請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95612完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李家岩 | zh_TW |
| dc.contributor.advisor | Chia-Yen Lee | en |
| dc.contributor.author | 許芸嘉 | zh_TW |
| dc.contributor.author | Yun-Chia Hsu | en |
| dc.date.accessioned | 2024-09-12T16:19:40Z | - |
| dc.date.available | 2024-09-13 | - |
| dc.date.copyright | 2024-09-12 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-07 | - |
| dc.identifier.citation | Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
AlOwaifeer, M. and Meliopoulos, A. S. (2018). Centralized microgrid energy management system based on successive linearization. In 2018 North American Power Symposium (NAPS), pages 1–6. Bergstra, J., Bardenet, R., Bengio, Y., and Kegl, B. (2011). Algorithms for hyper- parameter optimization. In Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., and Weinberger, K., editors, Advances in Neural Information Processing Systems, volume 24. Curran Associates, Inc. Bertsimas, D. and Boussioux, L. (2023). Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach. arXiv e-prints, page arXiv:2304.04308. Bremen, L. V. (2010). Large-scale variability of weather dependent renewable energy sources. In Troccoli, A., editor, Management of Weather and Climate Risk in the Energy Industry, pages 189–206, Dordrecht. Springer Netherlands. Chen, N., Qian, Z., Nabney, I. T., and Meng, X. (2014). Wind power forecasts using gaussian processes and numerical weather prediction. IEEE Transactions on Power Systems, 29(2):656–665. El Bourakadi, D., Yahyaouy, A., and Boumhidi, J. (2022). Intelligent energy management for micro-grid based on deep learning lstm prediction model and fuzzy decision-making. Sustainable Computing: Informatics and Systems, 35:100709. Fang, X., Zhang, W., Guo, Y., Wang, J., Wang, M., and Li, S. (2022). A novel reinforced deep rnn–lstm algorithm: Energy management forecasting case study. IEEE Transactions on Industrial Informatics, 18(8):5698–5704. Gomes, I., Melicio, R., and Mendes, V. (2021). A novel microgrid support management system based on stochastic mixed-integer linear programming. Energy, 223:120030. Guo, C., Wang, X., Zheng, Y., and Zhang, F. (2022). Real-time optimal energy management of microgrid with uncertainties based on deep reinforcement learning. Energy, 238:121873. Guterres, A. (2020). Carbon neutrality by 2050: the world’s most urgent mission. https://www.un.org/sg/en/content/sg/articles/ 2020-12-11/carbon-neutrality-2050-the-world\\\\OT1\\\\ textquoterights-most-urgent-mission. Accessed: 2023-12-20. Hung, Y.-H., Shen, H.-Y., and Lee, C.-Y. (2024). Deep reinforcement learning- based preventive maintenance for repairable machines with deterioration in a flow line system. Annals of Operations Research. IEA (2021). Net zero by 2050. Paris https://www.iea.org/reports/ net-zero-by-2050. Licence: CC BY 4.0. Accessed: 2023-12-20. Johansson, T. B., Patwardhan, A. P., Nakicenovic, N., and Gomez-Echeverri, L. (2012). Global energy assessment: toward a sustainable future. Cambridge University Press. Karabiber, O. A. and Xydis, G. (2019). Electricity price forecasting in the danish day-ahead market using the tbats, ann and arima methods. Energies, 12(5). Kisvari, A., Lin, Z., and Liu, X. (2021). Wind power forecasting – a data-driven method along with gated recurrent neural network. Renewable Energy, 163:1895– 1909. Lee, C.-Y., Ho, C.-Y., Hung, Y.-H., and Deng, Y.-W. (2024a). Multi-objective genetic algorithm embedded with reinforcement learning for petrochemical melt-flow-index production scheduling. Applied Soft Computing, 159:111630. Lee, C.-Y., Huang, Y.-T., and Chen, P.-J. (2024b). Robust-optimization-guiding deep reinforcement learning for chemical material production scheduling. Computers & Chemical Engineering, 187:108745. Lisi, F. and Shah, I. (2020). Forecasting next-day electricity demand and prices based on functional models. Energy Systems, 11(4):947–979. Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with Deep Reinforcement Learning. arXiv e-prints, page arXiv:1312.5602. Mnih, V., Puigdomenech Badia, A., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., and Kavukcuoglu, K. (2016). Asynchronous Methods for Deep Reinforcement Learning. arXiv e-prints, page arXiv:1602.01783. Nair, U. R. and Costa-Castello, R. (2020). A model predictive control-based energy management scheme for hybrid storage system in islanded microgrids. IEEE Access, 8:97809–97822. Nakabi, T. A. and Toivanen, P. (2021). Deep reinforcement learning for energy management in a microgrid with flexible demand. Sustainable Energy, Grids and Networks, 25:100413. Nikolopoulos, K. (2021). We need to talk about intermittent demand forecasting. European Journal of Operational Research, 291(2):549–559. Panapakidis, I. P. and Dagoumas, A. S. (2016). Day-ahead electricity price forecasting via the application of artificial neural network based models. Applied Energy, 172:132–151. Poncelet, K., Delarue, E., Six, D., Duerinck, J., and D’haeseleer, W. (2016). Impact of the level of temporal and operational detail in energy-system planning models. Applied Energy, 162:631–643. Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., and Dormann, N. (2021). Stable-baselines3: Reliable reinforcement learning implementations. Journal of Machine Learning Research, 22(268):1–8. Raya-Armenta, J. M., Bazmohammadi, N., Avina-Cervantes, J. G., Saez, D., Vasquez, J. C., and Guerrero, J. M. (2021). Energy management system optimization in islanded microgrids: An overview and future trends. Renewable and Sustainable Energy Reviews, 149:111327. Ruan, N., Xu, Y., Chan, W. K., and Wei, Z. (2022). Real-time energy management of a low-carbon micro-grid based on deep reinforcement learning. In 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia), pages 1102–1107. Salazar, A., Berzoy, A., Song, W., and Velni, J. M. (2020). Energy management of islanded nanogrids through nonlinear optimization using stochastic dynamic programming. IEEE Transactions on Industry Applications, 56(3):2129–2137. Sanayha, M. and Vateekul, P. (2022). Model-based deep reinforcement learning for wind energy bidding. International Journal of Electrical Power & Energy Systems, 136:107625. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv e-prints, page arXiv:1707.06347. Shah, I., Iftikhar, H., Ali, S., and Wang, D. (2019). Short-term electricity demand forecasting using components estimation technique. Energies, 12(13). Taiwan Power Company (n.d.). Taiwan power company official website. https: //www.taipower.com.tw/. Accessed: 2024-06-21. Tayab, U. B., Lu, J., Taghizadeh, S., Metwally, A. S. M., and Kashif, M. (2021). Microgrid energy management system for residential microgrid using an ensemble forecasting strategy and grey wolf optimization. Energies, 14(24). Torkan, R., Ilinca, A., and Ghorbanzadeh, M. (2022). A genetic algorithm optimization approach for smart energy management of microgrids. Renewable Energy, 197:852–863. Tsai, C.-T., Shen, T.-W., Chen, Y.-P., and Hsu, P.-H. (2018). Control strategy of pv/diesel/battery hybrid system for island-based microgrid. In 2018 International Symposium on Computer, Consumer and Control (IS3C), pages 121–124. Uddin, M., Mo, H., Dong, D., Elsawah, S., Zhu, J., and Guerrero, J. M. (2023). Microgrids: A review, outstanding issues and future trends. Energy Strategy Reviews, 49:101127. Wen, L., Zhou, K., Yang, S., and Lu, X. (2019). Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting. Energy, 171:1053–1065. Yagli, G. M., Yang, D., and Srinivasan, D. (2019). Automatic hourly solar forecasting using machine learning models. Renewable and Sustainable Energy Reviews, 105:487–498. Yang, J. and Su, C. (2021). Robust optimization of microgrid based on renewable distributed power generation and load demand uncertainty. Energy, 223:120043. Yin, T., Du, C., Chen, A., Jiang, T., Guo, S., and Zhang, H. (2020). Improved genetic algorithm-based optimization approach for energy management of microgrid. In 2020 IEEE 9th International Power Electronics and Motion Control Conference (IPEMC2020-ECCE Asia), pages 3234–3239. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95612 | - |
| dc.description.abstract | 微電網是整合多種能源發電設備與電力負載的在地化電力系統，而其中的能源管理系統能提升資源利用率、減少浪費、並提高整體效率。本研究聚焦於孤島微電網內的能源管理問題，微電網由太陽能光伏發電系統、風力發電系統、柴油發電機組和儲能系統組成。本研究在定義能源管理問題之數學模型時，考慮了柴油發電機組在啟動所需的暖機特性和調節發電量時的逐漸變化時間，此在以往的研究中往往被忽視。因再生能源發電量與電力負載量皆變化很大且受到許多外部因子影響，容易影響能源管理決策之穩健性，故本研究提出結合集成預測模型和深度強化學習的能源管理方法框架：預測模型使用改良的自適應穩健最佳化集成方法，並實作三種深度強化學習演算法，包含深度 Q 學習網路、優勢動作評論算法和近端策略優化。本研究使用搜集自臺灣澎湖島的每小時數據集驗證方法論，結果顯示改良的自適應穩健最佳化集成方法在預測電力負載量和風力發電量方面勝過其他機器學習集成模型，但在太陽能發電量預測效果較差。而結合預測的深度強化學習模型在決策效力和穩健性方面皆優於未考慮預測值之模型，在本實驗中，平均目標值提升 3.4 倍且標準差降低 11%。此外，決策空間維度較大的深度 Q 學習網路算法得到最高目標值。 | zh_TW |
