Comparative Analysis of Traditional, Machine Learning, and Hybrid Optimization Techniques for Production Scheduling in Small-Scale Industries

Production scheduling plays a crucial role in improving productivity, reducing operational delays, and enhancing resource utilization in small-scale manufacturing industries. The present study focuses on the comparative analysis of traditional scheduling methods, machine learning approaches, and hybrid optimization techniques for minimizing makespan and machine idle time. Experimental investigations were carried out using industrial production data including processing time, machine availability, setup time, and job priority parameters. Traditional scheduling methods such as FIFO, SPT, and EDD were compared with heuristic optimization techniques including Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), along with machine learning models such as ANN and SVM. Statistical analysis using ANOVA, regression analysis, and prediction accuracy evaluation was performed to validate scheduling performance. Experimental results indicated that hybrid ML-GA optimization achieved approximately 30–35% reduction in makespan, 40–45% reduction in idle time, and significant improvement in machine utilization and production throughput compared to conventional scheduling approaches. The study concluded that hybrid optimization models provide superior adaptability, scheduling efficiency, and real-time decision-making capability for Industry 4.0-oriented intelligent manufacturing systems in SMEs.

© 2026 — Authors retain the copyright of this article. This is an open access article distributed under the Creative Commons Attribution License (CC BY 4.0) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.