為因應氣候變遷所帶來之影響，全球的電力系統皆面臨去碳化壓力，且我國在2050淨零排放路徑中，規劃至2050年時總電力的60～70%將來自再生能源。為有效管理電網風險，準確的短期負載預測至關重要。而電動車的發展被視為運輸部門未來達成淨零碳排的關鍵策略，在達成淨零排放目標下至2030年時全球電動車銷售量須達到汽車總銷量的60%，當前台灣電動車市場尚處於發展階段，未來電動車發展將會對於電網造成衝擊。
本研究旨在建立一個考量電動車充電需求下的短期電力負載預測模型。研究首先回顧了機器學習方法應用於電力負載預測及電動車負載預測的相關研究，並使用分位數迴歸隨機森林和長短期記憶神經網路模型建構短期電力負載預測模型，再利用S曲線推估2030年電動小客車數量，接著利用自小客車行車行為推估電動車電力消費量，並建立小時別電動車充電負載曲線。最後，將短期電力負載預測模型與電動車負載模型結合，估算出2030年小時別總電力負載需求。
研究結果顯示，2030年時市場上約有534,485輛電動小客車，造成2030年的電動小客車總耗電量約為10.68億度電，相較2023年成長約9.1倍。此外，2030年預測之電力需求約為3,506億度，電動車充電負載約占0.29%，若以預測最高日尖峰負載加以計算，電動車之耗電量約占0.25%，夜尖峰推估電動車將增加負載192MW~281MW。
本研究可作為台灣發展電動車之政策參考，在未來將會有更多電動車加入市場，屆時，充電時段管理與電網基礎建設將更為重要，且須進一步將電動車之使用者行為納入政策制定之考量。

According to Taiwan's 2050 net-zero emissions pathway, 60-70% of total electricity is expected to come from renewable energy sources by 2050. Accurate short-term load forecasting is crucial for effectively managing grid risks. The development of electric vehicles (EVs) is a key strategy for the transportation sector to achieve net-zero carbon emissions. Future EV growth will significantly impact the power grid. This study establishes a short-term probabilistic forecasting model for seasonal climate and electricity load using Quantile Regression Forest (QRF) and Long Short-Term Memory (LSTM) neural network methods, and compares their performance. The results indicate that the LSTM model outperforms the QRF model. However, due to the limited large-scale adoption of EVs in Taiwan, there is not yet sufficient data for machine learning methods. Therefore, this study simulates the short-term charging load of EVs by setting driving patterns and converting them into electricity demand. It then combines the short-term electricity load forecasting model with the EV load model to estimate the total hourly electricity load demand for 2030. This provides a diverse basis for electricity load estimation and regulation for the power system. Finally, the study suggests that the government introduce smart charging management and develop more comprehensive charging infrastructure.

王志文(2019)，「國內電動車發展對電力影響之探討」，台灣綜合研究院。
台灣電力公司(2020)，「智慧電網總體規劃方案推動辨理情形」。
台灣電力公司(2022)，「電動車充換電設施電價」。
交通部(2023) ，「自用小客車使用狀況調查報告」。
李宗瑾(2022)，「電動車對電力負載之探討」，台灣綜合研究院。
李宜馨、陳彥銘和李明峯(2018)，「動態迴歸模型於短期區域電力負載預測之研究」，臺灣能源期刊，第5卷，第4期，第395-406頁。
國家發展委員會 (2022)，都市及區域發展統計彙編。
國家發展委員會(2022)，「台灣2050淨零排放路徑及策略」。
張宇琦和柏雲昌(2021)，「推廣電動車輛之電力負載預測與環境衝擊分析」，綠色經濟電子期刊，第7卷，第A21-46頁。
經濟部(2023)，「電力系統與儲能關鍵戰略行動計畫」。
籃宏偉（2011）。區域電力負載與氣候相關性研究-多元線性迴歸模型，國立高雄應用科技大學臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/e2r7e4。
Abdalla, A. A., and Khalid, M. (2019). Smoothing methodologies for photovoltaic power fluctuations. In 2019 8th International Conference on Renewable Energy Research and Applications (ICRERA), 342-346.
Abdalla, A. N., Nazir, M. S., Tao, H., Cao, S., Ji, R., Jiang, M., and Yao, L. (2021). Integration of energy storage system and renewable energy sources based on artificial intelligence: An overview. Journal of Energy Storage, 40, 102811.
Azizipanah-Abarghooee, R., Golestaneh, F., Gooi, H. B., Lin, J., Bavafa, F., and Terzija, V. (2016). Corrective economic dispatch and operational cycles for probabilistic unit commitment with demand response and high wind power. Applied energy, 182, 634-651.
