In fog computing platforms, the users are often mobile but the computing resources that serve them are not. However, the quality of service of a fog computing application largely depends on the proximity of the fog resources with the end-user devices making use of them. When a user moves, it is therefore important at some point to migrate the fog computing workload to maintain sufficient proximity.
Migrating an application requires to migrate both its code (which is usually executed inside a container) and its data (which are usually stored in separate storage systems).
- Code migration: all the current techniques for live-migration have limitations and therefore can successfully apply only in a limited set of scenarios. Besides, they were designed for general-purpose cloud computing environments and therefore do not exploit the specificities of fog computing platforms. The objective in this part of the PhD research project is to develop service roaming techniques based on live container migration and/or service elasticity techniques, exploiting the fact that these migrations will by definition happen over relatively short distances.
- Data migration: in cloud computing scenarios, VMs or containers can access the data in specific network-attached storage so migrating the data is rarely necessary. However, in a fog scenario it is important to keep the data close to the containers using them. We will need to investigate how to store the application data in such a way that it can be migrated efficiently in a fog infrastructure.
- Application roaming is typically triggered by the mobility of human users. This means that predicting a user’s future mobility patterns may enable the system to start migrating the application proactively even before a roaming request is issued.
- Methods and software for choosing the appropriate migration technique based on characteristics of the fog computing application.
- Methods and software for predicting user’s mobility based on prior statistical patterns.
- An integrated software for efficiently live-migrating fog computing services without affecting the application being migrated.
Rennes is the capital city of Britanny, in the western part of France. It is easy to reach thanks to the high-speed train line to Paris. Rennes is a lively city and a major center for higher education and research. The job will take place within the INRIA/IRISA research center, which is internationally recognized for its research in the domain of information and communication sciences.
14 months at U-Hopper (Trento, Italy); 7 months at Las Naves (Valencia, Spain).
Please write your application in English, as it will be examined by multiple people in different European countries. Please do not apply to more than two positions within the FogGuru project.