Adaptive Scheduling of Continuous Operators for IoT Edge Analytics

Abstract

In this paper, we address the problem of adaptive scheduling of data stream processing and analytics (DSPA) applications in a shared edge fog cloud (EFC) continuum with response time constraints. The focus is on handling the dynamic workload of DSPA applications caused by the variability of their input data stream rates generated by mobile IoT devices, and the dynamically available resource capacity in the EFC continuum. To address these challenges, we characterise the different types of resources in the EFC continuum, as well as the operators that make up a DSPA application. Based on this characterisation, we propose models to evaluate the response time and the cost of using the resources in the always dynamic EFC continuum. We then formulate the problem of adaptive scheduling of a DSPA application in the EFC continuum with the objective of minimising the cost of using the shared resources subject to the constraints of the response time and the available capacity of the EFC resources. We propose a heuristic algorithm that dynamically computes a new scheduling of the DSPA application, taking into account its current deployment state and the current state of the shared resources in the EFC continuum. Experimental results, using simulation, show the effectiveness of our proposed algorithm against algorithms of related work.