TY - GEN
T1 - Communication scheduling scheme based on big-data regression analysis and genetic algorithm for cyber-physical factory automation
AU - Chen, Chao Chun
AU - Chen, Chao Lieh
AU - Ciou, Che Yang
AU - Liu, Jia Xuan
N1 - Funding Information:
Authors thank Jung-Chung Yeh and Hsin-Ting Shih with Tong-Tai Co. for sharing valuable machining experiences in whole factory, which assist us to create the simulation environment of data collection. This work was supported by Ministry of Science and Technology of Taiwan (R.O.C) and Tong-Tai Machine and Tool Co. under Grants MOST 105-2218-E-006-014, 103-2221-E-006-155, and NCKU B104- 018. This research was also received funding from the Headquarters of University Advancement at the National Cheng Kung University, which is sponsored by the Ministry of Education, Taiwan, R.O.C
Publisher Copyright:
© 2016 IEEE.
PY - 2017/2/6
Y1 - 2017/2/6
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85015778987&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85015778987&partnerID=8YFLogxK
U2 - 10.1109/SMC.2016.7844631
DO - 10.1109/SMC.2016.7844631
M3 - Conference contribution
AN - SCOPUS:85015778987
T3 - 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
SP - 2603
EP - 2608
BT - 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016
Y2 - 9 October 2016 through 12 October 2016
ER -