隨著經濟的成長與發展，能源的消耗量逐年增加。日益增長的能源消耗量造成全球氣候變遷並帶來嚴重災害，因此，高耗能產業如半導體及TFT-LCD等高科技產業，開始重視以全面資源管理增進工廠綜合能源效率。其中，除了製程設備之外，冰水系統為工廠最耗能的設備，其耗電量約佔總耗電量的21%。為了達到綜合能源效益增加以節省能源的目標，如何在不影響製程環境的情況下，使冰水主機調度最佳化並達到節能最優化成為現今關注的議題。
過去冰水主機的調度主要仰賴廠務人員的經驗法則；然而，變動的天氣與複雜的冰水主機組合等不確定性因素造成廠務人員不一致的調度冰水主機決策以及能源的浪費。為了透過全面資源管理優化綜合能源效益，本研究建構一紫式決策分析架構，整合機器學習模型與最佳化數學模型，包括收集冰水主機運轉數據、預測冷凍噸需求之區間估計以及提供冰水主機調度優化決策支援，以達到節省能源之目的。
本研究以臺灣某半導體製造廠進行實證並檢驗模型效度，證實最佳化冰機調度節省4.26%之耗電量。此冰機調度決策支援系統將減少廠務人員在操作冰機上的不確定性，避免不一致的決策，達到冰機調度的最佳化與效率最優化，同時增進全廠綜合能源效率。

With economic growth and development, energy consumption has significantly increased every year. Since the growing problem of electricity consumption is the critical reason for global climate change which has caused worldwide severe disasters, energy-intensive industries focus on the issue of enhancing overall power efficiency. Semiconductor manufacturing is one of the most energy-intensive industries. Except for the production equipment, the chiller system is the major power-consuming equipment which requires around 21% of total electricity usage in the semiconductor factory. In order to achieve the overall energy saving enhancement, optimizing chiller system operations and minimizing chiller power consumption without affecting the environment of wafer production become a crucial issue.
Conventionally, chiller operations greatly rely on engineers’ practical experiences. However, various uncertainties, including changeable weather and complicated chiller combinations, lead to inconsistent decisions of switching chiller machines as well as energy waste. To improve the overall energy-saving performance based on total resource management, this research developed a UNISON decision framework to minimize the electricity consumption for air-conditioning system including collecting operation parameters of chillers, predicting chiller cooling load demand and developing an optimal chiller adjustment decision under uncertainty of interval estimation of cooling load demand. An empirical study was conducted in a semiconductor fab and validate the proposed approach with 4.26% energy conservation.

Content i
List of Tables iii
List of Figures iv
Chapter 1 Introduction 1
1.1 Research Background 1
1.2 Research Motivation 1
1.3 Research Objectives 2
1.4 Thesis Organization 2
Chapter 2 Literature Review 3
2.1 The Air-Conditioning System 3
2.2 Energy Saving for Air-Conditioning System 5
2.2.1 Cooling Load Forecasting 5
2.2.2 Chiller Operation Optimization 6
2.3 Time Series Model 8
2.4 Overall Power Energy Effectiveness (OPE) 9
Chapter 3 Research Framework 11
3.1 Understand and Define Problem 12
3.2 Identify the Niche for Decision Quality Improvement 12
3.3 Structure the Objective Hierarchy and Influence Relation 13
3.3.1 Data Preparation 13
3.3.2 Cooling Load Model with Interval Estimation 15
3.3.3 Chiller Operation Optimization 16
3.4 Sense and Describe Expected Outcomes 20
3.5 Overall Judgements and Value Assessments 20
3.6 Tradeoff and Decision 21
Chapter 4 Empirical Study 22
4.1 Understand and Define Problem 22
4.2 Identify the Niche for Decision Quality Improvement 23
4.3 Structure the Objective Hierarchy and Influence Relation 24
4.3.1 Data Preparation 24
4.3.2 Cooling Load Model with Interval Estimation 29
4.3.3 Chiller Operation Optimization 31
4.4 Sense and Describe Expected Outcomes 35
4.5 Overall Judgements and Value Assessments 38
4.6 Tradeoff and Decision 39
Chapter 5 Conclusion 43
5.1 Summary and Contribution 43
5.2 Future Research 44
Acknowledgements 45
References 45

Bakar, N. N. A., Hassan, M. Y., Abdullah, H., Rahman, H. A., Abdullah, M. P., Hussin, F., and Bandi, M. (2015), "Energy efficiency index as an indicator for measuring building energy performance: A review," Renewable and Sustainable Energy Reviews, Vol. 44, No., pp. 1-11.