| dc.description.abstract | Microgrids (MGs) are localized energy systems integrating diverse energy sources. An energy management (EM) system can enhance resource usage, minimize waste, and boost efficiency. This study focuses on EM within an islanded MG, comprising a solar photovoltaic (PV) system, wind power system, diesel generator (DG) set, and energy storage system (ESS). Notably, the model formulation considers the gradual changes required by dispatchable systems like DG sets during engine start-up and power regulation, aspects often overlooked in prior studies. To address the variability of renewables and load, this study proposes a novel EM framework combining ensemble forecasting models and deep reinforcement learning (DRL) algorithms. An improved adaptive robust optimization (ARO) ensemble approach is utilized, and three DRL algorithms are implemented: deep Q-network (DQN), advantage actor-critic (A2C), and proximal policy optimization (PPO). An hourly dataset collected from Penghu Island in Taiwan is used to validate the methodology. The improved ARO ensemble approach excels in forecasting energy load and wind power but is less effective for solar power. The overall results demonstrate that DRLs with forecasts outperform those without in both effectiveness and robustness, showing a 3.4-fold increase in average rewards and an 11% reduction in standard deviations in the experiments. Additionally, the DQN algorithm with finer granularity in decision space achieves the highest reward. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-12T16:19:40Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-12T16:19:40Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 謝辭 i
摘要 iii Abstract v List of Figures xi List of Tables xiii 1 Introduction 1 1.1 Background and Motivation 1 1.1.1 Background 1 1.1.2 Motivation 4 1.2 Research Objective 6 1.3 Thesis Architecture 7 2 Literature Review 9 2.1 Forecasting Method 9 2.1.1 Statistical Approach 12 2.1.2 Machine Learning-based Approach 12 2.1.3 Ensemble Approach 13 2.2 Optimization Approach 14 2.2.1 Mathematical Programming 17 2.2.2 Metaheuristic Algorithm 17 2.2.3 Rule-based Method 18 2.2.4 Control Theory Based Framework 19 2.2.5 Deep Reinforcement Learning 19 2.3 Summary and Discussion 20 3 Methodology 23 3.1 Research Framework 23 3.2 Ensemble Forecasting 23 3.2.1 ARO Ensemble Method 24 3.3 Problem Description 26 3.3.1 Diesel Generator Set 28 3.3.2 Energy Storage System 29 3.3.3 Imbalance Conditions 30 3.3.4 Objective Function 31 3.4 Markov Decision Process 32 3.5 Deep Reinforcement Learning Algorithms 35 3.5.1 Deep Q Network 35 3.5.2 Advantage Actor-Critic 37 3.5.3 Proximal Policy Optimization 37 4 Case Study 39 4.1 Data Source and Parameters Setting 39 4.2 Data Science Workflow 42 4.2.1 Forecasting Procedure 42 4.2.2 Data Splitting 44 4.3 Ensemble Models 45 4.3.1 Evaluation Metrics 45 4.3.2 Forecasting Results 46 4.3.3 Summary and Discussion 48 4.4 Deep Reinforcement Learning 50 4.4.1 Experiments and Benchmarks Setting 50 4.4.2 Hyperparameters Tuning 51 4.4.3 Optimization Results 53 5 Conclusion and Future Work 65 5.1 Conclusion 65 5.2 FutureWork 66 Reference 69 | - |
| dc.language.iso | en | - |
| dc.subject | 孤島微電網 | zh_TW |
| dc.subject | 自適應穩健最佳化 | zh_TW |
| dc.subject | 再生能源預測 | zh_TW |
| dc.subject | 集成模型 | zh_TW |
| dc.subject | 深度強化學習 | zh_TW |
| dc.subject | 能源管理 | zh_TW |
| dc.subject | ensemble modeling | en |
| dc.subject | deep reinforcement learning | en |
| dc.subject | islanded microgrid | en |
| dc.subject | energy management | en |
| dc.subject | adaptive robust optimization | en |
| dc.subject | renewables forecasting | en |
| dc.title | 穩健集成預測與深度強化學習於孤島微電網能源管理 | zh_TW |
| dc.title | Robust Ensemble Forecasting and Deep Reinforcement Learning for Energy Management of Islanded Microgrids | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 吳政鴻;孫紹華;洪一薫 | zh_TW |
| dc.contributor.oralexamcommittee | Cheng-Hung Wu;Shao-Hua Sun;I-Hsuan Hong | en |
| dc.subject.keyword | 能源管理,孤島微電網,深度強化學習,集成模型,再生能源預測,自適應穩健最佳化, | zh_TW |
| dc.subject.keyword | energy management,islanded microgrid,deep reinforcement learning,ensemble modeling,renewables forecasting,adaptive robust optimization, | en |
| dc.relation.page | 74 | - |
| dc.identifier.doi | 10.6342/NTU202403682 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-11 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 13.45 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。