A Relative Position-Based Bacterial Foraging Optimization Algorithm with Dropout Strategy for Computation Offloading in Mobile Edge Computing

As a practical solution that could reduce the communication and computation load of central servers in digital factories, edge computing has been widely used in modern industry. In mobile edge computing, a reasonable offloading strategy can balance the computation load and reduce the energy consumption of mobile devices, which is the key to optimizing network operation. In this paper, a Relative Position-based Bacterial Foraging Optimization algorithm with Dropout strategy, RPBFO-D, is proposed to optimize the computation offloading problem. A many-to-many relationship model of devices-tasks-servers is established, comprehensively considering the time delay and energy consumption, and RPBFO-D is proposed to solve the problem. In this algorithm, the structure and operators of the original BFO are redesigned, and the dropout strategy of the neural network maintains diversity. Experiments with parameter settings demonstrate the effectiveness of the dropout strategy. Results show that RPBFO-D has better convergence accuracy than comparison algorithms, which demonstrates that it is a competitive approach for computation offloading.