Computation power maximization for mobile edge computing enabled dense network

High-density connection is among the natures of next-generation wireless communication systems. Meanwhile, various computation-intensive smart applications are becoming growing popularity with the technology boom. Thus, strong computation power will become a crucial requirement for wireless communication systems. Mobile edge computing provides a promising solution to this requirement by pushing a cloud-like computation capacity to the network edge. This study aims to maximize the computation power of a mobile edge computing enabled dense network. To this end, a computation bits maximization problem is formulated by jointly optimizing offloading decision and resource allocation. The problem is a mixed-variable nonlinear programming problem. First, by analyzing the feasibility of computation modes and constructing a user distribution strategy, the original problem is decoupled into two sub-problems, i.e., the assignment of the offloading users and resource allocation. The offloading users' assignment is modeled as a restricted multiple knapsack problem, and a profit density is defined to maximize the overall profits of multiple knapsacks. Then, an improved differential evolution algorithm is developed to address the knapsack problem, in which mutation and repair operators are designed according to the profit density. Based on the optimal solution to the knapsack problem, the resource allocation sub-problem is solved by the corresponding calculation. Finally, extensive experiments are conducted to evaluate the performance of our scheme. Results show that: (1) our scheme provides superior computation power compared to that of benchmark schemes; (2) the performance gain of our scheme over benchmark schemes expands with growing connection density. Therefore, our scheme is an effective computation power optimization scheme.