New generations of mobile access networks promise low delay and high-speed throughput data connections paired with in-network processing capabilities. IoT data and local information available to users’ devices will feed AI-based applications executed in proximity on edge servers and service composition will routinely include such applications and their microservice components. PARFAIT tackles new resource allocation problems emerging due to the need of distributed edge orchestration of both computing and communication, in a context where the unknown footprint of AI-based applications requires advanced learning capabilities to permit efficient and reliable edge service orchestration. The PARFAIT project develops theoretical foundations for distributed and scalable resource allocation schemes on edge computing infrastructures tailored for AI-based processing tasks. Algorithmic solutions will be developed based on the theory of constrained, delayed, and distributed Markov decision processes to account for edge service orchestration actions and quantify the effect of orchestration policies. Furthermore, using both game and team formulations, the project will pave the way for a theory of decentralized orchestration, a missing building block necessary to match the application quest for data proximity and the synchronization problems that arise when multiple edge orchestrators cooperate under local or partial system view. Finally, to achieve efficient online edge service orchestration, such solutions will be empowered with reinforcement learning techniques to define a suit of orchestration algorithms able to at once adapt over time to the applications’ load and cope with the uncertain information available from AI-based applications’ footprints. Validation activities will be designed to demonstrate real-world solutions for practical orchestration use cases, using both large scale simulation experiments and research testbeds.

5G networks are expected to revolution our living environments, our cities and our industry by connecting everything. 5G design has, thus, to meet the requirements of two “new” mobile services: massive Machine-Type Communications (mMTC), and Ultra Reliable Low Latency Communications (URLLC). Slicing concept facilitates serving these services with very heterogeneous requirements on a unique infrastructure. Indeed, slicing allows logically-isolated network partitioning with a slice representing a unit of programmable resources such as networking, computation and storage. Slicing was originally proposed for core networks, but is now being discussed for the Radio Access Network (RAN) owing to the evolution of technologies which now enable its implementation. These technologies include mainly the tendency for virtualizing the RAN equipment and its programmable control, the advent of Mobile Edge Computing (MEC) and the flexible design of 5G on the physical and MAC layers. However, the complete implementation of slicing in the RAN faces several challenges, in particular to manage the slices and associated control and data planes and for scheduling and resources allocation mechanisms. MAESTRO-5G project develops enablers for implementing and managing slices in the 5G radio access network, not only for the purpose of serving heterogeneous services, but also for dynamic sharing of infrastructure between operators. For this aim the project puts together exerts on performance evaluation, queuing theory, network economy, game theory and operations research. MAESTRO-5G is expected to provide: •A resource allocation framework for slices, integrating heterogeneous QoS requirements and spanning on multiple resources including radio, backhauling/fronthauling and processing resources in the RAN. •A complete slice management architecture including provisioning and re-optimization modules and their integration with NFV and SDN strata. •A business layer for slicing in 5G, enabling win-win situations between players from the telecommunications industry and the verticals, ensuring that the 5G services are commercially viable and gain acceptance in the market. •A demonstrator showing the practical feasibility as well as integration of the major functions and mechanisms proposed by the project, on a 5G Cloud RAN platform. The enhanced platform is expected to support the different 5G services (eMBB and IoT) and to demonstrate key aspects of slicing, such as: - Ability to create and operate in parallel multiple slices, on the same infrastructure and sharing the same radio resources (e.g. spectrum), each having different service requirements. - Ability to create and operate in parallel and independently different slices, sharing the same infrastructure/spectrum, belonging to different business actors, such as different operators. - Demonstrate inter-slice control ensuring respect of SLAs and a fair resource sharing.

Building on the databases of images of melanocytic lesions and certain methodological developments from the SKINAN and DIAMELA projects of the French National Agency for Research (ANR), it is proposed to build a computer-assisted melanoma diagnostics tool based on the presentation in real time of similar images of the case studied by the dermatologist and whose histology is known. The project aims to segment in both a supervised and semi-supervised manner, the image databases into groups having a perceived similarity. Approaches using pairwise and structured classifier types coupled notably with an extraction of characteristics through deep learning will be implemented. This original approach will be evaluated in the concrete framework of routine dermatological consultations. We expect to have a noticeable improvement in the quality of the diagnosis of melanocytic lesions, especially for suspicious lesions, responsible for a great deal of unnecessary excisional biopsies.

