In Mobile Cloud Computing (MCC), computational offloading is an external infrastructure to execute a computational task deployed by low-power devices with weak computational devices, whereas large cloud servers can handle expensive workloads, and thus, intensive computing tasks are often offloaded to the cloud. It facilitates improved energy-saving and mobile application performance improvement.
   The computational offloading systems are based on the system awareness of its surrounding environment, information regarding the resources that are being provided, to decide where and when to perform offloading, as well as to infer the contextual information of mobile devices. Cloud resource monitoring plays a significant role in offloading decision-making since the cloud offers runtime support for the offloaded application to gain the advantage of computation offloading.
   Traditional machine learning models have introduced decision engines and techniques for the adaptive and dynamic nature of mobile devices for decision-making on whether the computation is offloaded or not. However, it lacks support for multi-task environments and workload adaptation to multiple cloud models. Thus, deep learning-based context-aware offloading decision algorithm aims at providing code or data offloading decisions at runtime on the selection of wireless medium and appropriate cloud resources. It focuses on performing context-sensitive computational offloading by utilizing different deep learning classifiers to predict and ensure high accuracy in offloading decisions.