Maximizing Profit of Network Operators through Task Offloading in Mobile Edge Computing and Computational Resource Allocation

Abstract

Mobile edge computing is universally recognized as a crucial catalyst for the development of next-generation low-latency services and applications on mobile devices that have limited resources. The concept of delegating computationally intensive tasks to the cloud. To realize this concept, these efforts typically concentrate on optimizing system energy consumption and minimizing latency. The idea is to enable user equipment to utilize cloud resources due to limitations in user resources, facilitating dynamic sharing of computational instances among multiple users in the cloud, thus achieving efficient utilization of core cloud resources. To realize this concept, this paper employs the Cloud Radio Access Network (C-RAN) with Mobile Edge Computing (MEC) architecture comprising a pool of Baseband Units (BBU) integrated with a MEC server, along with multiple Remote Radio Heads (RRHs) situated alongside mobile terminals equipment. This configuration assists users in executing computationally intensive tasks and simultaneously generates additional profits for the network operator. This paper explores the profitability of computational offloading from the perspective of a network operator. The decisions to offload, along with the joint optimization of radio and computational resources, lead to a mixed integer nonlinear optimization problem, which is non-deterministic polynomial-time (NP) hard. Firstly, calculate the maximum profit by using three optimization algorithms: a normal Genetic Algorithm (GA), a heuristic-based Fast Genetic Algorithm (FGA), and Spectrum efficiency-based Joint Optimization for Offloading and Resource Allocation algorithm (SJOORA). Subsequently, the optimization problem of the input resource allocation. Next, the maximum profit is calculated in various scenarios to determine the most suitable algorithm for each situation.