Communication scheduling scheme based on big-data regression analysis and genetic algorithm for cyber-physical factory automation

In the Industry 4.0 era, enterprises are eager to add intelligent and cyber-physical technologies to further enhance the factory automation. However, in cyber-physical factory environment, more than hundreds of or thousands of IoT devices could send data at the same time, which affect the completeness of data collection and also diminish the consequent decision correctness. In this work, we proposed a novel communication scheduling scheme based on big-data regression analysis and genetic algorithm for IoT-enabling devices to collect data in cyber-physical factory automation. The basic idea is to discover collection behaviors of IoT devices and apply the extracted behavior in finding optimal communication schedules. Our proposed scheme asks each IoT device moderately utilize the network bandwidth with their in-memory buffer for maximizing the global benefit, rather than only self benefit. Then we conducted experiments to verify and analyze the proposed scheme. The results of the experiments indicate that our proposed scheme successfully achieve the long-term data collection in scenarios of 200 IoT devices working together. This work provides developers useful experiences for creating manufacturing systems of cyber-physical factory automation.