Reinforcement Learning based Fog and Cloud Resource Allocation for an IoRT-aware Business Process

Abstract

IoRT-aware BP aims to promote the business process (BP) within robotics and IoT capacities.This incorporation ensures machine-to-machine (M2M) communication and the automatic execution of tasks by using robot devices. Nonetheless, the execution of this process inside the enterprise may be costly due to the consumed resources, the need for computational capacity, etc. To close these gaps, the business process outsourcing (BPO) strategy can be carried out toout source the IoRT-aware BP to external environments (e.g., Cloud, Fog, etc.). To profit from outsourcing, an enterprise should identify suitable resources to ensure optimal process execution. The selection of resourcesis known in the literature as resource allocation (RA).The RA problem is described in this work using the Markov Decision Process (MDP), and it is resolved using reinforcement learning (RL). The proposed approach relies, on one hand, on Q-learning as an RL algorithm, and on the other hand, it considers the extension of the ifogSim tool to support the process execution using Fog and Cloud resources. The obtained results are promising in terms of response time regarding the scale-up of the considered resources. Furthermore, the experimental results show that our approach offers a substantial advantage in optimizing the performance of RA, which confirms its usefulness and relevance compared to other common methods.