Microservice architectures are increasingly used to modularize IoT applications and deploy them in distributed and heterogeneous edge computing environments. Over time, these microservice-based IoT applications are su...
详细信息
Microservice architectures are increasingly used to modularize IoT applications and deploy them in distributed and heterogeneous edge computing environments. Over time, these microservice-based IoT applications are susceptible to performance anomalies caused by resource hogging (e.g., CPU or memory), resource contention, etc., which can negatively impact their Quality of Service and violate their Service Level Agreements. Existing research on performance anomaly detection for edge computing environments focuses on model training approaches that either achieve high accuracy at the expense of a time-consuming and resource-intensive training process or prioritize training efficiency at the cost of lower accuracy. To address this gap, while considering the resource constraints and the large number of devices in modern edge platforms, we propose two clustering-based model training approaches: (1) intra-cluster parameter transfer learning-based model training (ICPTL) and (2) cluster-level model training (CM). These approaches aim to find a trade-off between the training efficiency of anomaly detection models and their accuracy. We compared the models trained under ICPTL and CM to models trained for specific devices (most accurate, least efficient) and a single general model trained for all devices (least accurate, most efficient). Our findings show that ICPTL’s model accuracy is comparable to that of the model per device approach while requiring only 40% of the training time. In addition, CM further improves training efficiency by requiring 23% less training time and reducing the number of trained models by approximately 66% compared to ICPTL, yet achieving a higher accuracy than a single general model.
The papers in this volume were the fruitful scientific results of the Second International Conference on Social robotics (ICSR), held during November 23–24, 2010 in Singapore, which was jointly organized by the Socia...
详细信息
ISBN:
(数字)9783642172489
ISBN:
(纸本)9783642172472
The papers in this volume were the fruitful scientific results of the Second International Conference on Social robotics (ICSR), held during November 23–24, 2010 in Singapore, which was jointly organized by the Social roboticslaboratory (SRL), Interactive Digital Media Institute (IDMI), the National University of Singapore and 2 Human Language Technology department, the Institute for Infocomm Research (I R), A*STAR, Singapore. These papers address a range of topics in social robotics and its applications. We received paper submissions from America, Asia, and Europe. All the papers were reviewed by at least three referees from the 32-member Program Committee who were assembled from the global community of social robotics researchers. This v- ume contains the 42 papers that were selected to report on the latest developments and studies of social robotics in the areas of human––robot interaction; affective and cognitive sciences for interactive robots; design philosophies and software archit- tures for robots; learning, adaptation and evolution of robotic intelligence; and mec- tronics and intelligent control.
This book constitutes the refereed proceedings of the 17th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2022, held in Salamanca, Spain, in September 2022.;The 43 full papers presented in thi...
详细信息
ISBN:
(数字)9783031154713
ISBN:
(纸本)9783031154706
This book constitutes the refereed proceedings of the 17th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2022, held in Salamanca, Spain, in September 2022.;The 43 full papers presented in this book were carefully reviewed and selected from 67 submissions. They were organized in topical sections as follows: bioinformatics; data mining and decision support systems; deep learning; evolutionary computation; HAIS applications; image and speech signal processing; and optimization techniques.
暂无评论