A Hybrid Optimization Algorithm for Enhancing Transportation and Logistics Scheduling in IoT-Enabled Supply Chains

IoT-integrated supply chains play an important role in managing the movement of products and distribution, which relies on the processing of real-time data gathered using sensors and IoT-connected vehicles to make informed decisions that reduce logistical expenses. However, the optimization of transportation and logistics scheduling is still one of the most difficult tasks, which requires balancing demand and vehicle capacity, as well as delivery time in varying circumstances. This research assesses the performance capabilities and utility of four optimization algorithms, differential evolution (DE), a genetic algorithm (GA), simulated annealing (SA), and prism refraction search (PRS), which are applicable in IoT-integrated logistical processes. Notably, on the basis of the unique characteristics possessed by the four algorithms, a combination approach referred to as Bidirectional PRS-SA Optimization (Bi-PRS-SA) was formulated. This method ideally exploits the strengths of global and local searches within the search space. Furthermore, the research aims to discuss the proposed conceptual framework for integrating the proposed strategy into an overall IoT framework that would initiate dynamic supply chain management through the adaptation of the proposed strategy. Results show that the proposed strategy is better than the existing strategies of DE, GAs, SA, and PRS in terms of an overall range of 15–25%. Statistical validation via the Wilcoxon signed-rank test confirms these improvements are significant (p < 0.05). The findings suggest that the Bi-PRS-SA framework offers a robust and scalable solution for real-time logistics management in IoT-enabled environments.