|
The AI@EDGE Project - Newsletter #3
|
Artificial Intelligence has become a major innovative force, and it is one of the pillars of the fourth industrial revolution. While significant progress has been made during the last years concerning AI-enabled platforms’ accuracy and performance, their integration in potentially autonomous decision-making systems or even critical infrastructures requires assuring end-to-end quality.
|
|
The goal of the AI@EDGE project is to offer a cost-effective, open, and decentralised platform for the creation of networks-for-AI and networks-for-AI paradigms in systems that go beyond 5G. In 2022, the project offered the condensed form of interface standards, techno-economic analysis, and system architecture.
|
|
|
|
The project has also continued to define the systems and procedures for the automation of the AI@EDGE platform and the validation of the AI@EDGE connect-compute platform. Additionally, the project has presented an overview of the progress made with the validation of the 4 AI@EDGE use case demonstrators. The application cases include cooperative perception for vehicle networks, secure, multi-stakeholder AI for IoT, aerial infrastructure inspections, and in-flight entertainment with the goal of maximising the project's economic, social, and environmental impact.
|
|
The project has a clear roadmap for future development and expansion, which includes initiatives like cross-chain interoperability and improved usability for end users. It has a strong commitment to community engagement and has established a number of channels for developers, validators, and enthusiasts to participate and contribute.
|
|
|
|
|
|
|
|
D2.3 Consolidated system architecture, interfaces specifications, and techno-economic analysis
|
|
|
|
|
This deliverable details the consolidated AI@EDGE system architecture, describing its components, interfaces and workflows (Milestone 2.6). Together with D3.2 and D4.2, it provides a complete view of the key technical challenges and contributions of the AI@EDGE project and defines the scope of the software prototypes used in the trials.
|
|
|
|
|
D5.2 Preliminary Validation and Use Case Benchmarking
|
|
|
|
|
This deliverable reports the complete set of activities performed during the second year of the project related to dissemination, standardisation, contribution to 5G-PPP, collaboration with other projects, as well as IPR, open access and data management.
|
|
|
|
|
D6.4 Second Dissemination, Impact Assessment and Exploitation Report
|
|
|
|
|
This deliverable reports the complete set of activities performed during the second year of the project related to dissemination, standardisation, contribution to 5G-PPP, collaboration with other projects, as well as IPR, open access and data management.
|
|
|
|
|
|
|
|
|
AI@EDGE Workshop at EUCNC 2023
|
|
|
On the 6th of June 2023, AI@EDGE held a half-day workshop at the EUCNC 2023 in Gothenburg, Sweden. The workshop titled “Exploring the Intersection of 6G and Artificial Intelligence: Unleashing the Potential of Next-Gen Technologies” has been hosted together with the projects DEAMON, 5G-IANA, and HEXA-X.
|
|
|
|
|
|
|
AI@EDGE @ ICT-52 Workshop 2023
|
|
|
AI@EDGE has made a presentation on AI@EDGE Network Architecture and Automation of Future Telecom Networks at the forthcoming “VIRTUAL ICT-52 Workshop on 6G 2023“. The presentation by Neiva Linder (Ericsson) on behalf of AI@EDGE took place on the 19th of January in the afternoon.
|
|
|
|
|
AI@EDGE Booth @ Mobile World Congress 2023
|
|
|
|
|
|
|
Joint workshop @ Cloudnet 2022
|
|
|
|
|
|
|
|
|
Evaluating Versal ACAP and conventional FPGA platforms for AI inference
|
|
|
|
|
Xilinx Versal ACAP is the newest acceleration platform, developed by Xilinx, proposed to enhance the capabilities of the conventional FPGA ones and meet the demands of modern applications. However, …
|
|
|
|
|
Deep Reinforcement Learning for QoS-aware scheduling under resource heterogeneity Optimizing serverless video analytics
|
|
|
|
|
Today, video analytics are becoming extremely popular due to the increasing need for extracting valuable information from videos available in public sharing services through camera-driven streams. Typically, …
|
|
|
|
|
A memory footprint optimization framework for Python applications targeting edge devices
|
|
|
|
|
The advantages of processing data at the source motivate developers to offload computations at the edges of IoT networks. However, …
|
|
|
|
|
Design and Evaluation of a K8s-based System for Distributed Open-Source Cellular Networks
|
|
|
|
|
Virtualization in cellular networks is one of the key areas of research where technologies, infrastructure and challenges are rapidly changing as 5G system architecture demands a paradigm shift. …
|
|
|
|
|
Towards Sustainable and Trustworthy 6G: Challenges, Enablers, and Architectural Design
|
|
|
|
|
While the 5th Generation (5G) system is being widely deployed across the globe, the information and communication technology (ICT) industry, research, standardization and consensus building for the 6th generation (6G) …
|
|
|
|
|
|
|
|
|
AI@EDGE is one of the 9 research projects retained from the 81 proposals submitted to the European Commission in response to the 5G-PPP ICT-52-2020 call: 5G-PPP Smart Connectivity beyond 5G. The project, started in January 2021, lasts 3 years and involves 19 partners among industries, universities and research institutes from 8 countries.
|
|
|
|
|
|