Beal, L. D., Hill, D. C., Martin, R. A., and Hedengren, J. D. (2018), "Gekko optimization suite," Processes, Vol. 6, No. 8, pp. 106.
Box, G. E. and Jenkins, G. M. (1970), "Time series analysis: Forecasting and control Holden-Day," San Francisco, Vol., No., pp. 498.
Chen, C.-L., Chang, Y.-C., and Chan, T.-S. (2014), "Applying smart models for energy saving in optimal chiller loading," Energy and Buildings, Vol. 68, No., pp. 364-371.
Chien, C.-F. (2005), "Decision analysis and management: A unison framework for total decision quality enhancement," Yeh-Yeh Book Gallery, Taipei, Taiwan, Vol., No., pp.
Chien, C.-F., Chen, H.-K., Wu, J.-Z., and Hu, C.-H. (2007), "Constructing the OGE for promoting tool group productivity in semiconductor manufacturing," International Journal of Production Research, Vol. 45, No. 3, pp. 509-524.
Chien, C.-F., Chu, P.-C., and Zhao, L. (2015), "Overall resource effectiveness (ORE) indices for total resource management and case studies," International Journal of Industrial Engineering, Vol. 22, No. 5, pp.
Chien, C.-F., Diaz, A. C., and Lan, Y.-B. (2014), "A data mining approach for analyzing semiconductor MES and FDC data to enhance overall usage effectiveness (OUE)," International Journal of Computational Intelligence Systems, Vol. 7, No. sup2, pp. 52-65.
Chien, C.-F., Hsu, C.-Y., and Chang, K.-H. (2013a), "Overall wafer effectiveness (OWE): A novel industry standard for semiconductor ecosystem as a whole," Computers and Industrial Engineering, Vol. 65, No. 1, pp. 117-127.
Chien, C.-F., Hsu, C.-Y., and Chang, K.-H. (2013b), "Overall wafer effectiveness (OWE): A novel industry standard for semiconductor ecosystem as a whole," Computers & Industrial Engineering, Vol. 65, No. 1, pp. 117-127.
Chien, C.-F., Hu, C.-H., and Hu, Y.-F. (2016a), "Overall space effectiveness (OSE) for enhancing fab space productivity," IEEE Transactions on Semiconductor Manufacturing, Vol. 29, No. 3, pp. 239-247.
Chien, C.-F., Peng, J.-T., and Yu, H.-C. (2016b), "Building energy saving performance indices for cleaner semiconductor manufacturing and an empirical study," Computers and Industrial Engineering, Vol. 99, No., pp. 448-457.
Chien, C.-F. and Wu, J.-Z. (2003), "Analyzing repair decisions in the site imbalance problem of semiconductor test machines," IEEE Transactions on Semiconductor Manufacturing, Vol. 16, No. 4, pp. 704-711.
Ding, Y., Zhang, Q., and Yuan, T. (2017), "Research on short-term and ultra-short-term cooling load prediction models for office buildings," Energy and Buildings, Vol. 154, No., pp. 254-267.
dos Santos Coelho, L. and Mariani, V. C. (2013), "Improved firefly algorithm approach applied to chiller loading for energy conservation," Energy and Buildings, Vol. 59, No., pp. 273-278.
Durbin, J. (1960), "Estimation of parameters in time‐series regression models," Journal of the Royal Statistical Society: Series B, Vol. 22, No. 1, pp. 139-153.
Fan, C., Xiao, F., and Zhao, Y. (2017), "A short-term building cooling load prediction method using deep learning algorithms," Applied energy, Vol. 195, No., pp. 222-233.
