研究生: |
張博鈞 Po-Chun Chang |
---|---|
論文名稱: |
運用機器學習預測 Youbike2.0供需與優化運補路徑-公館區為例 Using Machine Learning for Demand Forecasting and Route Optimization: The Case Study of Gongguan Youbike 2.0 District |
指導教授: |
呂志豪
Shih-Hao Lu |
口試委員: |
黃政嘉
Jheng-Jia Huang 黃振皓 Chen-Hao Huang |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 企業管理系 Department of Business Administration |
論文出版年: | 2023 |
畢業學年度: | 112 |
語文別: | 英文 |
論文頁數: | 32 |
中文關鍵詞: | 共享單車系統 、最佳化 、路徑規劃 、啟發式演算法 、機器學習 、隨機森林迴歸 、多元迴歸 |
外文關鍵詞: | Shared Bicycle System, Youbike2.0, Optimization; Route Planning, Heuristic Algorithms, Machine Learning, Random Forest Regression, Multiple Regression, eXtreme Gradient Boosting |
相關次數: | 點閱:246 下載:18 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來,共享單車在各大城市迅速普及,成為解決城市交通擁堵和環境永續性問題的重要方法。共享單車環保與方便,受到了廣泛關注。然而,隨著共享單車的使用率不斷增加,出現了一些新的問題,最棘手的為站點之間供需不平衡的情況。在尖峰時段,一些熱門站點經常出現共享單車不足或者無位可還的問題。影響了民眾的使用體驗且降低了共享單車系統的使用效率。為了解決這一問題,優化共享單車的調度。本研究採用了機器學習預測每個站點在特定時刻的淨需求,這些預測模型使用天氣、時間等變數,以更準確地估計淨需求。通過預測淨需求,我們可以更容易了解哪些站點在未來的某個時刻出現共享單車不足的問題,從而提前補充共享單車。此外,本研究使用啟發式演算法於路線規劃,找尋最佳化的路線,使 Youbike 更有效地配送車輛,以緩解尖峰時段的問題。改善共享單車系統的運營效率,減少共享單車不足和停車位不足等問題。通過結合機器學習和最佳化路徑,更精準預測共享單車需求,提高使用效率。
In recent years, shared bicycles have rapidly gained popularity in major cities, emerging as a vital solution to urban traffic congestion and environmental sustainability. Their eco-friendliness and convenience have garnered widespread attention. However, as the usage rate of shared bicycles continues to rise, new challenges have emerged, the most daunting being the imbalance of supply and demand between stations. During peak hours, popular stations often experience shortages of shared bicycles or lack of available parking spaces. This affects the user experience and reduces the efficiency of the shared bicycle system. To address this issue, efforts have been made to optimize the dispatch of shared bicycles. Our study employs machine learning to predict the net demand at each station at specific times. The predictive model takes into account various factors, such as weather and time, to estimate net demand more accurately. By forecasting net demand, we can better understand which stations may face a shortage of shared bicycles in the future and, therefore, restock in advance. Additionally, the study uses heuristic algorithms for route planning to find the most optimized routes, enabling more efficient distribution of vehicles for Youbike, thus alleviating problems during peak periods. The operational efficiency of the shared bicycle system is improved by reducing issues like bicycle shortages and insufficient parking. By combining machine learning with optimized routing, the demand for shared bicycles can be predicted more accurately, enhancing usage efficiency.
Benedini, D. J., Lavieri, P. S., & Strambi, O. (2020). Understanding the use of private and shared bicycles in large emerging cities: The case of Sao Paulo, Brazil. Case Studies on Transport Policy, 8(2), 564-575.
Cruz, F., Subramanian, A., Bruck, B. P., & Iori, M. (2017). A heuristic algorithm for a single vehicle static bike sharing rebalancing problem. Computers & Operations Research, 79, 19-33.
Dantzig, G. B., & Ramser, J. H. (1959). The truck dispatching problem. Management science, 6(1), 80-91.
Eren, E., & Uz, V. E. (2020). A review on bike-sharing: The factors affecting bike-sharing demand. Sustainable cities and society, 54, 101882.
Hu, Z., Huang, K., Zhang, E., Ge, Q. a., & Yang, X. (2021). Rebalancing strategy for bike-sharing systems based on the model of level of detail. Journal of advanced transportation, 2021, 1-15.
Jia, R., Chamoun, R., Wallenbring, A., Advand, M., Yu, S., Liu, Y., & Gao, K. (2023). A spatio-temporal deep learning model for short-term bike-sharing demand prediction. Electronic Research Archive, 31(2), 1031-1047.
Jia, Y., Zeng, W., Xing, Y., Yang, D., & Li, J. (2020). The bike-sharing rebalancing problem considering multi-energy mixed fleets and traffic restrictions. Sustainability, 13(1), 270.
Li, W., & Kamargianni, M. (2018). Providing quantified evidence to policy makers for promoting bike-sharing in heavily air-polluted cities: A mode choice model and policy simulation for Taiyuan-China. Transportation research part A: policy and practice, 111, 277-291.
LI, Y. (2022). Statistical Application Analysis Report: Analysis of Usage Characteristics of Taipei's YouBike 2.0.
Lin, S. (1965). Computer solutions of the traveling salesman problem. Bell System Technical Journal, 44(10), 2245-2269.
Peláez-Rodríguez, C., Pérez-Aracil, J., Fister, D., Torres-López, R., & Salcedo-Sanz, S. (2024). Bike sharing and cable car demand forecasting using machine learning and deep learning multivariate time series approaches. Expert Systems with Applications, 238, 122264.
Qiao, J., He, M., Sun, N., Sun, P., & Fan, Y. (2023). Factors affecting the final solution of the bike-sharing rebalancing problem under heuristic algorithms. Computers & Operations Research, 159, 106368.
Qiu, L.-Y., & He, L.-Y. (2018). Bike sharing and the economy, the environment, and health-related externalities. Sustainability, 10(4), 1145.
Sathishkumar, V., Park, J., & Cho, Y. (2020). Using data mining techniques for bike sharing demand prediction in metropolitan city. Computer Communications, 153, 353-366.
Vallez, C. M., Castro, M., & Contreras, D. (2021). Challenges and opportunities in dock-based bike-sharing rebalancing: a systematic review. Sustainability, 13(4), 1829.
VE, S., & Cho, Y. (2020). A rule-based model for Seoul Bike sharing demand prediction using weather data. European Journal of Remote Sensing, 53(sup1), 166-183.
Wang, B., & Kim, I. (2018). Short-term prediction for bike-sharing service using machine learning. Transportation research procedia, 34, 171-178.
Wang, M., & Zhou, X. (2017). Bike-sharing systems and congestion: Evidence from US cities. Journal of transport geography, 65, 147-154.
YouBike Co., L. (2022). Total Number of bike rentals in Taipei City https://www.youbike.com.tw/region/taipei/operation/
Zhang, Y., & Mi, Z. (2018). Environmental benefits of bike sharing: A big data-based analysis. Applied energy, 220, 296-301.