近來隨著電動車數量的上漲，對電動車充電站的需求也愈加迫切。充電站可以通過電網和可再生能源為電動車充電，以滿足其電力需求。然而，由於電網容量有限，充電站面臨無法提供足夠電力滿足電動車需求的挑戰。為了應對這一挑戰，能量存儲系統因為能預先儲存電力所以被認為是有效解決方案之一。
因此，一個高效的儲能系統控制演算法對於有效管理儲能系統中的充電和放電過程至關重要。儲能系統控制問題的主要挑戰是與進入的電動車相關的不確定性，包括到達時間、電池容量以及初始和期望的電池充電狀態。在本文中，我們提出了兩種在充電站中能夠調節儲能系統充電和放電的在線儲能系統控制算法。這兩種算法分別基於儲能系統過去充電狀態的平均值和基於Long Short-term Memory（LSTM）模型預測充電負載來確定儲能系統的充電/放電。我們的模擬實驗表明，所提出的算法表現良好，相比基線算法，充電站運營方的利潤更高。

With the increasing number of electric vehicles (EVs), the demand for charging stations (CSs) has also risen sharply. A CS can charge EVs to meet their power requirements through the power grid and renewable energy. However, due to the limited capacity of the power grid, CSs face the challenge of not being able to provide sufficient power to meet the demand of EVs. To address this challenge, an energy storage system (ESS) that can store power in advance is considered to be an effective solution.
Therefore, an efficient ESS control algorithm is crucial for effectively managing the charging and discharging processes in the ESS. The main challenge of the ESS control problem is the uncertainty surrounding incoming EVs, including their arrival time, battery capacity, and initial and desired battery state of charge (SOC). In this paper, we propose two online ESS control algorithms that can regulate the charging and discharging of ESS in CSs. The two algorithms determine ESS to charge/discharge based on the average of State-of-Charge (SOC) of ESS in history and based on pre-diction charging load from Long Short-term Memory (LSTM) model, respectively. Our simulations demonstrate that the proposed algorithms perform well, resulting in higher profits for CS operators compared to the baseline algorithm.

Contents i
List of Figures iii
List of Tables iv
1 Introduction 1
2 Problems 5
2.1 The Scenario . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.2 The ESS Control Problem . . . . . . . . . . . . . . . . . . . . 6
3 Proposed Algorithms 7
3.1 Curve Algorithm . . . . . . . . . . . . . . . . . . . . . . . . 7
3.1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.1.2 Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.2 RNN-based Algorithm . . . . . . . . . . . . . . . . . . . . . . 9
3.2.1 Features and Models . . . . . . . . . . . . . . . . . . . . . 10
3.2.2 Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4 Simulation 14
4.1 Simulation Settings . . . . . . . . . . . . . . . . . . . . . . 14
4.1.1 EV Arrivals . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.1.2 EV Setting . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.1.3 Charging Station Setting . . . . . . . . . . . . . . . . . . 15
4.1.4 Charging Scheduling Algorithm . . . . . . . . . . . . . . . 16
4.2 Simulation Results . . . . . . . . . . . . . . . . . . . . . . 16
5 Conclusion 19
References 20

[1] The paris agreement. Accessed May. 28, 2023. [Online]. Available:
https://unfccc.int/process-and-meetings/the-paris-agreement
[2] 6 automakers and 30 countries say they’ll phase out gasoline
car sales. Accessed May. 28, 2023. [Online]. Available:
https://www.nytimes.com/2021/11/09/climate/cars-zero-emissions-cop26.html
[3] 表燈(住商)用戶如何評估選用時間電價. Accessed May. 29, 2023. [Online]. Available: https://www.taipower.com.tw/tc/faq2 info.aspx?id=87&chk=a1c9b4a0-1a53-4f11-94db-6c503c33100c&mid=80
[4] 電價表. Accessed May. 30, 2023. [Online]. Available:
https://www.taipower.com.tw/tc/page.aspx?mid=238
[5] L. Affolabi, M. Shahidehpour, F. Rahimi, F. Aminifar, K. Nodehi, and S. Mokhtari, “Hierarchical transactive energy scheduling of electric vehicle charging stations in constrained power distribution and transportation networks,” IEEE Transactions on Transportation Electrification, 2022.
[6] Q. Yan, B. Zhang, and M. Kezunovic, “Optimized operational cost reduction for an ev charging station integrated with battery energy storage and pv generation,” IEEE Transactions on Smart Grid, vol. 10, no. 2, pp. 2096–2106, 2018.
[7] Y. Zhang, Q. Yang, D. An, D. Li, and Z. Wu, “Multistep multiagent reinforcement learning for optimal energy schedule strategy of charging stations in smart grid,” IEEE Transactions on Cybernetics, 2022.
[8] S. Mishra, A. Mondal, and S. Mondal, “A multi-objective optimization framework for electric vehicle charge scheduling with adaptable charging ports,” IEEE Transactions on Vehicular Technology, 2022.
[9] L. Yang, X. Geng, X. Guan, and L. Tong, “Ev charging scheduling under demand charge: A block model predictive control approach,” IEEE Transactions on Automation Science and Engineering, 2023.
[10] T.-Y. Ma and S. Faye, “Multistep electric vehicle charging station occupancy prediction using hybrid lstm neural networks,” Energy, vol. 244, p. 123217, 2022.
[11] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[12] Electric vehicle charging station usage. Accessed May. 28, 2023. [Online]. Available: https://data.pkc.gov.uk/en/dataset/ev-charging-data/resource/845fe22f-19f4-499b-b8bc-8812a763e660
[13] 2020年度臺灣汽車市場銷售報告：電動車top 10. Accessed May. 28, 2023.
[Online]. Available: https://news.u-car.com.tw/news/article/64655
[14] 2021年度臺灣汽車市場銷售報告：電動車top 10. Accessed May. 28, 2023.
[Online]. Available: https://news.u-car.com.tw/news/article/69240
[15] T. S. Bryden, G. Hilton, B. Dimitrov, C. Ponce de Le´on, and A. Cruden, “Rating a stationary energy storage system within a fast electric vehicle charging station considering user waiting times,” IEEE Transactions on Transportation Electrification, vol. 5, no. 4, pp. 879–889, 2019.
[16] open-ev-data. Accessed May. 28, 2023. [Online]. Available:
https://github.com/chargeprice/open-ev-data
[17] 電動車用業務專區. Accessed May. 28, 2023. [Online]. Available:
https://www.taipower.com.tw/tc/page.aspx?mid=659422