A hybrid neural-genetic approach for reconfigurable scheduling of networked control system

ABSTRACT

In this paper, a novel approach for networked control system (NCS) task scheduling is proposed. The proposed neural-genetic method utilizes the information about the quality of service (QoS) over the communication network and enables online reconfigurable scheduling on distributed environment. In this way the NCS's bandwidth can be shared properly among different parallel control tasks. For NCS, two significant factors of QoS that affect validity of scheduling results are the packet loss and delay, which occurred in the communication among tasks. By adopting a Elman neural network based prediction model, the one-step ahead packet loss and time delay are obtained. The knowledge about the predict QoS factors, combined with the task execution features and the resources available in the system, are used as an entry to improve the decisions of the proposed scheduling algorithm. Such algorithm uses genetic algorithm techniques to find out the appropriate task scheduling scheme to adapt changes of application and communication circumstance. The proposed neural-genetic approach is evaluated through simulation by using a model parameterized with the features obtained from a real scenario of Ethernet based control system. The simulation results clearly show the effectiveness of the proposed approach in solving the task scheduling problems in NCS.

REFERENCES

• 1: Xia Feng, Wang Zhi and Sun You-Xian. 2004. Integrated Computation, Communication and Control: Towards Next Revolution in Information Technology. In Proceedings of 2004 International Conference on Information Technology (Hyderabad, India, Dec, 2004). CIT'04, Springer Press, 3356(2004), 117--125.
• 2: S. H. Hong. 1995 "Scheduling algorithm of data sampling times in the integrated communication and control systems," IEEE Trans. on Control Systems Technology. 3, 6(June, 1995), 225--230.
• 3: S. H. Hong and Y. C. Kim. 2002. "Implementation of a bandwidth allocation scheme in a token-passing fieldbus network", IEEE Trans. on Instrument and Measurement. 51, 2(Apr. 2002), 246--251.
• 4: J. Yepez, P. Marti, and J. M. Fuertes. 2003. Control loop scheduling paradigm in distributed control systems. In Proceedings of the 29th Annual Conference of the IEEE Industrial Electronics Society (Roanoke, USA, Nov. 2003). IECON '03, 1441--1446.
• 5: G. C. Walsh and H. Ye. 2001. Scheduling of networked control systems. IEEE Control Systems Magazine. 21, 1(Feb, 2001), 57--65.
• 6: Kil To Chong and Sung Goo Yoo. 2006. Neural network prediction model for a real-time data transmission. Neural Computing and Application. 15, 3(May, 2006), 373--382.
• 7: B. Ravindran, P. Kachroo, and T. Hegazy. 2001. "Intelligent feedback control based adaptive resource management for asynchronous, decentralized real-time", IEEE Transantion on Systems, Man, and Cybernetics. Part C: Applications and Reviews. 31, 2(May, 2001), 261--265.
• 8: J. Eker, P. Hagander and K.-E. Årzén. 2000. A feedback scheduler for real-time controller tasks. Control Engineering Practice. 8, 12 (2000), 1369--1378.
• 9: Xia Feng, Shen Xingfa, Liu Liping and Sun Youxian. 2005. Fuzzy Logic Based Feedback Scheduler for Embedded Control Systems. In Proceedings of 2005 International Conference on Intelligent Computing(Hefei, China, Aug, 2005). ICIC'05, Springer Press, 3645(2005), 453--462.
• 10: Xia Feng, Li Shanbin and Sun Youxian. 2005. Neural Network-based Feedback Scheduler for Networked Control System with Flexible Workload. In Proceedings of 2005 international conference on advances in natural computation(Changsha, China, August 27--29, 2005). ICNE'05, Springer Press, 3611(2005), 242--251.
• 11: Zhao Wenhong and Xia Feng. 2006. A Neural Network Approach to QoS Management in Networked Control Systems over Ethernet. In Proceedings of 2006 International conference on Intelligent computing(Kunming, China, Aug 16--19, 2006).ICIC'06, Springer Press, 344(2006), 444--449.
• 12: Faucou, S., Deplanche. A.-M and Beauvais, j.-P. 2000. Heuristic techniques for allocating and scheduling communicating periodic tasks in distributed real-time systems. In Proceedingsof 2000 IEEE International Workshop on Factory Communication Systems(Porto, Portugal, Sept 6--8, 2000), 257--265.
• 13: Benitez-Perez, H., Saavedra-Hernandez, H., and Ortega-Arjona, J.L. 2007. On-Line Reconfiguration for a Type of Networked Control System using Genetic Algorithms. WSEAS Transactions On Systems. 6, 1(Jan, 2007), 167--172
• 14: Yang Liman, Li Yunhua and Yuan Haibing. 2004. Analysis of Time Delay in Networked Control Systems and Study of Data Transmission Technology. Control and Decision. 9(2004), 361--382.
• 15: Shi G Y. 1997. A genetic algorithm applied to a classic job shop scheduling problem. International Journal of System Science. 1(1997), 25--32.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Scheduling

General Terms:
Algorithms, Experimentation

Keywords:
genetic scheduling, networked control system, neural prediction