An Intelligent Logistics Scheduling by using Combined Ant Colony Optimization with Harmony Search

Nowadays, the logistic scheduling a vital component of the modern economy, playing a critical role in ensuring the seamless and efficient operation of the supply chain. The logistic scheduling requires efficient operation for timely goods delivery. However, it involves complex factors and route allocation optimization in logistics systems is a significant issue with the lack of convergence speed. Hence, this research proposes an intelligent logistics scheduling model based Ant-Colony Optimization and Harmony Search (ACO-HS) to improve the convergence speed by minimizing the transportation time. This process begins with the collection of supply chain logistics dataset from kaggle portal. Then, the data is preprocessed by using regression imputation, for predicting the missing values and logarithmic-scaling for transforming values into nonlinear space. After that, ACO and HS are utilized for recognizing the new schedule of supply chain logistics to obtain an efficient optimal route. As per the results, the proposed ACO-HS model achieved outstanding results in terms of transportation time, product damage, and customer satisfaction with 2 days, 9%, and 97% respectively, when compared to existing Adaptive Ant Colony Optimization for Dynamic Scheduling (AACA-DS) model.