因應全球減少二氧化碳排放與能源轉型的風潮，各國政府和能源業者開始積極採取行動。近年來政府制定相應的政策和法規，以鼓勵再生能源的使用，限制化石燃料的排放，並推動能源效率的提升。隨著投資者和企業紛紛加大對再生能源和電能管理控制技術的投資，逐漸減少對化石能源的依賴。
本文因應全球減碳趨勢，考慮汽電共生廠用電與用汽負載、各機組發電成本及相應燃料之碳排放，對碳排放行為進行收費以驅使系統進行較低碳排放的操作策略，透過汽電共生廠調度中心的角度設計汽、電負載預測系統與汽電共生調度決策系統。汽、電負載預測系統應用工廠生產排程與相似日負載曲線和過去歷史資料作為特徵，輸入集成學習模型進行日前與即時滾動之汽、電負載曲線預測。所提汽電共生調度決策系統使用上述預測系統之結果進行最佳化排程，並以自用發電設備型式參與輔助服務市場，使用蒸汽流量與電功率作為能源架構，滿足汽、電負載之需求下，決策出各發電機組之日前投標策略，以達到最小化整體系統操作成本的目的。
本文所提之汽、電負載預測系統的預測誤差比其他的模型預測誤差更低，進而使調度系統能降低更多因不確定性產生的風險。除此之外，提出的相似日負載曲線也改善預測結果。本文以非夏月與夏月汽電共生實際運轉資料調度模擬分析，其中分別比較本文方法與其他排程方法於輔助服務市場投標、調度及成本效益結果，顯示本文方法的表現皆優於其他方法，並具有於實際系統應用價值。

In response to the global trend of reducing carbon dioxide emissions and energy transformation, governments and energy companies have begun to take proactive actions. In recent years, governments have formulated policies and regulations to encourage the use of renewable energy, limit fossil fuel emissions, and promote energy efficiency. As investors and corporations increase their investments in renewable energy and power management and control technologies, they are gradually reducing their reliance on fossil fuels.
In this study, in response to the global trend of carbon reduction, a steam and electric load prediction system and a steam and electric dispatch decision system are designed from the perspective of the dispatch center of a combined heat and power plant (CHP), taking into account the steam and electric loads, the cost of power generation of each unit, and the carbon emissions of the corresponding fuels, and charging the carbon emission behaviors to drive the system to carry out the operation strategy of lower carbon emissions. The steam and electric load forecasting system is characterized by plant production schedules, similar daily load profiles and historical data, and inputs integrated learning models to forecast the steam and electric load profiles in the day-ahead and real-time. The proposed CHP scheduling system uses the results of the above prediction system to optimize scheduling and participates in the auxiliary service market with its own generating equipment, using steam flow and electric power as the energy structure to satisfy the demand of steam and electric loads, and decides on the day-ahead bidding strategy for each generating unit to minimize the overall system operating costs.
The prediction error of the proposed steam and electric load prediction system is lower than the other models, which in turn enables the dispatching system to reduce more risks due to uncertainty. In addition, the proposed similar daily load profiles also improve the prediction results. In this study, the simulation analysis is based on the actual operation data of CHP in non-summer months and summer months, and the results of bidding, scheduling, and cost-effectiveness of this proposed method and other scheduling methods in the auxiliary service market are compared respectively, which show that the proposed method outperforms the other methods, and it has the value of being applied to real systems.

[1] 經濟部，能源轉型白皮書，2020年11月。
[2] Y. Zhang, V. Cheng, D. S. Mallapragada, J. Song, and G. He, “A Model-Adaptive Clustering-Based Time Aggregation Method for Low-Carbon Energy System Optimization,” IEEE Transactions on Sustainable Energy, vol. 14, no. 1, pp. 55–64, Jan. 2023.
[3] R. H. Byrne, T. A. Nguyen, D. A. Copp, B. R. Chalamala, and I. Gyuk, “Energy Management and Optimization Methods for Grid Energy Storage Systems,” IEEE Access, vol. 6, pp. 13231–13260, Mar. 2018.
