that they continuously exhibit acceptable behavior even in case of unexpected events represents a major challenge that is not completely addressed by existing verification approaches. To this end, in this paper we exploit the notion of equilibrium, i.e., the ability of the system to maintain an acceptable behavior within its multidimensional viability zone and we propose RUNE (RUNtime Equilibrium verification), an approach able to verify at runtime if the system satisfies the equilibrium condition. RUNE includes (i) a system specification that takes into account the uncertainties related to partial knowledge and possible changes by adopting parametric Markov decision processes; (ii) the computation of the equilibrium condition to define the boundaries of the viability zone; and (iii) a runtime equilibrium verification method that leverages on Bayesian inference to reduce the uncertainty under the required level and quantitatively reason about the ability of the system to remain inside the boundaries of the viability zone. We demonstrate the benefits of the proposed approach on a running example from the robotics domain.","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"1 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":"129789950","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}
{"title":"SeAC 2021 Committee","authors":"","doi":"10.1109/acsos52086.2021.00015","DOIUrl":"https://doi.org/10.1109/acsos52086.2021.00015","url":null,"abstract":"","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"45 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":"128181673","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}
Veronika Lesch, Tanja Noack, Johannes Hefter, Samuel Kounev, Christian Krupitzer
{"title":"Towards Situation-Aware Meta-Optimization of Adaptation Planning Strategies","authors":"Veronika Lesch, Tanja Noack, Johannes Hefter, Samuel Kounev, Christian Krupitzer","doi":"10.1109/ACSOS52086.2021.00042","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00042","url":null,"abstract":"Platooning is a promising approach for optimizing the usage of the existing road infrastructure by driving in convoys with low inter-vehicle distances. Platooning coordination fosters advantages like an increased road throughput and reduced fuel consumption. Diverse so-called platooning coordination strategies exist in the literature and according to the no-free-lunch theorem, each has individual assets and drawbacks, making them best applicable for different traffic situations. This paper proposes a layered system model and a feedback loop for meta-optimization of self-adaptive systems. We apply our concept on platooning coordination as a case study and provide an experience report. The platooning coordination strategy is exchangeable and its input parameters are tuned to fit the current traffic situation. Our evaluation results show that the choice of the platooning coordination strategy is situation-dependent. Further, our meta-optimization of the input parameters of these strategies for the traffic situation is favorable compared to a static approach.","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","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":"129005146","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}
Börge Kordts, Jan Patrick Kopetz, Andreas Schrader
{"title":"A Framework for Self-Explaining Systems in the Context of Intensive Care","authors":"Börge Kordts, Jan Patrick Kopetz, Andreas Schrader","doi":"10.1109/ACSOS52086.2021.00040","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00040","url":null,"abstract":"Ventilated intensive care patients represent a sizable group in the intensive care unit that requires special attention. Although intensive care units are staffed with more nurses per patient than regular wards, the situation is often precarious. A situation that has become more acute during the COVID-19 pandemic. Weaning from mechanical ventilation as well as the limited communication abilities pose substantial stress to the patients. The incapability to impart even basic needs may negatively impact the healing process and can lead to delirium and other complications. To support the communication and information of weaning patients as well as to foster patient autonomy, we are developing a smart environment that is tailored to the intensive care context. While the provision and connection of smart objects and applications for this purpose can be time-consuming, self-organization and self-explainability may present helpful tools to reduce the effort. In this paper, we present a framework for self-explaining and semi-automatically interconnected ensembles of smart objects and ambient applications (that are integrated into smart spaces) used to realize the assistive environment. Based on a description language for these components, ensembles can be dynamically connected and tailored to the needs and abilities of the patients. Our framework has been developed and evaluated iteratively and has been tested successfully in our laboratory.","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"53 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":"130581616","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}
