臺灣博碩士論文加值系統

電動車必須使用第三方建置的充電樁進行充電時，為了要讓後續付款交易正確，常要透過如RFID刷卡或者App來進行電動車身分認證，確認充電使用者身分，才有辦法開始進行充電。這些額外的身分驗證程序，造成充電動作延遲且衍生不方便。雖然已經有些標準開始進行制定，當充電槍插入汽車後就自動驗證車輛身分，減少額外身分驗證程序，但至今仍無實際使用。

本研究探討使用低功率無線電，基於在電動車與充電站設備低設備成本的前提下，設計開發應用於電動車自動身分驗證技術。目標是讓電動車輛從遠方駛近充電站、停入充電樁停車位後，即可以自動開始驗證確認其身分，且當使用者手動將充電槍插入之後，就可立刻開始充電。本研究基於低功率藍芽無線通訊技術，讓車輛上之無線設備與充電站進行雙向訊號通訊，透過不同位置之無線電之物理特性不同的基礎，驗證車輛的狀態是駛近、經過、遠離或者停入車位，並且透過現場附近之多個無線發射裝置之訊號改變，確認該車輛是在特定位置，並且考量到不會輕易就被偽造在現場的狀態。

本研究使用機器學習演算法，進行無線通訊訊號之分析與車輛狀態判斷，並且實際於停車場進行實驗，確認本研究方法的正確性。研究成果證明，本方法判斷車輛狀態正確機率達92.135%，透過研究方法中兩階段驗證之後的錯誤正確率僅7.865%。

When an electric vehicle must be charged with a charging pile built by a third party, in order to make the subsequent payment transaction correct, it is often necessary to conduct sub-authentication of the electric vehicle through RFID card swiping or an App to confirm the identity of the charging user. These additional authentication procedures result in delayed charging and inconvenience. Although some standards have been developed to automatically verify the identity of the vehicle when the charging gun is inserted into the car, reducing external identity verification procedures, it has not been practically used so far.

This study explores the use of low-power radios to design and develop automatic identity verification technology for electric vehicles based on the premise of low equipment costs for electric vehicles and charging station equipment. The goal is to automatically verify the identity of the vehicle when it approaching to the charging station and parking in the parking space in front of the charging pile, and when the user manually inserts the charging gun, the charging can be started immediately. This research is based on low-power bluetooth wireless communication technology, which allows the wireless device on the vehicle and the charging station to carry out bidirectional communication. Based on the different physical characteristics of the radio at different locations, it is verified that the state of the vehicle is approaching, passing, moving away or parking. Through the signal changes of multiple wireless transmitters near the scene, confirm that the vehicle is in a specific location, and consider the state that it will not be easily forged at the scene.

This study uses machine learning algorithms to analyze wireless communication signals and determine vehicle status, and actually conduct experiments in parking lots to ensure the correctness of this research method. The research results show that the correct probability of judging the state of the vehicle by this method is 92.135%, and the error correct rate after the two-stage verification in the research method is only 7.865%.

摘要 i
Abstract ii
目錄 iv
圖目錄 vi
表目錄 ix
第1章 緒論 1
1.1 前言 1
1.2 論文架構 3
第2章 相關研究 4
2.1 電動車充電站(cyber-physical system, CPS)的安全 4
2.2 電動車充電站的弱點與常遇到的攻擊 4
2.3 電動充電站防止攻擊的解決方法 5
2.4 各種在場認證方法比較 11
2.5 相關研究統整 12
第3章 系統架構 13
3.1 本研究所提出BLE在場認證設計 13
3.1.1 第一層認證(Level 1) — 透過KNN model預測目標是否進入停車格 15
3.1.2 第二層認證系統(Level 2) — 在場周遭beacon裝置確認 17
3.2 硬體設計 19
3.2.1 充電樁設計 20
3.2.2 電動車上的天線設計 22
3.2.3 周遭beacon裝置 22
3.3 軟體設計 23
3.3.1 系統運作流程 23
3.3.2 充電樁認證系統運作流程 24
3.3.3 電動車認證運作流程 25
3.3.4 周遭beacon運作流程 26
第4章 前導實驗 27
4.1 實驗設計 29
4.1.1 前導實驗第一部分 (第一層認證, Level 1) 29
4.1.2 前導實驗第二部分 (第二層認證, Level 2) 34
4.2 前導實驗結果分析 36
4.2.1 前導實驗第一部分分析 (第一層認證, Level 1) 36
4.2.2 前導實驗第二部分分析 (第二層認證, Level 2) 40
4.3 追加實驗 41
4.3.1 實驗設計 42
4.3.2 SVM模型建立 47
第5章 進階實驗 49
5.1 第一層認證 (Level 1) 49
5.1.1 實驗設計 49
5.1.2 實驗結果分析 52
5.2 第二層認證 (Level 2) 54
5.2.1 實驗設計 55
5.2.2 實驗結果分析 56
第6章 結論 58
第7章 未來工作 58
參考文獻 60