[4] 電力交易平台參考資料，輔助服務概論，2023年8月。
[5] 電力交易平台參考資料，日前輔助服務市場之參與作法，2023年8月。
[6] 電力交易平台參考資料，日前輔助服務市場之交易商品項目規格，2023年8月。
[7] 工業技術研究院，汽電共生系統節能手冊，2008年6月。
[8] Y. Yan, C. Huang, J. Guan, Q. Zhang, Y. Cai, and W. Wang, “Stochastic Optimization of Solar-Based Distributed Energy System: An Error-Based Scenario with a Day-Ahead and Real-Time Dynamic Scheduling Approach,” Applied Energy, vol. 363, p. 123099, Jun. 2024.
[9] J. Yuan, W. Gang, F. Xiao, C. Zhang, and Y. Zhang, “Two-Level Collaborative Demand-Side Management for Regional Distributed Energy System Considering Carbon Emission Quotas,” Journal of Cleaner Production, vol. 434, p. 140095, Jan. 2024.
[10] Y. Jin, Z. Wang, C. Jiang, and Y. Zhang, “Dispatch and Bidding Strategy of Active Distribution Network in Energy and Ancillary Services Market,” Journal of Modern Power Systems and Clean Energy, vol. 3, no. 4, pp. 565–572, Dec. 2015.
[11] A. M. Muqbel, A. T. Al-Awami, and A. S. Al-Bukhaytan, “A Planning Model for an Electric Vehicle Aggregator Providing Ancillary Services to an Unbalanced Distribution Network Considering Contract Design,” IEEE Access, vol. 12, pp. 29035–29048, Feb. 2024.
[12] S. Hadayeghparast, A. SoltaniNejad Farsangi, and H. Shayanfar, “Day-Ahead Stochastic Multi-Objective Economic/Emission Operational Scheduling of a Large Scale Virtual Power Plant,” Energy, vol. 172, pp. 630–646, Apr. 2019.
[13] A. Tavakoli, A. Karimi, and M. Shafie-Khah, “Linearized Stochastic Optimization Framework for Day-Ahead Scheduling of a Biogas-Based Energy Hub Under Uncertainty,” IEEE Access, vol. 9, pp. 136045–136059, Sep. 2021.
[14] Z. Zhang, F. M. A. Altalbawy, M. Al-Bahrani, and Y. Riadi, “Regret-Based Multi-Objective Optimization of Carbon Capture Facility in CHP-Based Microgrid with Carbon Dioxide Cycling,” Journal of Cleaner Production, vol. 384, p. 135632, Jan. 2023.
[15] P. Firouzmakan, R.-A. Hooshmand, M. Bornapour, and A. Khodabakhshian, “A Comprehensive Stochastic Energy Management System of Micro-CHP Units, Renewable Energy Sources and Storage Systems in Microgrids Considering Demand Response Programs,” Renewable and Sustainable Energy Reviews, vol. 108, pp. 355–368, Jul. 2019.
[16] A. Baringo and L. Baringo, “A Stochastic Adaptive Robust Optimization Approach for the Offering Strategy of a Virtual Power Plant,” IEEE Transactions on Power Systems, vol. 32, no. 5, pp. 3492–3504, Sep. 2017.
[17] A. Martinez-Mares and C. R. Fuerte-Esquivel, “A Robust Optimization Approach for the Interdependency Analysis of Integrated Energy Systems Considering Wind Power Uncertainty,” IEEE Transactions on Power Systems, vol. 28, no. 4, pp. 3964–3976, Jan. 2013.
[18] F. Verástegui, Á. Lorca, D. E. Olivares, M. Negrete-Pincetic, and P. Gazmuri, “An Adaptive Robust Optimization Model for Power Systems Planning with Operational Uncertainty,” IEEE Transactions on Power Systems, vol. 34, no. 6, pp. 4606–4616, Jan. 2019.
[19] Z. Hu and D. He, “Operation Scheduling Optimization of Gas–Steam–Power Conversion Systems in Iron and Steel Enterprises,” Applied Thermal Engineering, vol. 206, p. 118121, Apr. 2022.
[20] T. Xu, Z. Huo, T. Wang, J. Lv, Y. Han, and L. Mu, “Multi-Objective Optimization of Gas-Steam-Power System for an Integrated Iron and Steel Mill Considering Carbon Emission Reduction and Cost,” Journal of Cleaner Production, vol. 429, p. 139404, Dec. 2023.
[21] W. Zhuang, S. Zhou, J. Chen, and W. Gu, “Operation Optimization of Electricity-Steam Coupled Industrial Energy System Considering Steam Accumulator,” Energy, vol. 289, p. 129903, Feb. 2024.
