Cloud-Based Intelligent Business Platform for Optimization in Tobacco Enterprises Using Big Data Analytics and Genetic Algorithms

The tobacco sector has to deal with a number of complicated tasks in addition to the optimization of manufacturing, resource management and business systems owing to ever-changing customer needs and the complicated nature of operations. This research proposes an intelligent business platform for tobacco enterprises which possesses cloud technology and optimization techniques that can turn around the performance of enterprises. The platform amalgamates big data analytics, predictive analysis and multi-objective optimization in order to solve scheduling issues, stock control, energy consumption, as well as demand forecasting. A cloud-based system not only enhances the scalability of the system but also facilitates the access and speed of processing. The optimization framework employs genetic algorithms (GA) for scheduling of tasks with neural networks (NNs) for predicting demand and scheduling. Simulated enterprise scenarios are used to test the system both for the purpose of improving performance in relation to scheduling efficiency and costs, as well as the overall enterprise performance. This research’s originality can be traced to the conception of an integrated, cloud-based system which connects performance improvement at the enterprise level with localized manufacturing optimization. By taking the optimization process beyond the confines of scheduling and applying it to larger-scale business systems, this solution offers a flexible framework that accommodates the requirements of the tobacco industry. A final contribution of the consolidated knowledge is a case regarding the evolution of the implemented system in a cigarette factory. It is clear that the effectiveness of the automated optimization scheduling strategy from the production’s point of view is tested by simulation.