IDEAS home Printed from https://ideas.repec.org/a/pop/procee/v12y2024481-500.html
   My bibliography  Save this article

smart infrastructure management, urban AI solutions, IoT interoperability, edge-to-cloud integration, NVIDIA GPU cloud model integration (NMI)

Author

Listed:
  • Eduard Cristian POPOVICI

    (POLITEHNICA Bucharest)

  • Octavian FRATU

    (POLITEHNICA Bucharest)

  • Alexandru VULPE

    (POLITEHNICA Bucharest)

  • Razvan CRACIUNESCU

    (POLITEHNICA Bucharest)

  • Andra Paula AVASILOAIE

    (POLITEHNICA Bucharest)

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.

Suggested Citation

  • Eduard Cristian POPOVICI & Octavian FRATU & Alexandru VULPE & Razvan CRACIUNESCU & Andra Paula AVASILOAIE, 2024. "smart infrastructure management, urban AI solutions, IoT interoperability, edge-to-cloud integration, NVIDIA GPU cloud model integration (NMI)," Smart Cities International Conference (SCIC) Proceedings, Smart-EDU Hub, Faculty of Public Administration, National University of Political Studies & Public Administration, vol. 12, pages 481-500, september.
  • Handle: RePEc:pop:procee:v:12:y:2024:481-500
    as

    Download full text from publisher

    File URL: https://scrd.eu/index.php/scic/article/view/713/728
    Download Restriction: no

    File URL: https://scrd.eu/index.php/scic/article/view/713
    Download Restriction: no
    ---><---

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • O35 - Economic Development, Innovation, Technological Change, and Growth - - Innovation; Research and Development; Technological Change; Intellectual Property Rights - - - Social Innovation

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:pop:procee:v:12:y:2024:481-500. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Professor Catalin Vrabie (email available below). General contact details of provider: https://edirc.repec.org/data/fasnsro.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.