電力供需之預測有助於強化電力資源之規畫與管理，是維持現今社會運作的重要一環，而備轉電力(operating reserve power)可確保電力系統的可靠性及穩定性，並減少停電風險，是提高能源系統韌性的重要元件。本研究透過台灣電力公司之電力交易平台資料，以日前輔助服務市場的三種備轉容量之交易資料為標的，建構一個以基於時頻的圖神經網路(spectral temporal graph neural network, StemGNN)的多元時間序列深度學習模型，透過此模型同時預測三種備轉電力之需求，此模型能夠同時考量單一時間序列內之時間相依性、多個時間序列間之空間相依性，補足單變量時間序列預測未考量各時間序列相互依賴之不足。研究中亦透過與傳統時間序列析常用之差分整合移動平均自迴歸(autoregressive integrated moving average, ARIMA)模型與季節性差分整合移動自迴歸(seasonal autoregressive integrated moving average, SARIMA)模型進行預測準確度比較，以驗證基於時頻的圖神經網路在預測建模之有效性。研究結果顯示，在預測期較短的情況下，SARIMA模型已經能夠充分進行預測，但若要進行較長期的預測，可藉由本研究建構之多元時間序列預測模型，獲得更準確的預測結果。本研究之分析框架可提供日前輔助服務市場供需雙方作為決策評估之參考，以進行備轉電力需求的規劃與管理。

Forecasting power supply and demand contributes to the planning and management of power resources, which is essential for maintaining the functioning of today’s society. Operating reserve power ensures the reliability and stability of the power system and reduces the risk of blackouts, making it an important component for enhancing the resilience of the energy system. In this study, a multivariate time series deep learning model is constructed using a spectral temporal graph neural network (StemGNN), based on transaction data of three types of reserve capacity from Taiwan Power Company’s trading platform. This model simultaneously predicts the demand for the three types of reserve power, considering the temporal dependence within each individual time series and the spatial dependence among multiple time series. It addresses the limitations of univariate time series prediction that neglects the interdependencies among multiple time series. The study also compares the forecasting accuracy of the StemGNN model with traditional time series analysis models such as autoregressive integrated moving average (ARIMA) and seasonal autoregressive integrated moving average (SARIMA) to validate its effectiveness. The results show that the SARIMA model can sufficiently predict for a short forecast period, while the multivariate time series forecasting model developed in this study can obtain more accurate forecasting results for a longer forecast period. The analytical framework of this study provides valuable decision-making support for both the supply and demand sides in the day-ahead operating reserve service market, facilitating the planning and management of power demand.

英文文獻
Abderrezak, L., Mourad, M., & Djalel, D. (2014). Very short-term electricity demand forecasting using adaptive exponential smoothing methods. In Proceedings of the 2014 15th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), Hammamet, Tunisia.
Al Amin, M. A., & Hoque, M. A. (2019). Comparison of ARIMA and SVM for short-term load forecasting. In Proceedings of the 2019 9th annual information technology, electromechanical engineering and microelectronics conference (IEMECON), Shillong, India.
Al-Musaylh, M. S., Deo, R. C., Adamowski, J. F., & Li, Y. (2019). Short-term electricity demand forecasting using machine learning methods enriched with ground-based climate and ECMWF Reanalysis atmospheric predictors in southeast Queensland, Australia. Renewable and Sustainable Energy Reviews, 113, 109293.
Amina, M., & Kodogiannis, V. S. (2011). Load forecasting using fuzzy wavelet neural networks. In Proceedings of the 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), Taipei, Taiwan.
Aneiros, G., Vilar, J., & Raña, P. (2016). Short-term forecast of daily curves of electricity demand and price. International Journal of Electrical Power & Energy Systems, 80, 96-108
Atabay, F. V., Pagkalinawan, R. M., Pajarillo, S. D., Villanueva, A. R., & Taylar, J. V. (2022). Multivariate Time Series Forecasting using ARIMAX, SARIMAX, and RNN-based Deep Learning Models on Electricity Consumption. In Proceedings of the 2022 3rd International Informatics and Software Engineering Conference (IISEC), Ankara, Turkey.
Bao, M., Ding, Y., Zhou, X., Guo, C., & Shao, C. (2021). Risk assessment and management of electricity markets: A review with suggestions. CSEE Journal of Power and Energy Systems, 7(6), 1322-1333.
Box, G.E.P. and Jenkins, G.M. (1970) Time Series Analysis: Forecasting and Control, Holden Day, San Francisco.
Box, G. E., Jenkins, G. M., & Reinsel, G. C. (2015). Time series analysis: forecasting and control (4th ed.). John Wiley & Sons.
