Abstract—Recent development toward innovative applications and technologies like self-driving, augmented reality, smart
cities, and various other applications leads to excessive growth
in the number of devices. These devices have finite computation resources and cannot handle the applications that require
extensive computation with minimal delay. To overcome this,
the mobile edge cloud (MEC) emerges as a practical solution
that allows devices to offload their extensive computation to
MEC located in their vicinity; this will lead to succeeding the
arduous delay of the millisecond scale: requirement of 5
th generation communication system. This work examines the convex
optimization problem. The objective is to minimize the task
duration by optimal allocation of the resources like local and edge
computational capabilities, transmission power, and optimal task
segmentation. For optimal allocation of resources, an algorithm
name Estimation of Optimal Resource Allocator (EORA) is
designed to optimize the function by keeping track of statistics of
each candidate of the population. Using EORA, a comparative
analysis of the hybrid approach (partial offloading) and edge
computation only is performed. Results reveal the fundamental
trade-off between both of these models. Simultaneously, the
impact of devices’ computational capability, data volume, and
computational cycles requirement on task segmentation is analyzed. Simulation results demonstrate that the hybrid approach:
partial offloading scheme reduces the task’s computation time
and outperforms edge computing only.
Index Terms—Mobile Edge Cloud Computing, Partial Offloading Scheme, Resource Allocation