The application of computing resources through mobile devices (MD) is called Mobile Computing. Between cloud datacentres and devices is (Mobile) Fog Computing (MFC). We ran Cloudsim simulator to offload tasks in suitable Fog Devices (FDs), cloud, or mobile. We stored the outputs of the simulator as a dataset with features and a target class. A target class is a device in which tasks are. Decision Tree (DT), Random Forest (RF), Extra-trees, and AdaBoost classifiers were classified based on attribute values and draw the plot of trees. According to the plot of these classifiers, we extracted each sequential condition from root to leaves and inserted it to the simulator. What these classifiers do is improve the conditions that should be inserted in the corresponding section of the simulator. We improved the response time of offloading by Random Forest, Extra-trees, and AdaBoost over Decision Tree.
Key words: Fog Computing, Decision Tree Classifier, Random Forest Classifier, Offloading, Machine Learning.
|