Cao, D., Wang, Y., Duan, J., Zhang, C., Zhu, X., Huang, C., Tong, Y., Xu, B., Bai, J., Tong, J., & Zhang, Q. (2020). Spectral temporal graph neural network for multivariate time-series forecasting. Advances in neural information processing systems, 33, 17766-17778.
Chapagain, K., & Kittipiyakul, S. (2018). Short-term electricity demand forecasting with seasonal and interactions of variables for thailand. In Proceedings of the 2018 International Electrical Engineering Congress (iEECON), Krabi, Thailand.
Chatfield, C. (1996) The Analysis of Time Series: An Introduction (6th ed.), Chapman and Hall, New York.
Dehalwar, V., Kalam, A., Kolhe, M. L., & Zayegh, A. (2016). Electricity load forecasting for Urban area using weather forecast information. In the Proceedings of the 2016 IEEE International Conference on Power and Renewable Energy (ICPRE) (pp. 355-359), Shanghai, China.
Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American statistical association, 74(366a), 427-431.
Elamin, N., & Fukushige, M. (2018). Modeling and forecasting hourly electricity demand by SARIMAX with interactions. Energy, 165, 257-268.
Erdogdu, E. (2007). Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey. Energy policy, 35(2), 1129-1146.
Garcia-Ascanio, C., & Maté, C. (2010). Electric power demand forecasting using interval time series: A comparison between VAR and iMLP. Energy Policy, 38(2), 715-725.
Gonzalez-Romera, E., Jaramillo-Moran, M. A., & Carmona-Fernandez, D. (2006). Monthly electric energy demand forecasting based on trend extraction. IEEE Transactions on power systems, 21(4), 1946-1953.
Goswami, K., & Kandali, A. B. (2020). Electricity demand prediction using data driven forecasting scheme: ARIMA and SARIMA for real-time load data of Assam. In Proceedings of the 2020 International Conference on Computational Performance Evaluation (ComPE), Shillong, India.
Hamzaçebi, C., Es, H. A., & Çakmak, R. (2019). Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network. Neural Computing and Applications, 31, 2217-2231.
Hong, T., Gui, M., Baran, M. E., & Willis, H. L. (2010). Modeling and forecasting hourly electric load by multiple linear regression with interactions. In Proceedings of IEEE PES General Meeting, Minneapolis, MN, USA.
Huang, J., Xue, Y., Dong, Z. Y., & Wong, K. P. (2012). An efficient probabilistic assessment method for electricity market risk management. IEEE Transactions on Power Systems, 27(3), 1485-1493.
Hyndman, R. J., & Khandakar, Y. (2008). Automatic time series forecasting: the forecast package for R. Journal of statistical software, 27, 1-22.
Hyndman, R. J., & Fan, S. (2009). Density forecasting for long-term peak electricity demand. IEEE Transactions on Power Systems, 25(2), 1142-1153.
Jamil, R. (2020). Hydroelectricity consumption forecast for Pakistan using ARIMA modeling and supply-demand analysis for the year 2030. Renewable Energy, 154, 1-10.
Kale, R. V., & Pohekar, S. D. (2014). Electricity demand and supply scenarios for Maharashtra (India) for 2030: An application of long range energy alternatives planning. Energy Policy, 72, 1-13.
Kaytez, F., Taplamacioglu, M. C., Cam, E., & Hardalac, F. (2015). Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines. International Journal of Electrical Power & Energy Systems, 67, 431-438.
Khanna, M., & Rao, N. D. (2009). Supply and demand of electricity in the developing world. Annu. Rev. Resour. Econ., 1(1), 567-596.
Kumru, M. & Kumru, P.Y. (2015). Calendar-based short-term forecasting of daily average electricity demand. In Proceedings of the 2015 International Conference on Industrial Engineering and Operations Management (IEOM), Dubai.
Lebotsa, M. E., Sigauke, C., Bere, A., Fildes, R., & Boylan, J. E. (2018). Short term electricity demand forecasting using partially linear additive quantile regression with an application to the unit commitment problem. Applied Energy, 222, 104-118.
Liu, M., & Wu, F. F. (2007). Risk management in a competitive electricity market. International Journal of Electrical Power & Energy Systems, 29(9), 690-697.
Liu, X., & Lin, Z. (2021). Impact of COVID-19 pandemic on electricity demand in the UK based on multivariate time series forecasting with bidirectional long short term memory. Energy, 227, 120455.
Mamun, M. A., & Nagasaka, K. (2004). Artificial neural networks applied to long-term electricity demand forecasting. In Proceedings of the Fourth International Conference on Hybrid Intelligent Systems (HIS'04), Kitakyushu, Japan.