The use of spectrum in millimeter bands is becoming essential to enable future wireless networks to offer significant capacity gains. However, as propagation losses become significant, antenna and beam formation become key elements in maintaining a reasonable range and limited infrastructure costs. Phased array antenna solutions require a very large number of RF chains and are expensive. The project aims to develop innovative alternative solutions based on reconfigurable metasurfaces. The work will focus on three areas of research: the practical implementation of such antennas in the EHF bands, technical and algorithmic solutions enabling the antennas to address several users simultaneously, and the rapid reconfiguration of the beams adapted to the radio channel. To reach the aforementioned objectives, the project will first precise scenarios and usages, highlight mmWave radio channel constraints, and provide recommendations on metasurface based antenna design. This will be performed in WP1 during the first 6 months. WP2 addresses the design of electronically steerable antennas based on an array of unit cells having the possibility to reflect/transmit impinging waves from the feeder(s) with a phase shift in a predefined set including zero phase shift. To ensure reconfigurability of these unit cells, a control system will be defined and implemented. Unit cells will be optimized so that their phase shift remains within a given percentage of its nominal values over the bandwidth of interest. Two prototypes will be implemented in WP2: first a full antenna system including an electronically controlled transmitarray, the multi-element focal systems and the digital control will be designed, optimized, fabricated and fully characterized by CEA Leti in the 26-28 GHz band. The antenna system will be able to generate at least four independent beams. The know-how of CEA Leti on transmitarrays is almost unique and has been mostly developed during a long collaboration with the IETR antenna team. Coding metasurface for cmWave and mmWave are currently developed in DOME group at IEMN. In the framework of a partnership with DGA, the main goal has been to propose artificial structures for Radar Cross Section reduction. In this project, as an alternative to absorbing layers previously studied in the group, the idea is to deviate the incident beam in one or several directions out of the detector spatial range. This approach can also be used to select the beam reflection direction. Regarding the size reduction inherent to frequency increase up to 60 GHz, an external company (INODESIGN) will be in charge of the fabrication. CSAM group of IEMN will bring its expertise in mmWave tune able structures using semi-conductor switching devices. The characterization of the reflectarray will be carried out at the telecom platform of IRCICA institute. To this aim, the 60 GHz anechoic chamber, already available at IRCICA, will be completed with a Newport monitored platform allowing an accurate angular control. In WP3, BF will be studied for both single and multi-user cases assuming possibly more than one stream per user. The optimization of the grid can be performed off line (using predefined codebooks) or dynamically by applying algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), or deep learning (DL) approaches. The CNAM and Orange will provide their expertise in that domain to design and implement these algorithms. Performance evaluation of the prototypes and BF algorithms will be performed in a real environment in WP4 with channel sounder, or an SDR approach. This WP will be led by Orange, with contributions of all the partners, to ensure an efficient exploitation of MESANGES results in 5G+ and 6G networks.

An emergent trend has recently received significant attention: networks of passively and/or actively mobile sensors (that is, swarms of robots). These robots are able to execute collectively various complex tasks; one application being for example to optimise the coverage of interest zones under natural or human disaster, and help in search and rescue tasks. A characteristic feature is the extreme dynamism of their structure, content, load, and even execution environment. Possibly the subjects to Byzantine failures, obtaining certified guarantees on their behaviour is a crucial issue, as they belong to an area of computer science well-known for being remarkably harsh on informal reasoning, possibly leading to disastrous errors when arguments are not perfectly clear. Project SAPPORO aims to propose a formal provable framework (mechanised in the (awarded) Coq proof assistant) to assess the correctness of localised distributed protocols at the core of dynamic mobile sensor networks.