Fu, W. and Chien, C.-F. (2019), "UNISON data-driven intermittent demand forecast framework to empower supply chain resilience and an empirical study in electronics distribution," Computers & Industrial Engineering, Vol. 135, No., pp. 940-949.
Gang, W., Wang, S., Yan, C., and Xiao, F. (2015), "Robust optimal design of building cooling systems concerning uncertainties using mini-max regret theory," Science and Technology for the Built Environment, Vol. 21, No. 6, pp. 789-799.
Guo, Y., Nazarian, E., Ko, J., and Rajurkar, K. (2014), "Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression," Energy Conversion and Management, Vol. 80, No., pp. 46-53.
Hu, Y.-F., Hou, J.-L., and Chien, C.-F. (2019), "A UNISON framework for knowledge management of university–industry collaboration and an illustration," Computers & Industrial Engineering, Vol. 129, No., pp. 31-43.
Krzywanski, J., Grabowska, K., Herman, F., Pyrka, P., Sosnowski, M., Prauzner, T., and Nowak, W. (2017), "Optimization of a three-bed adsorption chiller by genetic algorithms and neural networks," Energy Conversion and Management, Vol. 153, No., pp. 313-322.
Lin, K.-Y., Chien, C.-F., and Kerh, R. (2016), "UNISON framework of data-driven innovation for extracting user experience of product design of wearable devices," Computers & Industrial Engineering, Vol. 99, No., pp. 487-502.
Lin, Y.-H., Chien, C.-F., and Yu, C.-M. (2015), "UNISON decision analysis framework for workforce planning for semiconductor fabs and an empirical study," International Journal of Industrial Engineering, Vol. 22, No. 5, pp.
Lu, L., Cai, W., Xie, L., Li, S., and Soh, Y. C. (2005), "HVAC system optimization—in-building section," Energy and Buildings, Vol. 37, No. 1, pp. 11-22.
May, G., Barletta, I., Stahl, B., and Taisch, M. (2015), "Energy management in production: A novel method to develop key performance indicators for improving energy efficiency," Applied Energy, Vol. 149, No., pp. 46-61.
Nakajima, S. (1988), "Introduction to TPM: total productive maintenance.(Translation)," Productivity Press, Inc., 1988, Vol., No., pp. 129.
SEMI (2000). Standard for definition and measurement of equipment productivity, Semiconductor Equipment and Material International Mt. View, CA.
Vu, H. D., Chai, K. S., Keating, B., Tursynbek, N., Xu, B., Yang, K., Yang, X., and Zhang, Z. (2017), "Data driven chiller plant energy optimization with domain knowledge," Proceedings of Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.
Walker, A. M. (1962), "Large-sample estimation of parameters for autoregressive processes with moving-average residuals," Biometrika, Vol. 49, No. 1/2, pp. 117-131.
Wu, J.-Z. and Chien, C.-F. (2008), "Modeling strategic semiconductor assembly outsourcing decisions based on empirical settings," OR spectrum, Vol. 30, No. 3, pp. 401-430.
Wudhikarn, R., Smithikul, C., and Manopiniwes, W. (2010), "Developing overall equipment cost loss indicator," Proceedings of Proceedings of the 6th CIRP-Sponsored International Conference on Digital Enterprise Technology.
Yao, Y. and Chen, J. (2010), "Global optimization of a central air-conditioning system using decomposition–coordination method," Energy and Buildings, Vol. 42, No. 5, pp. 570-583.
Yu, C.-M., Chien, C.-F., and Kuo, C.-J. (2017), "Exploit the value of production data to discover opportunities for saving power consumption of production tools," IEEE Transactions on Semiconductor Manufacturing, Vol. 30, No. 4, pp. 345-350.
Yun, K., Cho, H., Luck, R., and Mago, P. (2011), "Real-time combined heat and power operational strategy using a hierarchical optimization algorithm," Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, Vol. 225, No. 4, pp. 403-412.
Zheng, Z.-x. and Li, J.-q. (2018), "Optimal chiller loading by improved invasive weed optimization algorithm for reducing energy consumption," Energy and Buildings, Vol. 161, No., pp. 80-88.