Hasil untuk "Architecture"

K. Nichols, V. Jacobson, Lixia Zhang

Martin L. Griss

P. Guerrier, A. Greiner

S. Hofmeyr, S. Forrest

P. Stankiewicz, J. Lupski

L. Seiler, Douglas M. Carmean, Eric Sprangle et al.

M. Varga

J. Bodmer, P. Schneider, J. Tschopp

K. Czajkowski, Ian T Foster, N. Karonis et al.

L. Vosshall, R. Stocker

M. Ripeanu

M. MacDonald

S. Loyka

Yashpalsinh Jadeja, Kirit J. Modi

M. Lankhorst

T. Shan, Winnie W. Hua

E. Ellsworth

G. Hu, Wee Peng Tay, Yonggang Wen

L. Raghavendar Raju, M. Venkata Krishna Reddy, Sridhar Reddy Surukanti et al.

Abstract Edge–cloud computing has emerged as an important paradigm for modern Internet of Things (IoT) workflow applications, enabling low latency and on-demand resource allocation. In scenarios with heterogeneous deadlines and varying workloads, SLA compliance requires efficient coordination between edge and cloud resources. However, cloud-centric scheduling and heuristic approaches tend to lack adaptability to rapidly changing system conditions and, as a result, experience long waiting times (the same applies to QoS). To tackle these issues, we present IntelliScheduler, a hybrid actor–critic deep reinforcement learning framework for adaptive task scheduling in an edge–cloud system. Our framework presents a runtime-aware state representation combined with a learning-based decision mechanism, backed by a multi-buffer experience replay architecture. Second, a learning-based optimal task scheduling (LbOTS) algorithm is developed to minimise total task execution delay by discovering optimal deployment decisions across edge and cloud computational resources using latency-aware reward modelling. We assess the proposed approach by conducting extensive simulation experiments under different workloads. We evaluate LbOTS across various experimental scenarios and report up to 13% higher normalised reward, 67% lower training loss, 52–66% lower operational cost, and 80–90% lower rejection rate compared to PSO, MBO, and MOPSObaselines, achieving approximately 15–75% better QoE. Though the current assessment is simulation-based, the adaptive learning formulation is highly relevant for application in dynamic edge–cloud scheduling scenarios.

Fei Yu, Norihito Nakatani, Yiling Hua et al.

By tracing the historical activities of the Japan-China Society of Architecture and Building Technology (JCSABT, 1973–2003), which was established in Japan in 1973, this study firstly provides an overview of the friendly exchange groups visiting China from Japan over a 30-year period. Drawing upon a systematic review of Nichi-Chu Kenchiku [Japan – China Architecture], the official journal of JCSABT, this study delineates the evolving professional concerns and focal themes of Japanese architects engaged in China. The focus gradually shifted from early concerns with the construction of socialist China to an interest in cultural heritage, particularly Chinese vernacular architecture, and later to friendly visits and international exchanges. These shifts reflect the dynamic interplay between political context, architectural evolution, and cultural exchange. The study concludes that beneath the surface of “friendly diplomacy,” China and Japan each pursued distinct agendas. China seeks to learn advanced techniques from Japan, while Japan, faced with pressing issues such as widening urban-rural disparities and environmental crises, endeavours to learn from China’s urban and rural development models. Above all,“architectural diplomacy” played a crucial role in fostering Sino – Japanese friendship. The interplay among state power, architecture, and socioeconomic forces collectively contributed to strengthening bilateral relations in Cold War era.