Big data processing and artificial intelligence at the edge of the network


© Sborisov

The BRAINE project will help position Europe at the forefront of the field of Intelligent Edge Computing

Edge Computing is an exciting new approach to network architecture that leaves cloud computing behind and puts intelligence to process data closer to the source. This inherently offers many technical advantages, such as reduced latency, secure decentralized processing and storage, scalability at lower complexity, versatility to tailor nodes to the underlying application to be served, and increased reliability. .

Edge computing can dramatically boost services and applications by supporting artificial intelligence (AI) natively, instead of relying on AI in the cloud. Edge Computing supporting AI (without intervention in the cloud) is the key technology that will enable many long-awaited game changers, such as:

  • Factory 4.0 and smart manufacturing.
  • 5G.
  • Internet of things.
  • Autonomous vehicles.
  • Remote robotics for healthcare.
  • Industrial vision.

Introducing AI into advanced computing is a challenge. Specific low-power hardware must be developed with a secure software infrastructure specifically designed for big data processing and AI.

BRAINE project, edge computing

BRAINE project, edge computing

The overall objective of the BRAINE project is to stimulate the development of the Edge framework and, in particular, energy-efficient hardware and AI-based software systems, capable of processing Big Data at the edge, supporting security, data confidentiality and sovereignty.

The BRAINE project is partially funded by the ECSEL Joint Undertaking (JU) under Grant Agreement No 876967, supported by the European Union’s Horizon 2020 research and innovation program. It started on May 1, 2020, with a duration of 36 months and an overall budget of 16M €.

BRAINE’s overall objective will be achieved by targeting the following objectives:

  • Develop a heterogeneous and energy efficient Edge Micro Data Center (EMDC) hardware solution that goes beyond current hardware and software architectures and delivers big data and AI processing capabilities at the edge. BRAINE EMDC will be a functional eight-slot EMDC with a complementary GPU. Therefore, the project worked on innovative cooling systems, based on solid and liquid state approaches, mechanical systems to support highly dense EMDC in terms of components and BRAINE boards containing the composable building blocks. (i.e. GPU, ASIC, FPGA, CPU, memory, programmable P4 switching). Overall, a fully loaded BRAINE EMDC should only consume 1/3 of a standard 19 rack node, but with the computing power of eight standard rack size computers, consuming only up to 2 kW.
  • Design an EMDC software infrastructure that delivers 5G control, compute, acceleration, storage and networking at the edge and excels in scalability, agility, security, data privacy and sovereignty data in Big Data and AI for low latency and mission-critical applications. EMDC software infrastructure operates and enhances the Kubernetes orchestration system and provides specially designed components like resource and service repository, service registry, service manager, SLA broker, telemetry system, etc.
  • Develop a future-proof Edge security framework and associated infrastructure based on the latest software and hardware security technologies. The project is developing intra-network firewall technologies based on programmable Ethernet / smartNIC switches, CPU offload of IPSec and Transport Security Layer (TLS) protocols in smartNICs, post-quantum security solutions and a Cryptographic acceleration for fiber optic connectivity links for the edge. knots.

BRAINE project, edge computing

BRAINE project, edge computing

BRAINE project, edge computing

BRAINE project, edge computing

The BRAINE approach is based on creating a transparent Edge by creating clusters of nodes, forming an Edge MicroDataCenter (EMDC), as well as intelligent network interface cards (NICs) capable of pairing with Edge devices. to enable high-speed connectivity and native AI.

BRAINE offers a new vision for the use of edge resources by proposing new patterns of workload distribution at the edge of the network. Predicting resource availability and workload demand, identifying trends, and taking proactive action are all aspects of the new workload distribution. The workload balancing technology developed in the context of BRAINE can be transferred to many other Edge / Fog IT environments to achieve different goals. Last but not least, BRAINE will have a significant positive impact on the environment. With BRAINE, edge computing can reduce this predicted power consumption by offloading many AI functions to end users.

BRAINE will demonstrate edge computing enabling AI through four use cases:

  • Life assisted by health care (case 1). The new AI-based Digital Twin technology will run on the BRAINE EMDC platform as part of a powerful medical life support software. The aim is to efficiently deliver decentralized medical services that are secure, reliable, GDPR compliant and cost effective for a wide range of healthcare, care, health insurance bodies and various patients across the EU.
  • Hyper-connected smart city (case 2). The goal is to create a distributed federated infrastructure for multi-tenancy by leveraging the powerful EMDC acceleration capabilities, capable of serving video hyper-connectivity in terms of large-scale video processing, latency, learning automatic, security, GDPR and data sovereignty in a city.
  • Robotics in Factory 4.0 (case 3). The project will create digital twins and a multi-agent system for the production lines at Plant 4.0, where digital copies of the production line robots are simulated via AI, and production is planned at the node level. peripheral. This allows to reduce the time of (de) commissioning, the introduction of a new robot and a good follow-up of the performances, because the sensors of the real robot feed the agents and the digital twin, thus making it possible to predict failures, to perform real-time adjustments and optimization in individual robots and collaborative robot groups.
  • Industry 4.0 supply chain (case 4). The BRAINE EMDC will provide a federated distributed platform as an appliance enabling the deployment of Big Data and AI tools complementing the Arrowhead initiatives, the largest project in Europe providing engineering processes, a platform- Integration form, tools and tool chains for the cost-effective development of digitization, connectivity and automation systems solutions in various fields of industrial applications.

By achieving its objectives, the BRAINE project will help position Europe at the forefront of intelligent advanced computing, enabling growth in many sectors (manufacturing, intelligent healthcare, surveillance, satellite navigation , etc.). By lowering the barriers to the use of advanced computing for artificial intelligence applications, BRAINE will open the door for European SMEs to take advantage of cutting-edge technologies, stimulating their development and growth as market leaders. industry in their sectors.

BRAINE has received funding from the European Union’s HORIZON 2020 research program under grant agreement no. 876967.

Attention: This is a commercial profile

from the publisher advised Articles


Comments are closed.