TRANSPARENT APPLICATION DEPLOYMENT IN A SECURE, ACCELERATED AND COGNITIVE CLOUD CONTINUUM

Project Information

SERRANO

Grant agreement ID: 101017168

DOI

10.3030/101017168

Project closed

EC signature date 8 December 2020

Start date 1 January 2021

End date 31 December 2023

Funded under

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Total cost

€ 4 343 180,00

EU contribution

€ 4 343 180,00

Coordinated by

EREVNITIKO PANEPISTIMIAKO INSTITOUTO SYSTIMATON EPIKOINONION KAI YPOLOGISTON
Greece

Periodic Reporting for period 2 - SERRANO (TRANSPARENT APPLICATION DEPLOYMENT IN A SECURE, ACCELERATED AND COGNITIVE CLOUD CONTINUUM)

Reporting period: 2022-07-01 to 2023-12-31

Summary of the context and overall objectives of the project

We are witnessing a wave of emerging cloud computing technologies and services that empower advanced applications from different vertical sectors, with diverse requirements. These trends give rise to a number of fundamental challenges that relate to the application deployment, the support of heterogeneous infrastructures and the provided security.

Supporting a develop once, deploy everywhere approach over heterogeneous resources requires intent-driven operations that enable applications to express their high-level requirements in an infrastructure-agnostic manner and translate them to infrastructure-aware configuration parameters.

The utilization of decentralized and heterogeneous, edge/cloud/HPC infrastructures that operate under different administrative domains requires security and trustworthiness on multi-tenant environments. Providing acceleration at the edge and cloud is also mandatory for high performance and energy efficient operations.

The movement towards federations of loosely coupled autonomous or semi-autonomous systems that are self-organized in a distributed manner, present a number of challenges regarding unified management and service deployment, resource coordination, disaggregation, and interoperability. This make necessary intelligent and autonomous orchestration mechanisms that automatically determine the most appropriate resources to be used and service assurance mechanisms that facilitate the autonomous adaptation and management of the deployed services and resources.

SERRANO overall objectives are the following:
1: Define an intent-driven paradigm of federated infrastructures consisting of edge, cloud and HPC resources
2: Develop security and privacy mechanisms for accelerated encrypted storage over heterogeneous and federated infrastructures
3: Provide workload isolation and execution trust on untrusted physical tenders
4: Provide acceleration and energy efficiency at the edge and cloud
5: Cognitive resource orchestration and transparent application deployment over edge/fog-cloud/HPC infrastructures
6: Demonstrate the capabilities of the secure, disaggregated and accelerated SERRANO platform in supporting highly-demanding, dynamic and safety-critical applications

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The main achievements during the Reporting Period 1 (M1-M18) are summarized below. All related deliverables have been prepared and submitted.

WP1: Project technical and administrative management activities have been performed as planned.

WP2: (i) State of the art analysis, (ii) specifications of the SERRANO Use Cases (UCs) and requirements for the SERRANO platform, (iii) definition and quantification of Key Performance Indicators (KPIs), (iv) overview of the UCs business vision, the project’s and platform’s goals, (v) description of SERRANO platform architecture.

WP3: (i) Investigate and integrate non-volatile memory express accelerators and internet protocol secure and transport layer security accelerators, (ii) employ secure and measured boot techniques for edge infrastructure, (iii) build system demonstrator with network interface card and processing server, (iv) develop a lightweight hypervisor tailored to run unikernels as functions.

WP4: Develop accelerated versions of particular kernels on GPU/FPGA platforms. On the HPC side, the parallel shared and distributed memory implementation of various kernels have been accomplished. Activities regarding the efficient integration of hardware accelerators over the SERRANO platform have been performed. vAccel framework has been extended, facilitating access to hardware accelerators by applications running as containerized functions.

WP5: Develop and release the SERRANO platform's initial version. These included a number of components and their interfaces: the SERRANO abstraction models and the AI-enhanced Service Orchestrator, the Resource Optimization Toolkit and multi-objective resource optimization algorithms, the SERRANO Telemetry framework, a custom container runtime and the SERRANO core orchestration mechanisms. In addition, research activities conducted for the integration of a power measurement system into the EXCESS test cluster.

WP6: Provide the relevant CI/CD tools and set up the DevSecOps pipelines for development testing and continuously integration of the mechanisms, models and frameworks developed in technical WPs. The SERRANO SDK was also defined. Τhe KPIs and the evaluation methodology were also provided, identifying the role of the UCs. Initial developments have been performed for all three UCs.

WP7: Perform business modelling by defining a business canvas and capturing potential exploitation models for the innovations in SERRANO. Dissemination and communication activities have been carried out. Standardisation activities and compliance have also been pursued.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The European Union’s vision highlights the need to:
develop cloud solutions and testbeds combining various platforms
provide novel solutions for federating infrastructures
compose dynamic workflows, capable of reacting in real-time to unpredictable events
provide application developers with greater control over infrastructures and services
to provide end-users with seamless access to continuous service environments
to address security, data protection, performance, resilience, energy-efficiency and other requirements.

SERRANO combines in an automated, transparent and efficient manner heterogeneous resources from: (i) edge layer, (ii) multiple clouds (federated operation), and (iii) HPC infrastructures. In addition, SERRANO provides advancements on several fronts: (i) security and privacy by design, (ii) application security and low-latency in multi-tenant environments, (iii) hardware acceleration and energy efficiency, (iv) transparent application deployment, (v) data-driven orchestration of resources and applications.

SERRANO’s modular-by-design approach supports the creation of a plethora of services that can be placed in the center of an innovative market ecosystem comprising of a variety of stakeholders (Figure 1).

The SERRANO services include:
(i) SERRANO Infrastructure as a Service (IaaS): Secure, accelerated, federated infrastructures consisting of edge, cloud and HPC resources that also utilize novel cognitive mechanisms for the automation and optimization of their internal operations.
(ii) SERRANO Platform as a Service (PaaS): Domain specific and generic platforms for deploying and executing safety-critical, low-latency, data-intensive applications and other workflows.
(iii) SERRANO Cognitive Distributed Secure Storage (CDSSaaS) or Extreme Scale Analytics services (ESAaaS).
(iv) SERRANO Business Processes as a Service (BPaaS).

We expect that SERRANO, empowered by its technology advancements, will be among the major contenders of the cloud IaaS, PaaS and SaaS markets. In this way, SERRANO will boost EU’s edge, cloud, high-performance cloud infrastructures and cloud-native applications markets towards the competitive global market landscape.

figure01.png