計程車空車巡行路徑推估方法之研究

Abstract

計程車是都市重要的副大眾運輸工具，而對於計程車產業，需求熱點辨識為一重要議題，因為透過找出需求所在位置，可以減少計程車空駛，達到增加營運效率以及降低污染的作用。然而，在過去的研究中，對於需求熱點的計算多僅使用需求面資料，未考慮供需平衡關係。為改善此問題，本研究透過推估空車巡行路徑，並將推估結果轉換為各區域空車時間，作為計程車供給面資料供未來熱點辨識使用。 本研究利用計程車新式計費表資料，及影響計程車需求之因素，建立兩種空車巡行路徑推估方法，並以推估結果將空車時間分配至對應時段、區域，計算不同時空下之總空車時間。本研究利用衛星車隊之實際資料進行測試並驗證準確度，結果顯示本研究所提出之方法，推估出之數值準確度落於合理範圍內。

Taxicab is a vital paratransit in urban areas, and hotspot identification of taxi demand is an import topic for taxi industry. By identifying the distribution of demand, it can reduce the vacant taxi routing, improve the operating efficiency and reduce air pollution. However, most previous studies only use demand-side data to calculate hotspots rather than consider the balance between supply and demand. To improve this problem, this study estimates the vacant taxi routing and converts the results into regional vacant time, which can be used as supply-side data for future study for hotspot identification. This study establishes two estimation methods based on the new-designed taxi fare meters data and factors that will affect taxi demand, and then converts the result into vacant time by time period and region. In this study, the data of satellite taxicab are used to verify the accuracy. The results show that the method proposed in this study can estimate vacant time with accuracy within reasonable range.