QoS-Aware Service Placement for Fog Integrated Cloud Using Modified Neuro-Fuzzy Approach

Fog computing provides an infrastructure for enhancing quality of services (QoS), especially for time-critical applications. The reach of the Internet of things (IoT) has extended to another dimensions, expanding from acquisition of data to device interconnections and to data-processing. This acceleration assimilate fog and cloud compuhting into a single system for improving QoS and resource utilization. Due to the heterogeneity of IoT devices, selecting suitable computation devices and allocating resources are substantial issues that need to be addressed for effective resource utilization. This work proposes a smart decision-making system for service placement based on the various parameters. The proposed work utilizes machine learning based techniques: clustering for the labelling of the services followed by neuro-fuzzy based ANFIS model for offloading the services. A 5-layered neuro-fuzzy inference model is implemented to represent as an intelligent decisionmaking system. This work provides a solution for the learning phase of ANFIS by employing a meta-heuristic-based algorithm. Three metaheuristic algorithms, i.e. GA-ANFIS, JAYA-ANFIS and PSO-ANFIS are implemented for the training of the ANFIS model. The effectiveness of the model has been examined for the prediction of computing layer for offloading of the services. The results are compared with each other as well as with the conventional gradient-based ANFIS model. Experiment shows that the evolutionary-based neuro-fuzzy models yield imperative results against gradient-based neuro-fuzzy.