www.recap-project.eu
RELIABLE CAPACITY PROVISIONING AND
ENHANCED REMEDIATION FOR
DISTRIBUTED CLOUD APPLICATIONS
PROJECT MOTIVATION
EXPECTED RESULTS
Large-scale computing systems are today built as distributed systems where
components and services are distributed and accessed remotely through clients and
devices. However, while recent years have seen significant advances in system
instrumentation as well as data centre energy efficiency and automation, computational
resources and network capacity are often provisioned using best effort provisioning
models and coarse-grained quality of service (QoS) mechanisms.
1• Distributed and Efficient Data Collection on Heterogeneous Infrastructures
RECAP will go beyond the current state of the art and develop the next generation of
cloud/edge/fog computing capacity provisioning via targeted research advances in cloud
infrastructure optimization, simulation and automation. The overarching result of RECAP
is the next generation of agile and optimized cloud computing systems. The outcomes of
the project will pave the way for a radically novel concept in the provision of cloud
services, where services are instantiated and provisioned close to the users that actually
need them by self-configurable cloud computing systems.
4• End-to-end Component-level Quality Assurance by Capacity Provisioning
2• Data Science Analysis for Automated Infrastructure and Application Modelling
3• Intelligent Automation by Automated Cloud Infrastructure Optimisation
5• Application and Infrastructure Simulation for Cloud Optimisation
6• System Observability by Visualizing Data Collection and Modelling Results
7• Improved Resource Utilisation and User Satisfaction
REALISATION APPROACH
To fulfil the vision of RECAP, the project will define and implement a novel architecture realising
the ideas relating to resource management, data science, and analytics and intelligent
automation:
• The RECAP Collector will gather, synthesize and analyse the relevant monitoring metrics
across the infrastructure, specially focusing on the edge computing layer.
• The RECAP Application Modeller will address the challenge of discovering and defining
applications internal structure as well as their quality of service requirement.
• The RECAP Workload Modeller will implement for models decomposition, classification
and prediction of workloads, as well as models for how the load propagates in
applications.
• The RECAP Optimiser will make a more efficient use of the infrastructure and maintain
application KPIs through infrastructure optimisation techniques and application
placement optimisation actions.
• The RECAP Simulator will assist the RECAP Optimiser to evaluate different trade-offs
such as cost, energy, resource utilization, allocation of resources and performance, before
actually applying them into the real deployments.
USE CASES
INFRASTRUCTURE AND NETWORK MANAGEMENT
led by Tieto
COMPLEX BIG DATA ANALYTICS ENGINE
led by Linknovate
This use case will demonstrate how the profiling and simulation of
infrastructure, network function and service function characteristics
can be automated to ensure the desired QoS for the different networks
managed by Tieto.
This use case will demonstrate how complex applications and virtual
data centres can be modelled and automatically improved in cloud
environments, resulting in cost savings and improved performance.
FOG AND LARGE SCALE IOT SCENARIO FOR SUPPORTING SMART
CITIES
led by SATEC
NETWORK FUNCTION VIRTUALISATION, QOS MANAGEMENT AND
REMEDIATION
led by BT
This use case will demonstrate the capabilities of RECAP for
automating the reallocation of resources at the edge of the network via
edge and fog computing in order to reduce the latency for their
customers, and demonstrate cost savings and easy resource
management for data centre operators.
This use case will demonstrate how the remediation techniques
applied by RECAP can alleviate different types of failures due to the
automation of orchestration, scheduling and rescheduling of
virtualised network functions.
This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under Grant Agreement Number 732667