• Raj Kumari

In the Mobile Cloud Computing (MCC) environment, to improve the application performance on smart mobile devices computation offloading is preferred. Computation offloading is beneficial only if the contextual information about the wireless environment and application is available. As MCC environment is dynamic in nature, gathering of the contextual information is itself a challenging task. The performance of offloading is influenced by the number of parameters like network status, application characteristics, mobile device configuration, cloud configuration, the deadline for task execution etc. The offloading decision is a very time- consuming process if all these parameters are considered manually. This problem can be conquered by performing offloading decision through intelligent computational techniques. Thus, in this paper, an efficient dynamic offloading system is represented which helps to take the offloading decision with high accuracy using machine learning techniques namely Logistic Regression (LR) and Support Vector Machine (SVM). The proposed work is divided into two parts. In the first part, the offloading decision is made based on available contextual information. In the second part if offloading has to be executed, then the offloaded task is scheduled on either of the two resources, namely, cloudlet or workstation. To evaluate the performance of the proposed algorithm, we developed a dataset based on face recognition application. In the dataset, three different sizes of images are considered i.e., 2MP, 6MP and 8MP. The experimental study shows that LR technique has efficiently taken the offloading decision and has generated the highest accuracy rate with 98.26% in comparison to existing experimental techniques.

machine learning, offloading, mobile cloud computing.

"Machine Learning based Dynamic Offloading System for Mobile Cloud Computing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.a761-a771, July-2023, Available :http://www.jetir.org/papers/JETIR2307092.pdf

"Machine Learning based Dynamic Offloading System for Mobile Cloud Computing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppa761-a771, July-2023, Available at : http://www.jetir.org/papers/JETIR2307092.pdf