ERCM News 125 - Brain-Inspired Computing

Page 50

Research and Innovation

landscape, and (iii) mitigate the slow adoption rate of new technologies by many SMEs. In this context, ACCORDION aspires to: • provide an open, low-latency, privacy-preserving, secure and robust virtualised infrastructure; and • provide an application management framework, tailored to the needs of the SME’s skillset, that will enable the deployment of NextGen applications on top of this infrastructure. This method allows us to reap the benefits of edge computing while exploiting the set of heterogeneous resources that can embed such computing facilities.

ACCORdION: Edge Computing for NextGen Applications by Patrizio Dazzi (ISTI-CNR) Cloud computing has played a vital role in the digital revolution. Clouds enable consumers and businesses to use applications without dealing with local installations and the associated complexity. However, a big class of applications is currently being blocked because of their dependency on on-site infrastructures or specialised enddevices but also because they are too latency-sensitive or data-dependent to be moved to the public cloud.

ACCORDION’s key concept is aligned with the recent developments in the Multi-Access Edge Computing (MEC) front, extending the interest to both network and computation resources. ACCORDION aims to provide a platform to address the needs of NextGen applications by properly exploiting edge resources. The platform is intended to provide an integrated approach dedicated to both developers and local infrastructure owners. It will encompass frameworks for application development, solutions for an adaptive and robust cloud/edge infrastructure continuum, and the abstraction of widely heterogeneous pools.

These Next Generation (NextGen) applications would benefit from an advanced infrastructure with ubiquitous presence, unblocking them from fixed geographies. Current edge $&&25',21 3ODWIRUP 8VHUV $ &&25',21 3ODWIRUP 8VHUV

$ $&&25',21 &&25',21 S SODWIRUP RZQHU ODWIRUP RZQHU

( (GJH LQIUDVWUXFWXUH GJH LQIUDVWUXFWXUH RZQHU RZQHU

$SSOLFDWLRQ $SSOLFDWLRQ 3 3URYLGHU URYLGHU

$ $&&25',21 3ODWIRUP &&25',21 3ODWIRUP

9,0 DFFHVV SRLQW 9,0 DFFHVV SRLQW

,QWHOOLJHQW ,QWHOOLJHQW 2UFKHVWUDWRUV 2UFKHVWUDWRUV

$ $SSOLFDWLRQ SSOLFDWLRQ 0 0DQDJHPHQW DQDJHPHQW 6 6HUYLFHV HUYLFHV

0LQLFORXGV 0 LQLFORXGV 0HPEHUVKLS 0 HPEHUVKLS 0DQDJHPHQW 0 DQDJHPHQW

6/$ /LIHF\FOH 6/$ /LIHF\FOH 0DQDJHPHQW 0DQDJHPHQW

) )06 06 3 3RUWDO RUWDO

)HGHUDWHG ,QIUDVWUXFWXUH )HGHUDWHG ,QIUDVWUXFWXUH

0LQLFORXG 0LQLFORXG

0LQLFORXG 0LQLFORXG

0 0LQLFORXG LQLFORXG

3 XEOLF &ORXG 3XEOLF &ORXG

ACCORDION Platform architecture.

computing implementations support only specific geography and architectures, which means that the scope of local resources and infrastructures are also restricted to the needs of certain edge-enabled applications. Existing solutions lead to user lock-in and, overall, have a negative impact on the open diffusion of edge computing. They actually hinder the exploitation of the ubiquitous presence of edge infrastructure, limiting the edge-enablement of the NextGen applications. The shift towards edge computing, supported and promoted by the ACCORDION project aims to (i) limit vendor lock-in situations that trap SMEs into committing to the services offered by big vendors, but also (ii) leverage the vast pool of local, potentially specialised, resources of the SME 50

0 0LQLFORXG LQLFORXG

ACCORDION, coordinated by ISTI-CNR, started in early 2020, so we are just starting the second year of research. In line with our original plans, the first year of the project focused largely on analysing the state of the art, the selection of base technologies and the definition of the overall architecture of the system: moving from the high-level conceptual one to a more concrete one, in which the key modules of the system along with the interactions among them have been defined.

We will soon deliver the core modules of the ACCORDION platform, to be followed by a complete release of the integrated ACCORDION platform. Once the integrated platform is ready, a first release of ACCORDION use cases will be properly tailored to be run on top of it. Links: [L1] https://cordis.europa.eu/project/id/871793 [L2] https://www.accordion-project.eu Please contact: Patrizio Dazzi, Project Coordinator, ISTI-CNR, Italy patrizio.dazzi@isti.cnr.it ERCIM NEWS 125 April 2021


Turn static files into dynamic content formats.

Create a flipbook

Articles inside

ERCM News 125 - Brain-Inspired Computing: Introduction to the Special Theme

1min
page 6

Security Management and the Slow Adoption of Blockchains

3min
page 47

Graph-based Management of Neuroscience Data Representation, Integration and Analysis

2min
page 44

ACCORDION: Edge Computing for NextGen Applications

2min
page 50

The ICARUS Ontology: A General Aviation Ontology

7min
pages 45-46

Trick the System: Towards Understanding Automatic Speech Recognition Systems

7min
pages 48-49

Human-like AI

5min
pages 42-43

NeuroAgents – Autonomous Intelligent Agents that Interact with the Environment in Real Time

6min
pages 40-41

What Neurons Do – and Don’t Do

6min
pages 37-38

NEUROTECH - A European Community of Experts on Neuromorphic Technologies

2min
page 39

Uncovering Neuronal Learning Principles through Artificial Evolution

6min
pages 35-36

Touch in Robots: A Neuromorphic Approach

3min
page 34

E = AI

6min
pages 30-31

Fulfilling Brain-inspired Hyperdimensional Computing with In-memory Computing

6min
pages 28-29

Memory Failures Provide Clues for more Efficient Compression

7min
pages 25-26

Reentrant Self-Organizing Map: Toward Brain inspired Multimodal Association

7min
pages 22-23

Neuronal Communication Process Opens New Directions in Image and Video Compression Systems

3min
page 27

Brain-inspired Learning Drives Advances in Neuromorphic Computing

2min
page 24

Self-Organizing Machine Architecture

7min
pages 20-21

Fast and Energy-efficient Deep Neuromorphic Learning

6min
pages 17-18

Effective and Efficient Spiking Recurrent Neural Networks

7min
pages 9-10

The BrainScaleS Accelerated Analogue Neuromorphic Architecture

2min
page 14

BrainScaleS: Greater Versatility for Neuromorphic Emulation

6min
pages 15-16

ERCIM “Alain Bensoussan” Fellowship Programme

3min
page 5

Back-propagation Now Works in Spiking Neural Networks!

3min
page 11

ERCIM-JST Joint Symposium on Big Data and Artificial Intelligence

3min
page 4

Brain-inspired Computing

7min
pages 6-7
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.