 smart infrastructure management, urban AI solutions, IoT interoperability, edge-to-cloud integration, NVIDIA GPU cloud model integration (NMI)Eduard Cristian Popovici (),
Octavian Fratu (),
Alexandru Vulpe (),
Razvan Craciunescu () and
Andra Paula Avasiloaie ()
Smart Cities International Conference (SCIC) Proceedings, 2024, vol. 12, 481-500 Abstract: In order to provide a solid, scalable solution for edge AI applications suited to smart city projects, this article suggests an architecture that combines NVIDIA AI Microservices with the Eclipse Arrowhead Framework. The integration addresses the demand for smooth, real-time AI-powered functions across heterogeneous devices and serves a variety of sectors, including social innovation, urban planning, and e-government. The framework seeks to improve citizen services and optimize urban resource management by utilizing Arrowhead's service-oriented skills and NVIDIA's cutting-edge AI models. As seen by applications like automated systems and industrial IoT, the study expands on developments in cloud-edge integration and service orchestration within the Arrowhead Framework. Few existing frameworks have specifically addressed the integration of high-performance AI microservices for smart city contexts, instead concentrating on general interoperability and dynamic service discovery. By using Docker for containerization, the suggested approach makes it possible to deploy AI services in a secure and scalable manner. While Arrowhead manages service registration, discovery, and secure communication, NVIDIA AI models take care of activities like data analysis and pattern identification. Workloads are balanced across cloud and edge settings because of the architecture's support for decentralized execution. The successful orchestration of AI microservices for applications such as environmental monitoring and traffic optimization is demonstrated by the preliminary implementation. Through simulated urban scenarios, the system's ability to process data with minimal latency and make dependable decisions across heterogeneous platforms is tested. By providing a model for improving urban infrastructure, this framework can greatly increase the effectiveness of smart city operations for both practitioners and scholars. Additionally, it establishes the framework for incorporating upcoming advancements in AI into public services. To guarantee compatibility, scalability, and security, the study presents a novel method of integrating Arrowhead's orchestration tools with NVIDIA's AI Microservices. The framework provides a creative answer to contemporary urban problems by considering the particular requirements of smart cities. Keywords: smart infrastructure management; urban AI solutions; IoT interoperability; edge-to-cloud integration; NVIDIA GPU cloud model integration (NMI) Decision-Making; Workforce Development (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:pop:procee:v:12:y:2024:481-500 Access Statistics for this article More articles in Smart Cities International Conference (SCIC) Proceedings from Smart-EDU Hub, Faculty of Public Administration, National University of Political Studies & Public Administration Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.