DEEP: A Vertical-Oriented Intelligent and Automated Platform for the Edge and Fog

Abstract

The 5 th generation (5G) of mobile communications introduces improvements on many fronts when compared to its previous generations. Besides the performance enhancements and new advances in radio technologies, it also integrates other technological domains, such as cloud-to-things continuum and artificial intelligence. In this work, the 5G-DIVE Elastic Edge Platform (DEEP) is proposed as the linking piece for the integration of these technological domains, making available an Intelligent Edge and Fog 5G End-to-End (E2E) solution. Such solution brings numerous benefits to the vertical industries by enabling a streamlined, abstracted, and automated management of their vertical services, thus contributing to the introduction of novel services, cost savings, and improved time-to-market. Preliminary validation of the proposed platform is performed through a proof-of-concept, along with a qualitative analysis of its benefits to Industry 4.0 and Autonomous Drone Scouting vertical industries.

FoReCo: A Forecast-Based Recovery Mechanism for Real-Time Remote Control of Robotic Manipulators

“…Under the umbrella of the 5G-Public-Private-Partnership (5G-PPP) and the European Research Council (ERC), the European networking community has been focusing on how 5G and beyond 5G architectures can support Industry 4.0. 5G-DIVE [8] and 5Growth [9], are two examples of platforms that manage the adequate resource provisioning and allocation of services like a remote control in Industry 4.0. More recent European research projects [10] as Daemon [11] and Hexa-X [12] also provide support to Industry 4.0 applications by bringing intelligence to the network in order to meet strict constraints such as reliability.…”

“…Works as [13]- [16] introduce errors in remotely-controlled robotic manipulators when applied in networks that suffer from high latencies or packet losses. Also, they cannot rely on network platforms like [8], [17], [11] and [12] to overcome such problems, as these platforms make a best-effort approach by means of network resource allocation and life-cycle management. That is, platforms as 5Growth [17] make the best to allocate network and computing resources for applications as [16], but they do not assist the remote-control application to recover when control commands are delayed or lost in the network.…”

“…Fig. 8 (middle) shows the results when FoReCo recovers packets using the MA solution specified in (8), and Fig. 8 (bottom) shows the results when FoReCo uses the VAR solution to recover packets -as specified in (5).…”

OROS: Orchestrating ROS-driven Collaborative Connected Robots in Mission-Critical Operations

“…Nevertheless, none of the above works considers networking aspects in their optimization, nor adopt an NFV approach for their deployments. Recent works such as [15] and [16], started exploring the benefits of adopting 5G and cloud-native deployment in robotic applications exploiting the offloading of computational tasks to fog, edge or cloud systems so as to build a cloud-to-things continuum. Despite their promising results, the current research is mainly focusing on virtualization aspects, and on the development of orchestration platforms to automate the deployment and allocation of both networking and computing resources over the 5G infrastructure.…”

FoReCo: a forecast-based recovery mechanism for real-time remote control of robotic manipulators

“…Under the umbrella of the 5G-Public-Private-Partnership (5G-PPP) and the European Research Council (ERC), the European networking community has been focusing on how 5G and beyond 5G architectures can support the Industry 4.0. 5G-DIVE [8] and 5Growth [9], are two examples of platforms that manage the adequate resource provisioning and allocation of services like remote control in Industry 4.0. More recent European research projects [10] as Daemon [11] and Hexa-X [12] also provide support to Industry 4.0 applications by bringing intelligence to the network in order to meet strict constraints as reliability.…”