{"title":"Many Models at the Edge: Scaling Deep Inference via Model-Level Caching","authors":"Samuel S. Ogden, Guin Gilman, R. Walls, Tian Guo","doi":"10.1109/ACSOS52086.2021.00027","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00027","url":null,"abstract":"Deep learning (DL) models are rapidly expanding in popularity in large part due to rapid innovations in model accuracy, as well as companies' enthusiasm in integrating deep learning into the existing application logic. This trend will inevitably lead to a deployment scenario, akin to the content delivery network for web objects, where many deep learning models-each with different popularity-run on a shared edge with limited resources. In this paper, we set out to answer the key question of how to manage many deep learning models at the edge effectively. Via an empirical study based on profiling more than twenty deep learning models and extrapolating from an open-source Microsoft Azure workload trace, we pinpoint a promising avenue of leveraging cheaper CPUs, rather than commonly promoted accelerators, for edge-based deep inference serving. Based on our empirical insights, we formulate the DL model management problem as a classical caching problem, which we refer to as model-level caching. As an initial step towards realizing model-level caching, we propose a simple cache eviction policy, called CremeBrulee, by adapting BeladyMIN to explicitly consider DL model-specific factors when calculating each in-cache object's utility. Using a small-scale testbed, we demonstrate that CremeBrulee can achieve a 50% reduction in memory while keeping load latency below 92% of execution latency and less than 36% of the penalty of using a random approach to model eviction. Further, when scaling to more models and requests in a simulation, we demonstrate that CremeBrulee can keep the model load delay lower than other eviction policies that only consider workload characteristics by up to 16.6%. Relevant research artifacts are available at https://github.com/cake-lab/CremeBrulee","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"67 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":"131462424","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}
Soeren Becker, Florian Schmidt, L. Thamsen, A. J. Ferrer, O. Kao
{"title":"LOS: Local-Optimistic Scheduling of Periodic Model Training For Anomaly Detection on Sensor Data Streams in Meshed Edge Networks","authors":"Soeren Becker, Florian Schmidt, L. Thamsen, A. J. Ferrer, O. Kao","doi":"10.1109/ACSOS52086.2021.00033","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00033","url":null,"abstract":"Anomaly detection is increasingly important to handle the amount of sensor data in Edge and Fog environments, Smart Cities, as well as in Industry 4.0. To ensure good results, the utilized ML models need to be updated periodically to adapt to seasonal changes and concept drifts in the sensor data. Although the increasing resource availability at the edge can allow for in-situ execution of model training directly on the devices, it is still often offloaded to fog devices or the cloud. In this paper, we propose Local-Optimistic Scheduling (LOS), a method for executing periodic ML model training jobs in close proximity to the data sources, without overloading lightweight edge devices. Training jobs are offloaded to nearby neighbor nodes as necessary and the resource consumption is optimized to meet the training period while still ensuring enough resources for further training executions. This scheduling is accomplished in a decentralized, collaborative and opportunistic manner, without full knowledge of the infrastructure and workload. We evaluated our method in an edge computing testbed on real-world datasets. The experimental results show that LOS places the training executions close to the input sensor streams, decreases the deviation between training time and training period by up to 40% and increases the amount of successfully scheduled training jobs compared to an in-situ execution.","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"26 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":"131807561","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}
{"title":"AMGCC 2021 Committee","authors":"","doi":"10.1109/acsos52086.2021.00013","DOIUrl":"https://doi.org/10.1109/acsos52086.2021.00013","url":null,"abstract":"","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","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":"116647023","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}
{"title":"On Adapting SNMP as Communication Protocol in Distributed Control Loops for Self-adaptive Systems","authors":"Ilja Shmelkin, T. Springer","doi":"10.1109/ACSOS52086.2021.00022","DOIUrl":"https://doi.org/10.1109/ACSOS52086.2021.00022","url":null,"abstract":"Self-adaptive Systems (SASs) are one way to address the ever-growing complexity of software systems by allowing the system to react on changes in its operating environment. In today's systems, self-adaptation is typically realized with a control loop, for which the MAPE-K feedback loop is a prominent example. Research uses the notion of patterns to describe the distribution and decentralization of individual control loop components or control loops and their underlying managed subsystems. While there are some well-accepted standards about which components a managed subsystem has to implement so that it can interact with the control loop, research still lacks detailed investigation of control mechanisms, protocols, message formats and trade-offs for communication within and across control loops. This paper examines the idea of using the Simple Network Management Protocol (SNMP) for the communication in centralized, decentralized and distributed control loops. For this, a mapping of the SNMP function pool on the component communication of the MAPE-K control loop based on interfaces will be presented. Then, the SNMP approach is assessed with respect to its support for self-adaptive capabilities and limitations are discussed. The evaluation is based on a prototype that implements the prior presented mapping for the well-accepted Znn.com benchmark. The evaluation shows that the presented infrastructure can handle a sudden increase or decrease in resource demand by using self-adaptivity, which otherwise would lead to partial or complete loss of functionality by using SNMP as its communication protocol.","PeriodicalId":130761,"journal":{"name":"2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)","volume":"127 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":"114453234","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}