Many-Objective Computation Offloading in Vehicular Edge Computing Using Bayesian and Incremental Learning Methods

Many-objective computation offloading (MOCO) has emerged as a critical research issue in vehicular edge computing. A key challenge in the MOCO problem is how to optimize task offloading under limited edge computing resources to effectively balance multiple objectives, such as latency, energy consumption, and load balancing. To address this challenge, we formulate the MOCO problem by modeling the task computation and offloading procedure of vehicle terminals (VTs) based on queuing theory, which aims to minimize the average delay time, average-energy consumption, and average offloading cost for each VT task, as well as the average load variance of edge resources. To tackle the MOCO problem, we propose a novel evolutionary algorithm based on Bayesian maximum entropy and incremental learning (BMEILEA) for efficient optimization of all objectives. A novel many-objective fitness evaluation mechanism based on Bayesian maximum entropy is proposed to evaluate and select solutions in the evolving population. An adaptive dynamic reference point strategy based on incremental learning is developed to effectively guide the evolutionary process. Extensive experimental results show that BMEILEA outperforms other well-known many-objective algorithms in solving the MOCO problem and achieves better convergence and diversity in the obtained nondominated solutions.