Boonluk, P., Siritaratiwat, A., Fuangfoo, P., and Khunkitti, S. (2020). Optimal siting and sizing of battery energy storage systems for distribution network of distribution system operators. Batteries, 6(4), 56.
Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M. A. (2020). Multi-sequence LSTM-RNN deep learning and metaheuristics for electric load forecasting. Energies, 13(2), 391.
Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32.
Cai, C., Li, Y., Su, Z., Zhu, T., and He, Y. (2022). Short-term electrical load forecasting based on VMD and GRU-TCN hybrid network. Applied Sciences, 12(13), 6647.
Central Weather Bureau CWB. (2023). Observation data inquire system. Taiwan. https://e-service.cwb.gov.tw/HistoryDataQuery/.
Chaudhuri, D., and Chaudhuri, B. B. (1997). A novel multiseed nonhierarchical data clustering technique. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 27(5), 871-876.
Chen, C.H., Huang ,Y.H., Wu, J.H., & Lin, H. (2023). Assessing the cross-sectoral economic–energy–environmental impacts of electric-vehicle promotion in Taiwan. Sustainability, 15(19), 14135.
Chi, D. (2022). Research on electricity consumption forecasting model based on wavelet transform and multi-layer LSTM model. Energy Reports, 8, 220-228.
Dai, Y., and Zhao, P. (2020). A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization. Applied Energy, 279, 115332.
Dang, S., Peng, L., Zhao, J., Li, J., Kong, Z. (2022). A quantile regression random forest-based short-term load probabilistic forecasting method. Energies, 15, 663.
Das, S., and Basu, M. (2020). Day-ahead optimal bidding strategy of microgrid with demand response program considering uncertainties and outages of renewable energy resources. Energy, 190, 116441.
Department of Household Registration DHR. (2023). Population statistics data. Ministry of the Interior, Taiwan.
Eskandari, H., Imani, M., and Moghaddam, M. P. (2021). Convolutional and recurrent neural network based model for short-term load forecasting. Electric Power Systems Research, 195, 107173.
ETI(2022)，Energy System Modelling Environment(ESME) v4.4.
Freeway Bureau. (2023). Traffic data collection system TDCS. Ministry of Transportation and Communications, R.O.C. https://tisvcloud.freeway.gov.tw/.
Gang, W., Wu, L., and Xuan, G. (2021). A load forecasting method of electric vehicles charging station group based on GAN-RF model. In 2021 IEEE 5th Conference on Energy Internet and Energy System Integration, 3076-3079.
Ghimire, S., Deo, R. C., Casillas-Pérez, D., and Salcedo-Sanz, S. (2023). Efficient daily electricity demand prediction with hybrid deep-learning multi-algorithm approach. Energy Conversion and Management, 297, 117707.
Huang, J., Wu, Q. H., Li, Z. G., and Zheng, J. H. (2018). Multi-objective Optimal Power Flow Problem Using DE-NSGA-III Algorithm. In 2018 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia), 693-698.
IEA (2022), Global EV Outlook 2022, IEA, Paris https://www.iea.org/reports/global-ev-outlook-2022.
IEA (2022), World Energy Outlook 2022, IEA, Paris https://www.iea.org/reports/world-energy-outlook-2022.
International Energy Agency IEA. (2019). Status of Power System Transformation 2019. Paris: OECD.
International Energy Agency IEA. (2022a), Global EV Outlook 2022, Paris, France: IEA. https://www.iea.org/reports/global-hydrogen-review-2022.
International Energy Agency IEA. (2022b), Global Hydrogen Review 2022, Paris, France: IEA. https://www.iea.org/reports/global-ev-outlook-2022.
International Energy Agency IEA. (2023). Net Zero Roadmap: A Global Pathway to Keep the 1.5 °C Goal in Reach. Paris, France: IEA. https://www.iea.org/reports/net-zero-roadmap-a-global-pathway-to-keep-the-15-0c-goal-in-reach.
Jafari, A., Ganjehlou, H. G., Khalili, T., and Bidram, A. (2020). A fair electricity market strategy for energy management and reliability enhancement of islanded multi-microgrids. Applied Energy, 270, 115170.
Khaloie, H., Abdollahi, A., Shafie-Khah, M., Anvari-Moghaddam, A., Nojavan, S., Siano, P., and Catalão, J. P. (2020). Coordinated wind-thermal-energy storage offering strategy in energy and spinning reserve markets using a multi-stage model. Applied Energy, 259, 114168.