[22] T. Xu, T. Li, J. Long, L. Zhao, and W. Du, “Data-Driven Multi-Period Modeling and Optimization for the Industrial Steam System of Large-Scale Refineries,” Chemical Engineering Science, vol. 282, p. 119112, Dec. 2023.
[23] P. Mandal, T. Senjyu, N. Urasaki, and T. Funabashi, “A Neural Network Based Several-Hour-Ahead Electric Load Forecasting Using Similar Days Approach,” International Journal of Electrical Power & Energy Systems, vol. 28, no. 6, pp. 367–373, Jul. 2006.
[24] S. Wang, X. Wang, S. Wang, and D. Wang, “Bi-Directional Long Short-Term Memory Method Based on Attention Mechanism and Rolling Update for Short-Term Load Forecasting,” International Journal of Electrical Power & Energy Systems, vol. 109, pp. 470–479, Jul. 2019.
[25] Z. Zhu et al., “A Day-Ahead Industrial Load Forecasting Model Using Load Change Rate Features and Combining FA-ELM and the AdaBoost Algorithm,” Energy Reports, vol. 9, pp. 971–981, Dec. 2023.
[26] 台灣電力股份有限公司，電價表，2024年3月。
[27] 台灣電力股份有限公司，特高壓用戶申請用電專區 - 業務專區 - 業務公告，[Online]. Available: https://www.taipower.com.tw/tc/page.aspx?mid=351 [Accessed 8 May 2024].
[28] M. Alipour, K. Zare, and M. Abapour, “MINLP Probabilistic Scheduling Model for Demand Response Programs Integrated Energy Hubs,” IEEE Transactions on Industrial Informatics, vol. 14, no. 1, pp. 79–88, Jan. 2018.
[29] M. Mazidi, N. Rezaei, and A. Ghaderi, “Simultaneous Power and Heat Scheduling of Microgrids Considering Operational Uncertainties: A New Stochastic P-Robust Optimization Approach,” Energy, vol. 185, pp. 239–253, Oct. 2019.
[30] X. Xiao, H. Mo, Y. Zhang, and G. Shan, “Meta-ANN – A Dynamic Artificial Neural Network Refined by Meta-Learning for Short-Term Load Forecasting,” Energy, vol. 246, p. 123418, May 2022.
[31] D. Li, G. Sun, S. Miao, Y. Gu, Y. Zhang, and S. He, “A Short-Term Electric Load Forecast Method Based on Improved Sequence-to-Sequence GRU with Adaptive Temporal Dependence,” International Journal of Electrical Power & Energy Systems, vol. 137, p. 107627, May 2022.
[32] R. J. Hyndman and A. B. Koehler, “Another Look at Measures of Forecast Accuracy,” International Journal of Forecasting, vol. 22, no. 4, pp. 679–688, Oct. 2006.
[33] S. Wang, J. Zhao, C. Shao, C. Dong, and C. Yin, “Truck Traffic Flow Prediction Based on LSTM and GRU Methods with Sampled GPS Data,” IEEE Access, vol. 8, pp. 208158–208169, Nov. 2020.
[34] 台灣電力股份有限公司，日前輔助服務市場 - 歷史結清價格與交易量，[Online]. Available: https://etp.taipower.com.tw/web/service_market/historical_settlement_trading [Accessed 8 May 2024].
[35] X. Li et al., “Operation Optimization for Integrated Energy System Based on Hybrid CSP-CHP Considering Power-to-Gas Technology and Carbon Capture System,” Journal of Cleaner Production, vol. 391, p. 136119, Mar. 2023.
[36] T. Xu, T. Li, J. Long, L. Zhao, and W. Du, “Data-Driven Multi-Period Modeling and Optimization for the Industrial Steam System of Large-Scale Refineries,” Chemical Engineering Science, vol. 282, p. 119112, Dec. 2023.
[37] B. Zhang, Q. Li, L. Wang, and W. Feng, “Robust Optimization for Energy Transactions in Multi-Microgrids under Uncertainty,” Applied Energy, vol. 217, pp. 346–360, May 2018.
[38] C. Wang, Y. Zhou, B. Jiao, Y. Wang, W. Liu, and D. Wang, “Robust Optimization for Load Scheduling of a Smart Home with Photovoltaic System,” Energy Conversion and Management, vol. 102, pp. 247–257, Sep. 2015.