A Novel Decision Making Strategy for Computation Offloading in Mobile Edge Computing
Sasmita Rani Behera, Niranjan Panigrahi, Sourav Kumar Bhoi, Anoop Sahani, Jagadish Mohanty, Diptimayee Sahoo, Anita Maharana, Lakshmi Priya Kanta, Pratistha Mishra · 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA) · 2020
Recently, Mobile Edge Computing (MEC) has emerged as a suitable computing paradigm to resource-constrained mobile devices for efficient execution of complex online applications, e.g., augmented reality, face recognition application, gaming etc. Computation offloading in MEC is a solution to handle such computational-intensive applications. It is a process by virtue of which computations are migrated to edge nodes for execution. It will provide benefits in terms of energy savings, reduced latency and improved mobile application performance. However, making an offloading decision is a challenging task because of its dependency on many time-varying network parameters, environment parameters, and device parameters. An improper decision can lead to under-performance of the offloading process. In this context, this paper has proposed a novel decision making strategy based on machine learning approaches by using profiler's information. Simulation results show that the proposed decision tree method has a performance accuracy of 95%, based on the context information.