Khoshrou, A., and Pauwels, E. J. (2019). Short-term scenario-based probabilistic load forecasting: a data-driven approach. Applied Energy, 238, 1258-1268.
Koenker, R. (2005). Quantile regression. Cambridge U. Press.
Koenker, R., and Xiao, Z. Quantile autoregression. (2006). Journal of the American Statistical Association, 101(475), 980-990.
Koenker, R.and J.A.F. Machado (1999) Goodness of Fit and Related Inference Processes for Quantile Regression, JASA, 1296-1310.
Kumar, A., Meena, N. K., Singh, A. R., Deng, Y., He, X., Bansal, R. C., and Kumar, P. (2019). Strategic integration of battery energy storage systems with the provision of distributed ancillary services in active distribution systems. Applied Energy, 253, 113503.
Lei, X., Yang, Z., Zhao, J., and Yu, J. (2022). Data-driven assisted chance-constrained energy and reserve scheduling with wind curtailment. Applied Energy, 321, 119291.
Li, Z., Hurn, A. S., and Clements, A. E. (2017). Forecasting quantiles of day-ahead electricity load. Energy Economics, 67, 60-71.
Meinshausen, N., and Ridgeway, G. (2006). Quantile regression forests. Journal of Machine Learning Research, 7(6), 983-999.
Mohamed, M. A., Jin, T., and Su, W. (2020). An effective stochastic framework for smart coordinated operation of wind park and energy storage unit. Applied Energy, 272, 115228.
Rajbhandari, Y., Marahatta, A., Ghimire, B., Shrestha, A., Gachhadar, A., Thapa, A., Chapagain, K., and Korba, P. (2022). Impact study of temperature on the time series electricity demand of urban Nepal for short-term load forecasting. Applied System Innovation, 4(3), 43.
Sardi, J., Mithulananthan, N., and Hung, D. Q. (2017). Strategic allocation of community energy storage in a residential system with rooftop PV units. Applied energy, 206, 159-171.
Shohan, M. J. A., Faruque, M. O., and Foo, S. Y. (2022). Forecasting of electric load using a hybrid LSTM-neural prophet model. Energies, 15(6), 2158.
Taiwan Power Company TPC. (2023). Installed capacity and hourly generation of owned solar PV power plants by region. Department of Power Dispatch, Taiwan.
Torres, J.F., Martínez-Álvarez, F. and Troncoso, A. (2022) A deep LSTM network for the Spanish electricity consumption forecasting. Neural Computing and Applications, 34(13), 10533-10545.
Vanting, N.B., Ma, Z. and Jørgensen, B.N. (2021) A scoping review of deep neural networks for electric load forecasting. Energy Inform 4 (Suppl 2), 49.
Vanting, N.B., Ma, Z. and Jørgensen, B.N.(2022) A scoping review of deep neural networks for electric load forecasting. Energy Inform 4 (Suppl 2), 49.
Wang, H., Zhang, N., Du, E., Yan, J., Han, S., and Liu, Y. (2022). A comprehensive review for wind, solar, and electrical load forecasting methods. Global Energy Interconnection, 5(1), 9-30.
Wei, P., Ning, Z., Ye, S., Sun, L., Yang, F., Wong, K.C., Westerdahl, D., Louie, P.K.K. (2018) Impact analysis of temperature and humidity conditions on electrochemical sensor response in ambient air quality monitoring. Sensors, 18(2), 59.
Wu, Z., Luo, G., Yang, Z., Guo, Y., Li, K., and Xue, Y. (2022). A comprehensive review on deep learning approaches in wind forecasting applications. CAAI Transactions on Intelligence Technology, 7(2), 129-143.
Xie, J., and Hong, T. (2017). Wind speed for load forecasting models. Sustainability, 9(5), 795.
Yang, Y., Bremner, S., Menictas, C., and Kay, M. (2022). Modelling and optimal energy management for battery energy storage systems in renewable energy systems: A review. Renewable and Sustainable Energy Reviews, 167, 112671.
Zhang, J., Yan, J., Liu, Y., Zhang, H., and Lv, G. (2020). Daily electric vehicle charging load profiles considering demographics of vehicle users. Applied Energy, 274, 115063.
Zhang, T., Huang, Y., Liao, H., and Liang, Y. (2023). A hybrid electric vehicle load classification and forecasting approach based on GBDT algorithm and temporal convolutional network. Applied Energy, 351, 121768.
Zhao, B., Zhang, X., Chen, J., Wang, C., and Guo, L. (2013). Operation optimization of standalone microgrids considering lifetime characteristics of battery energy storage system. IEEE transactions on sustainable energy, 4(4), 934-943.