A Runtime Resource Management and Provisioning Middleware for Fog Computing Infrastructures

The pervasiveness and the growing processing capabilities of mobile and embedded systems have enabled the widespread of the Fog Computing paradigm in the Internet of Things scenario, where computing is directly performed at the edges of the networked infrastructure in distributed cyber-physical systems. In such a scenario a static workload distribution does not suffice, because of the high dynamicity of the workload, with applications entering and leaving the system with an unknown trend, and the architecture, that may change due to connections/disconnections of the processing nodes. This paper proposes a runtime resource management and provisioning middleware for this scenario, for the dynamic distribution of the applications on the processing resources. It consists of a two-level hierarchy: i) a global Fog Orchestrator monitoring the architecture status to identify the most promising node where to run the applications to meet the expected Quality of Service while optimizing a user-defined goal, and ii) a Local Agent on each node, performing a fine-grain tuning of its resources. The co-operation between these components allows to dynamically adapt and to exploit the fine-grain nodes view for achieving the required performance/optimization goals. A middleware prototype is presented and experimentally evaluated in a Smart Building casestudy.