Periodic Reporting for period 1 - DAIS (Distributed Artificial Intelligent Systems)
Période du rapport: 2021-05-01 au 2022-04-30
In recent years, technological developments in consumer electronics and industrial applications have been advancing rapidly. More and more, small, networked devices are able to collect and process data anywhere. This Internet of Things (IoT) is a revolutionary change for many sectors like building, automotive, digital industry, energy, etc. The new paradigm of edge computing provides new solutions by bringing resources closer to the user, keeps sensitive & private data on device, and provides low latency, energy efficiency, and scalability compared to cloud services while reducing the network bandwidth.
At the same time, there is an increasing need to use Artificial Intelligence (AI) at the edge. The developments of AI applications mostly require processing of data in centralized cloud locations and hence cannot be used for applications where milliseconds matter in safety-critical applications. In addition to speed, edge computing offers security benefits due to wider data distribution at the edge level. Reducing the distance data has to travel for processing means decreasing the opportunities for trackers and hackers to intercept it during transmission and preserves its privacy.
DAIS has ambitious objective to develop Intelligent and Secure Edge solutions for industrial applications for European industry throughout the whole Supply Chain. More precisely, we do so by:
* Providing intelligent processing of data and communication locally at the edge to enable real-time and safety-critical industrial applications.
* Developing industrial-grade secure, safe and reliable solutions that can cope with cyberattacks and difficult network conditions.
* Providing AI techniques on the edge that match with diverse computing powers contrary to relatively consistent computing power on the cloud. As different AI algorithms have different computing power requirements, it is a big challenge to match an existing algorithm with the certain edge platform.
* Distribute and divide the complex AI operations between the cloud and edge, with edge undertaking early intelligent data processing reducing the bandwidth of data being transmitted to cloud; and building the hardware and software infrastructure to provide for this in Europe.
* Providing data sharing and collaborating solutions on the edge to handle the temporal-spatial diversity of edge data.
* Developing solutions for IoT, i.e. mostly wireless devices with energy- and processing- constraints, in heterogeneous and also hostile/harsh environments.
* Providing re-usable solutions across industrial domains.
* Methodological approach with the Integral Supply Chain, from academic, to system designers and integrators, to component providers, applications and services developers & providers and end users
At the same time, there is an increasing need to use Artificial Intelligence (AI) at the edge. The developments of AI applications mostly require processing of data in centralized cloud locations and hence cannot be used for applications where milliseconds matter in safety-critical applications. In addition to speed, edge computing offers security benefits due to wider data distribution at the edge level. Reducing the distance data has to travel for processing means decreasing the opportunities for trackers and hackers to intercept it during transmission and preserves its privacy.
DAIS has ambitious objective to develop Intelligent and Secure Edge solutions for industrial applications for European industry throughout the whole Supply Chain. More precisely, we do so by:
* Providing intelligent processing of data and communication locally at the edge to enable real-time and safety-critical industrial applications.
* Developing industrial-grade secure, safe and reliable solutions that can cope with cyberattacks and difficult network conditions.
* Providing AI techniques on the edge that match with diverse computing powers contrary to relatively consistent computing power on the cloud. As different AI algorithms have different computing power requirements, it is a big challenge to match an existing algorithm with the certain edge platform.
* Distribute and divide the complex AI operations between the cloud and edge, with edge undertaking early intelligent data processing reducing the bandwidth of data being transmitted to cloud; and building the hardware and software infrastructure to provide for this in Europe.
* Providing data sharing and collaborating solutions on the edge to handle the temporal-spatial diversity of edge data.
* Developing solutions for IoT, i.e. mostly wireless devices with energy- and processing- constraints, in heterogeneous and also hostile/harsh environments.
* Providing re-usable solutions across industrial domains.
* Methodological approach with the Integral Supply Chain, from academic, to system designers and integrators, to component providers, applications and services developers & providers and end users
The DAIS project kick-started by brainstorming about the requirement collection framework in WP1. All the partners in DAIS are involved in WP1.
After several brainstorming sessions, the current requirement collection framework was developed and announced to all partners. After collecting requirements from partners, several review meetings (virtual and F2F) were organized to review the requirements by WP, SC and task leaders. A first version of reviewed requirements was reported in D1.1.
The requirement list is a live document that changes over time. Therefore, the review process continues.
Monthly joined WP2/SC1 meetings were organized to follow up on the progress of the work and status of all available DAIS hardware. The status of the different tasks and PoC is followed up with special attention for potential delays in hardware component delivery, seen the worldwide semiconductor supply situation. So far, no major delays are reported. Almost all partners selected the ML edge node components according to the requirements in WP1 and in close interaction with different demo leaders.
WP3 includes five tasks. In the period, the focus has been on producing D3.1 which includes detailed presentations of the Proof of Concept (PoC) use-cases under development in WP3, together with presentations of the 60+ specific technical contributions under development. This has been further elaborated by the development of a unifying architecture that when completed will show the dependencies and interrelations between the TCs.
