An Ontology-Based Approach to the Workload Distribution Problem Solving in Fog-Computing Environment

A problem of workload distribution within the heterogeneous computing environment is not new and has been solved frequently and successfully. However, optimization problem models neglect such aspects of fog computing concept as: the computation nodes are unequal in terms of desirable workload distribution; the cloud layer is the mandatory participant of the computing process. The current paper focuses on the formalizing of workload distribution optimization problem in terms of fog computing special aspects for device "offload" strategy. The task subgraph relocation to computing devices of fog layer takes place. This is a multicriteria NP-hard optimization problem with multiple constraints, which are determined by the fog-computing peculiarities. So there is a problem to get solutions of an acceptable quality under the restricted time conditions. In this paper an approach based on the optimization problem search space reduction is proposed. An ontological approach is used for this purpose. It allows to reduce the optimization problem search space and the problem solving time thereby.