Dynamic Cooperative Whale Optimization Algorithm for Multivehicle IoV Path Planning

Abstract

The Internet of Vehicles (IoV) presents significant challenges for path planning algorithms in dynamic traffic environments. This article proposes the Dynamic Cooperative Whale Optimization Algorithm (DCWOA) for multivehicle path planning in IoV. DCWOA enhances the Whale Optimization Algorithm with a three-layer structure (Individual, Group, and Group Cooperation) to optimize from local to global scope. Key innovations include: 1) a dynamic adjustment factor combining improved encircling and spiral update mechanisms; 2) local and global cooperation mechanisms enabling coordinated planning through vehicle communications; and 3) a multiobjective weighted decision model integrating travel time, fuel consumption, safety, and emissions. Comparisons with five state-of-the-art algorithms (WOA, MEWOA, PSBES, MGO, DGCO) on the CEC2017 benchmark suite show DCWOA achieving optimal performance in 27–29 of 30 test functions. In IoV environments, DCWOA demonstrates 36% improvement in optimization efficiency at 60% traffic density and reduces travel time by 21%–26%. During unexpected events, DCWOA achieves 7-s path adjustment time with 100% success rate, outperforming comparison algorithms’ 12–28 s and 65%–85%. The code is available at: https://github.com/yangwb02/MVPP-DCWOA.