Multi-objective optimal offloading decision for multi-user structured tasks in intelligent transportation edge computing scenario

With the continuous increase in the number of vehicles and people on urban roads, various traffic problems have become increasingly serious and intelligent transportation has gradually gained widespread attention. As a computing paradigm that could effectively reduce the task processing time consumption of user device and the cost of cloud server, edge computing has become an indispensable part of intelligent transportation system. However, how to reduce the load imbalance of edge computing server while ensuring that the task processing of intelligent transportation device takes less time consumption and energy consumption has become a challenge. In order to tackle this challenge, the computation offloading decision-making problem in the intelligent transportation edge computing scenario was modeled as a multi-objective optimization problem in this paper, and an adaptive multi-objective optimization algorithm (E-NSGA-III) based on NSGA-III was used to solve this problem, and comparative experiment with other methods was made. Experimental results show that compared with NSGA-II, MOEA/D and NSGA-III, proposed algorithm (E-NSGA-III) in this paper can mostly reduce time consumption by 14.28%, 18.42% and 9.82%, energy consumption by 5.59%, 6.79% and 4.83%, and load balancing variances by 21.73%, 33.46% and 18.25%.