能源供應問題，已成為世界各國政府所關注的焦點。 我們可以在各大報章雜誌上看到類似“原油開採已接近尾聲”、 “天然氣供應短缺”等的標題。人類歷史上, 不管是人為或自然因素造成的核能危機，使得人們對核能供電望之卻步。在更好的替代能源被開發出來之前，節省能源是我們可以選擇的一個選項。
近年來，網宇實體系統被廣泛應用在各個領域上，包括自動化系統、製造業、網路化樓宇控制系統、大眾交通運輸、醫療保健等。網宇實體系統提升了人類的生活品質，也幫助人們達成以前難以完成的目標。與此同時，它所帶來的能量消耗也是相當可觀的。本研究之目的在於提出一套方法適用於網宇實體系統，使得系統整體的能量消耗能夠降低的同時，我們的需求仍然能夠得到滿足。
本研究主要採用基因演算法來安排網宇實體系統裡操作設備的運作排程。我們希望經由對本網宇實體系統裡操作設備之特性的了解，如:操作設備的能力以及能量消耗量，安排出一套排程來讓操作設備相互合作，以達成共同之目標。除了把回饋觀念納入到本研究方法外，本研究也把環境的變化因子考慮進來。本研究另外把世代的觀念引進了將要實作的網宇實體系統中。透過兩組感測器分別監測到的系統運作後之輸出值以及實際環境變化值，將會在計算下一個世代的排程時被加以利用。

In recent years, more and more energy problems are discussed and reported. Headlines such as “crude-oil production is winding down”, “natural gas is in scarce supply” can be seen on major newspapers and magazines from time to time. Nuclear crisis that might be caused by natural disasters such as tsunami, earthquake deterred people from keeping nuclear energy plant. Energy supply becomes one of the most important issues that we need to deal with. Before any meaningful alternative energy supply is discovered, saving energy seems to be a good way.
In this paper, we proposed a genetic algorithm based method by which electrical operators in a cyber physical system could be scheduled and controlled. We considered not only the output of the processes but also the environmental variation into our method. We suppose that the electrical operators are of the same type but with different capabilities. One set of sensors would be placed dispersedly around the to-be-affected area to measure the output of the processes. Another set of sensors collects the environmental variation value for prediction. As we can see in the simulation result, by applying our proposed GA-based Actuators Controlling (GAAC) method in a cyber physical system that we described above, the power consumption of the system could be minimized while the desire set point can still be accomplished.

[ 1 ] Andrei, Neculai, “Modern Control Theory - A historical Perspective”. Retrieved 2007-10-10.
[ 2 ] H. Aytug, G.J. Koehler, “New Stopping criteria for genetic algorithms”, European Journal of Operational Research, issue. 3, vol. 126, pp. 662-674.
[ 3 ] H. Aytug, G.J. Koehler, “Stopping criteria for finite length genetic algorithms”, Information Journal on Computing, no. 2, vol. 8, pp. 183-191, 1996.
[ 4 ] J. W. Branch, L. Chen, B. K. Szymanski, "A Middleware Framework for Market-Based Actuator Coordination in Sensor and Actuator Networks", International Conference on Pervasive Services, pp. 101-110, 2008.
[ 5 ] L. Davis, “Genetic Algorithms and Simulated Annealing”, London: Pitman, 1987.
[ 6 ] K. A. DeJong, “Genetic algorithms: A 10 year perspective”, International Conference of Genetic Algorithms and their Applications, pp. 169-177, 1985.
[ 7 ] Bin. Feng, Guofang. Gong, Huayong. Yang, “Self-tuning-parameter fuzzy PID temperature control in a large hydraulic system”, Advanced Intelligent Mechatronics, pp 1418-1422, 2009.
[ 8 ] D. E. Goldberg, K. Deb, and B. Korb, “Messy genetic algorithms revisited: Studies in mixed size and scale,” Complex Systems, vol. 4, pp. 415-444 , 1990.
[ 9 ] D. E. Goldberg, “Genetic Algorithms in Search, Optimization and Machine Learning” Reading, Addison Wesley, 1989.
[ 10 ] H. R. Hall, “Governors and governing mechanisms”, The Technical Publishing Co., Manchester, 2nd Ed., 1907.
[ 11 ] J. H. Holland, “Adaptation in Natural and Artificial Systems”, University of Michigan Press, Ann Arbor, 1975.
[ 12 ] T. H. S. Li, S. J. Chang, and W. Tong, “Fuzzy target tracking control of autonomous mobile robots by using infrared sensors”, Fuzzy System, no. 4, vol. 12, pp. 491-501, 2004.
[ 13 ] M. Mitchell, S. Forrest and J.H. Holland, “The royal road for genetic algorithms: Fitness landscapes and GA performance”, Artificial Life, MIT Press, Cambridge, pp. 245–254, 1992.
[ 14 ] Robert A. Monzingo, Thomas W. Miller, “Introduction to Adaptive Arrays”, John Wiley & Sons, 1980.
[ 15 ] A. Nix, M. D. Vose, “Modeling genetic algorithms with Markov chains”, Annals of Mathematics and Artificial Intelligence”, vol. 5, pp. 79-88, 1992.
[ 16 ] R. R. Sharapov, A. V. Lapshin, “Convergence of genetic algorithms”, no. 3, vol. 16, pp. 392-397, 2006.
[ 17 ] J. Stankovic, C. Lu, S. Son, and G. Tao, “The case for feedback control real-time scheduling”, Real-Time systems, pp. 11-20, 1999.
[ 18 ] F. Xia, Y. Sun, Y. C. Tian, "Feedback scheduling of priority-driven control networks", Computer Standards & Interfaces, issue. 3, vol. 31, pp. 539-547, March 2009.
[ 19 ] T P. Xiaohong, M. Zhi, X. LaiSheng, “Research and Application on GA-based Two-stage Fuzzy Temperature Control System for a Type of Industrial Furnace”, Electrical and Control Engineering, pp.1558-1561, 2010.