[1]R. Gottumukkala, R. Merchant, A. Tauzin, K. Leon, A. Roche and P. Darby, "Cyber-physical System Security of Vehicle Charging Stations," 2019 IEEE Green Technologies Conference(GreenTech), 2019, pp. 1-5, doi: 10.1109/GreenTech.2019.8767141.
[2]A. C. . -F. Chan and J. Zhou, "Cyber–Physical Device Authentication for the Smart Grid Electric Vehicle Ecosystem," in IEEE Journal on Selected Areas in Communications, vol. 32, no. 7, pp. 1509-1517, July 2014, doi: 10.1109/JSAC.2014.2332121.
[3]S. Saadat, S. Maingot and S. Bahizad, "Electric Vehicle Charging Station Security Enhancement Measures," 2020 5th IEEE Workshop on the Electronic Grid (eGRID), 2020, pp. 1-8, doi: 10.1109/eGRID48559.2020.9330666.
[4]M. Basnet, S. Poudyal, M. H. Ali and D. Dasgupta, "Ransomware Detection Using Deep Learning in the SCADA System of Electric Vehicle Charging Station," 2021 IEEE PES Innovative Smart Grid Technologies Conference - Latin America (ISGT Latin America), 2021, pp. 1-5, doi: 10.1109/ISGTLatinAmerica52371.2021.9543031.
[5]M. Basnet and M. Hasan Ali, "Deep Learning-based Intrusion Detection System for Electric Vehicle Charging Station," 2020 2nd International Conference on Smart Power & Internet Energy Systems (SPIES), 2020, pp. 408-413, doi: 10.1109/SPIES48661.2020.9243152.
[6]Y. -Y. Chu and K. -H. Liu, "IoT in Vehicle Presence Detection of Smart Parking System," 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 2020, pp. 56-59, doi: 10.1109/ECICE50847.2020.9301942.
[7]https://www.switch-ev.com/knowledgebase/what-is-iso-15118
[8]https://www.switch-ev.com/knowledgebase/basics-of-plug-and-charge
[9]Y. Leguesse, C. Colombo, M. Vella and J. Hernandez-Castro, "PoPL: Proof-of-Presence and Locality, or How to Secure Financial Transactions on Your Smartphone," in IEEE Access, vol. 9, pp. 168600-168612, 2021, doi: 10.1109/ACCESS.2021.3137360.
[10]J. Ferreira and M. L. Pardal, "Witness-Based Location Proofs for Mobile Devices," 2018 IEEE 17th International Symposium on Network Computing and Applications (NCA), 2018, pp. 1-4, doi: 10.1109/NCA.2018.8548244.
[11]D. K. Manase, Z. Zainuddin, S. Syarif and A. K. Jaya, "Car Detection in Roadside Parking for Smart Parking System Based on Image Processing," 2020 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2020, pp. 194-198, doi: 10.1109/ISITIA49792.2020.9163744.
[12]A. Albiol, L. Sanchis, A. Albiol and J. M. Mossi, "Detection of Parked Vehicles Using Spatiotemporal Maps," in IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp. 1277-1291, Dec. 2011, doi: 10.1109/TITS.2011.2156791.