The main purpose of WP4 was to consolidate technical outputs and the industrial applications being developed throughout SC6, SC7, and SC8.
The SCs focus on three different concepts and develop applications:
Digital industry: Improvement in processes inherent to a Smart Grid, deriving in an increase in energy efficiency.
Smart transport and mobility: The ability of a swarm of drones to detect objects and obstacles, verify and track them, make decisions about the threat they may cause and trigger appropriate actions will be demonstrated.
Digital life: Show strong improvements in secure, comfortable and sustainable spaces. By utilizing distributed DAIS components with the clusters of edge IoT nodes, show ability to compute media recommendations based upon user emotions.
The work in WP6 started with project website and social media presence,
The dissemination activities have been also successfully initiated, all the relevant procedures for collecting and monitoring the dissemination progress data have been set up, and initial dissemination events have run on individual level.
Initial exploitation plans have been updated and the project-integrated exploitation has been established. The project is also active in the standardization efforts.
After several brainstorming sessions, the current requirement collection framework was developed and announced to all partners. After collecting requirements from partners, several review meetings (virtual and F2F) were organized to review the requirements by WP, SC and task leaders. A first version of reviewed requirements was reported in D1.1.
The requirement list is a live document that changes over time. Therefore, the review process continues.
Monthly joined WP2/SC1 meetings were organized to follow up on the progress of the work and status of all available DAIS hardware. The status of the different tasks and PoC is followed up with special attention for potential delays in hardware component delivery, seen the worldwide semiconductor supply situation. So far, no major delays are reported. Almost all partners selected the ML edge node components according to the requirements in WP1 and in close interaction with different demo leaders.
WP3 includes five tasks. In the period, the focus has been on producing D3.1 which includes detailed presentations of the Proof of Concept (PoC) use-cases under development in WP3, together with presentations of the 60+ specific technical contributions under development. This has been further elaborated by the development of a unifying architecture that when completed will show the dependencies and interrelations between the TCs.
The main purpose of WP4 was to consolidate technical outputs and the industrial applications being developed throughout SC6, SC7, and SC8.
The SCs focus on three different concepts and develop applications:
Digital industry: Improvement in processes inherent to a Smart Grid, deriving in an increase in energy efficiency.
Smart transport and mobility: The ability of a swarm of drones to detect objects and obstacles, verify and track them, make decisions about the threat they may cause and trigger appropriate actions will be demonstrated.
Digital life: Show strong improvements in secure, comfortable and sustainable spaces. By utilizing distributed DAIS components with the clusters of edge IoT nodes, show ability to compute media recommendations based upon user emotions.
The work in WP6 started with project website and social media presence,
The dissemination activities have been also successfully initiated, all the relevant procedures for collecting and monitoring the dissemination progress data have been set up, and initial dissemination events have run on individual level.
Initial exploitation plans have been updated and the project-integrated exploitation has been established. The project is also active in the standardization efforts.
The project aims to progress beyond state-of-the-art by developing novel hardware and software solutions and architectures for distributed AI systems, including new AI methods.
The hardware development in the project has proceeded more or less as planned and designs pushing the state of the art have been developed, but due to global supply chain issues, there will be some delays in getting delivery of the new hardware. Systems using COTS hardware have been possible to construct for use with PoCs and demonstrators.
The project will develop a number of highly innovative software components ranging from hardware support layers and drivers, through middleware, to libraries and support systems for data analytics and AI. These components will be used and integrated across project partners and demonstrators but also allowing partners to develop their competence and product portfolios.
Within the project, several new hardware/software/security/communication solutions have been developed and implemented and showcased in Proof-of-Concepts of single partner organisations or national consortia or integrated into joint demonstrators. Significant progress on these demonstrators in the different industrial application use cases was achieved during the reporting period.
Through participation in different community events, integration of project results in education, and dissemination and communication of project results to scientific, industrial, and societal communities, the project has also provided wider socio-economical impact.
The hardware development in the project has proceeded more or less as planned and designs pushing the state of the art have been developed, but due to global supply chain issues, there will be some delays in getting delivery of the new hardware. Systems using COTS hardware have been possible to construct for use with PoCs and demonstrators.
The project will develop a number of highly innovative software components ranging from hardware support layers and drivers, through middleware, to libraries and support systems for data analytics and AI. These components will be used and integrated across project partners and demonstrators but also allowing partners to develop their competence and product portfolios.
Within the project, several new hardware/software/security/communication solutions have been developed and implemented and showcased in Proof-of-Concepts of single partner organisations or national consortia or integrated into joint demonstrators. Significant progress on these demonstrators in the different industrial application use cases was achieved during the reporting period.
Through participation in different community events, integration of project results in education, and dissemination and communication of project results to scientific, industrial, and societal communities, the project has also provided wider socio-economical impact.