使用GBRT預測短期國道交通路況

Using GBRT to predict short-term freeway traffic condition

林崇翔(Chung-Hsiang Lin)

指導教授 ： 張明峰

國立交通大學/資訊學院/資訊科學與工程研究所/碩士(2018年)

摘要

在智慧交通系統的發展與應用中，準確預測旅行時間是不可或缺的應用，使大眾在旅行開始前做出更好的規劃以及旅行方式的選擇，有助於減少旅客焦慮跟運輸成本。旅行時間估計和預測是個複雜且具有挑戰性的任務，由於不同車輛組合以及天氣、事件等外部因素往往會造成預測準確度的下降。本研究目的是針對在高速公路上的短期國道交通預測，利用現有可蒐集到的國道交通資訊來做預測，整理出我們所需要的預測目標(旅行時間、壅塞排除時間)及變量(車速、車輛數、道路佔有率…等)，做前置的資料處理與產生新的特徵。使用梯度提升決策樹(GBRT)來預測，我們提出一個調整GBRT參數與特徵挑選的方法來提高短期國道交通路況預測準確度。觀測皮爾森相關係數找出鄰近VD的影響設定基礎模型，並使用分位損失而不是最小平方差損失函數，在所選路段預測TT降低平均2.44% MAPE誤差，預測TTF降低平均0.21 MAE誤差。調整GBRT超參數提高模型的準確度。透過影響目標路段預測TT準確度找出最佳鄰近VD組合，上下游交通對目標的影響並不平衡。透過特徵工程產生的路段壅塞長度(congestion length)，在三條選取的路段預測TTF時有助於模型降低預測誤差。對所選路段作特徵轉換，使得96路段預測TT降低0.5% MAPE。最後，比較深度學習預測誤差與分析四月份預測的結果，在較常發生壅塞的路段以及壅塞將要解除的時刻，GBRT擁有較低的預測誤差(壅塞路段最多降低0.32%)以及錯誤統計量(L2:壅塞解除時的錯誤預測次數少於NN平均29.5次、FC:壅塞時預測順暢的次數少於NN平均12.25次)。本研究訓練完的GBRT模型最後在路段96獲得了比NN低1.08%的MAPE誤差。

關鍵字

旅行時間 ； 短期交通預測 ； 集成模型學習 ； 梯度上昇回歸樹演算法

並列摘要

In the development and application of intelligent transportation systems, accurate prediction of travel time is an indispensable application, so that the public can make better trip planning before travel begins. This helps to reduce passenger anxiety and transportation costs. Travel time estimation and prediction is a complex and challenging task, which tends not to be able to grantee the accuracy of prediction due to different vehicle combinations and external factors such as weather and events. The purpose of this study is to forecast the short-term national highway traffic on expressways, using the available national highway traffic information. In addition to travel time, our forecast target including the time needed for a congestion to resolve. For prediction features, we used date/time related information, primitive VD data (speed, flow, and road occupancy), and new features generated from VD data. Using the Gradient Boosting Regression Tree (GBRT) to predict, we propose a method to adjust the GBRT parameters and perform feature selection to improve the prediction accuracy. Observing the Pearson correlation coefficient to include optimal adjacent VD set in our prediction model, and using the quantile loss function can reduce travel time prediction error by 2.44% in average and the average MAE of TTF prediction by 0.21. Moreover, we adjust the GBRT hyper-parameters to improve the prediction accuracy. Our experiments show that the impacts of upstream and downstream traffic are not the same for different road segments. Therefore, we need to find the best adjacent VD combination for each road segment. The total congestion road length generated by our feature engineering helps to reduce the TTF prediction errors in three out of four selected routes. Feature transform is also performed on the selected road segments, so that the MAPE of TT prediction is reduced by 0.5% on one selected. Finally, comparing with the deep learning prediction errors, our GBRT model performs better on heavy traffic segments; it has a lower prediction error (the reduction is up to 1.08% in MAPE) and a smaller number of prediction errors at the time when the congestion is about to resolve.

並列關鍵字

Gradient boosting regression tree ； Travel time ； Short-term forecasting ； Ensemble learning ； Machine learning

參考文獻

[1] M. Chen and S. I. J. Chien, "Dynamic Freeway Travel-time Prediction with Probe Vehicle Data: Link based versus Path based," Transportation Research Record: Journal of the Transportation Research Board, vol. 1768, p. 157–161, 2001.

[2] C. M. Kuchipudi and S. I. J. Chien, "Development of a Hybrid Model for Dynamic Travel Time Prediction," Transportation Research Record: Journal of the Transportation Research Board, vol. 1855, pp. 22-31, 2003.

[3] J.-S. Yang, "A Study of Travel Time Modeling via Time Series Analysis," in Proceedings of the 2005 IEEE Conference on Control Applications, 2005.

[4] W. Min and L. Wynter, "Real-time Road Traffic Prediction with Spatio-temporal Correlations," Transportation Research Part C, vol. 19, no. 4, p. 606–616, 2011.

[5] C.-H. Wu, J.-M. Ho and D. T. Lee, "Travel-time Prediction with Support Vector Regression," IEEE Transactions On Intelligent Transportation Systems, vol. 5, no. 4, p. 276–281, 2004.