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.
This book of;is another proof of Springer’s;on the lively interface of;It is a Master Piece of what our community of Academics and Experts can provide when an;is supported by;and Experience of the World-Leader;The 7t...
详细信息
ISBN:
(数字)9783031508875
ISBN:
(纸本)9783031508868
This book of;is another proof of Springer’s;on the lively interface of;It is a Master Piece of what our community of Academics and Experts can provide when an;is supported by;and Experience of the World-Leader;The 7th edition of;took place at Baitong Hotel & Resort on October 26–27, 2023, with tremendous support from the global research scholars across the planet. Objective was to celebrate “;” with researchers, scholars, experts and investigators in;across the globe,to share knowledge, experience and innovation—a marvelous opportunity for discourse and mutuality by novel research, invention and creativity.;This proceedings book of the 7th;is published by Springer Nature—
The 6th edition of International Conference on Intelligent Computing and Optimization took place at G Hua Hin Resort & Mall on April 27–28, 2023, with tremendous support from the global research scholars across t...
详细信息
ISBN:
(数字)9783031501517
ISBN:
(纸本)9783031501500
The 6th edition of International Conference on Intelligent Computing and Optimization took place at G Hua Hin Resort & Mall on April 27–28, 2023, with tremendous support from the global research scholars across the planet. Objective is to celebrate “Research Novelty with Compassion and Wisdom” with researchers, scholars, experts, and investigators in Intelligent Computing and Optimization across the globe, to share knowledge, experience, and innovation—a marvelous opportunity for discourse and mutuality by novel research, invention, and creativity.
This proceedings book of the 6th ICO’2023 is published by Springer Nature—Quality Label of Enlightenment.
The rapid advancements in big data and the Internet of Things (IoT) have significantly accelerated the digital transformation of medical institutions, leading to the widespread adoption of Digital Twin Healthcare (DTH...
详细信息
The rapid advancements in big data and the Internet of Things (IoT) have significantly accelerated the digital transformation of medical institutions, leading to the widespread adoption of Digital Twin Healthcare (DTH). The Cloud DTH Platform (CDTH) serves as a cloud-based framework that integrates DTH models, healthcare resources, patient data, and medical services. By leveraging real-time data from medical devices, the CDTH platform enables intelligent healthcare services such as disease prediction and medical resource optimization. However, the platform functions as a system of systems (SoS), comprising interconnected yet independent healthcare services. This complexity is further compounded by the integration of both black-box AI models and domain-specific mechanistic models, which pose challenges in ensuring the interpretability and trustworthiness of DTH models. To address these challenges, we propose a Model-Based Systems engineering (MBSE)-driven DTH modeling methodology derived from systematic requirement and functional analyses. To implement this methodology effectively, we introduce a DTH model development approach using the X language, along with a comprehensive toolchain designed to streamline the development process. Together, this methodology and toolchain form a robust framework that enables engineers to efficiently develop interpretable and trustworthy DTH models for the CDTH platform. By integrating domain-specific mechanistic models with AI algorithms, the framework enhances model transparency and reliability. Finally, we validate our approach through a case study involving elderly patient care, demonstrating its effectiveness in supporting the development of DTH models that meet healthcare and interpretability requirements.
暂无评论