Intelligent Optimization of Power Supply Chain Operational Decision based on Ant Colony Optimization-Convolutional Neural Network Framework

Optimizing power business supply chain processes is crucial for guaranteeing efficiency, reliability, and affordability in energy management. Conventional decision-making techniques are plagued by excessive computational complexity, inefficient resource utilization, and poor response times. Although methods such as linear programming and heuristic algorithms have been applied, they are inflexible and non-scalable to dynamic settings. To overcome such limitations, this research suggests a hybrid optimization model that integrates Ant Colony Optimization (ACO) with Convolutional Neural Networks (CNNs). ACO simulates ant search patterns in finding the best supply chain routes, whereas CNNs handle big data to identify patterns and predict the best strategies. The suggested ACO-CNN model is compared with traditional methods in terms of accuracy, F1-score, and computational expense. Experimental outcomes confirm the ACO-CNN model has 97.7% accuracy and a 96.5% F1-score, surpassing conventional methods. This hybrid solution strengthens supply chain logistics, predictive decision-making, and operational flexibility under uncertain conditions. The model effectively minimizes energy distribution costs, enhances resilience, and offers an intelligent, scalable solution for next-generation energy systems. These outcomes identify the strength of combining ACO and CNNs for innovative power supply chain optimization.