ICTEAM - Public Thesis defense - Richard GIL MARTINEZ

Automated Planning to Support the Deployment and Management of Applications in Cloud Environments

Engineering decision-making mechanisms to help the deployment and management of applications running in cloud infrastructures is a challenging task. These applications call for automated solutions that: (1) explore efficiently large solution spaces (defined by the combination of machine types, provisioning actions, and state transitions expected in the temporal horizon); (2) generate deliberate plans to operate the system in a way that satisfies requirements, maximizes performance and minimizes operational costs; and (3) support the definition and revision of policies to adapt the system under expected conditions.

This thesis focuses on the design and evaluation of mechanisms that exploit automated planning to face these challenges. It presents three contributions: (1) a solution to the (offline) generation of reactive policies that exploits classical planning to support the elastic scaling of interactive applications; (2) a solution to the (online) generation of proactive plans that benefits from temporal planning and workload predictions to reconfigure interactive applications; and (3) a solution to the (offline) generation of execution policies that resorts to probabilistic planning to handle uncertainty caused by spot instance in the deployment of workflow applications. These proposals have been evaluated using realistic case studies. Results support the claim that these solutions are scalable and responsive, and able to guide the system to satisfy requirements, optimize performance and minimize operational costs.

Jury members :

Prof. Peter Van Roy (UCLouvain), supervisor

Prof. Luis Rodrigues (IST – INESC – ID, Portugal), supervisor

Prof. Charles Pecheur (UCLouvain), chairperson

Prof. Etienne Riviere (UCLouvain), secretary

Prof. Rito Silva (IST – INESC – ID, Portugal)

Dr. Ahmad Al-Shishtawy (KTH, Sweden)

Dr. Bert Lagaisse ( KUL, Belgium)

Prof. José Carlos Monteiro (IST – INESC – ID, Portugal)