McSharry, P. E., Bouwman, S., & Bloemhof, G. (2005). Probabilistic forecasts of the magnitude and timing of peak electricity demand. IEEE Transactions on Power Systems, 20(2), 1166-1172.
Mirasgedis, S., Sarafidis, Y., Georgopoulou, E., Lalas, D. P., Moschovits, M., Karagiannis, F., & Papakonstantinou, D. (2006). Models for mid-term electricity demand forecasting incorporating weather influences. Energy, 31(2-3), 208-227.
Narajewski, M., & Ziel, F. (2022). Optimal bidding in hourly and quarter-hourly electricity price auctions: Trading large volumes of power with market impact and transaction costs. Energy Economics, 110, 105974.
Perera, S., Dissanayake, S., Fernando, D., De Silva, S., & Rankothge, W. (2019). Supply and demand planning of electricity power: a comprehensive solution. In the Proceedings of the 2019 IEEE Conference on Information and Communication Technology, Allahabad, India.
Ranaweera, D. K., Karady, G. G., & Farmer, R. G. (1997). Economic impact analysis of load forecasting. IEEE Transactions on Power Systems, 12(3), 1388-1392.
Said, S. E., & Dickey, D. A. (1984). Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika, 71(3), 599-607.
Serrallés, R. J. (2006). Electric energy restructuring in the European Union: Integration, subsidiarity and the challenge of harmonization. Energy Policy, 34(16), 2542-2551.
Setiawan, A., Koprinska, I., & Agelidis, V. G. (2009). Very short-term electricity load demand forecasting using support vector regression. In Proceedings of the 2009 International Joint Conference on Neural Networks, Atlanta, GA, USA.
Shah, I., Jan, F., & Ali, S. (2022). Functional data approach for short-term electricity demand forecasting. Mathematical Problems in Engineering, 2022.
Song, W., & Fujimura, S. (2021). Capturing combination patterns of long-and short-term dependencies in multivariate time series forecasting. Neurocomputing, 464, 72-82.
Spodniak, P., Ollikka, K., & Honkapuro, S. (2021). The impact of wind power and electricity demand on the relevance of different short-term electricity markets: The Nordic case. Applied energy, 283, 116063.
Staffell, I., & Pfenninger, S. (2018). The increasing impact of weather on electricity supply and demand. Energy, 145, 65-78.
Taylor, J. W. (2010). Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research, 204(1), 139-152.
Tarmanini, C., Sarma, N., Gezegin, C., & Ozgonenel, O. (2023). Short term load forecasting based on ARIMA and ANN approaches. Energy Reports, 9, 550-557.
Trull, O., García-Díaz, J. C., & Troncoso, A. (2021). One-day-ahead electricity demand forecasting in holidays using discrete-interval moving seasonalities. Energy, 231, 120966.
Ventosa, M., Baıllo, A., Ramos, A., & Rivier, M. (2005). Electricity market modeling trends. Energy policy, 33(7), 897-913.
Vu, D. H., Muttaqi, K. M., Agalgaonkar, A. P., & Bouzerdoum, A. (2017). Short-term electricity demand forecasting using autoregressive based time varying model incorporating representative data adjustment. Applied Energy, 205, 790-801.
Yang, H. Y. (2000). A note on the causal relationship between energy and GDP in Taiwan. Energy economics, 22(3), 309-317.
Yukseltan, E., Yucekaya, A., & Bilge, A. H. (2017). Forecasting electricity demand for Turkey: Modeling periodic variations and demand segregation. Applied Energy, 193, 287-296.
Zaman, S., Nayeem, M., Tatrapi, R., & Ripon, S. (2022). Deep Learning Approach for Electricity Load Forecasting Using Multivariate Time Series Data. In Machine Intelligence and Data Science Applications: Proceedings of MIDAS 2021 (pp. 805-818). Singapore: Springer Nature Singapore.
Zúñiga-García, M. A., Santamaría-Bonfil, G., Arroyo-Figueroa, G., & Batres, R. (2018). An association-rule method for short-term electricity demand forecasting and consumption pattern recognition. In Proceedings of the 2018 Seventeenth Mexican International Conference on Artificial Intelligence (MICAI), Guadalajara, Mexico.

中文文獻
吳再益、蘇家郁、胡慎芝、吳霽庭、賴靜仙、吳爵丞 (2021)。電力交易平台規劃現況與展望。臺灣電力企業聯合會110年度專刊：臺灣電網及電力交易市場現況與未來展望，頁151-167，臺北市。
張明杰、黃義協、何信毅、陳曾裕 (2021)。民營電廠參與電力市場之機會與挑戰。載於臺灣電力企業聯合會110年度專刊：臺灣電網及電力交易市場現況與未來展望，頁196-213，臺北市。