基於蜂巢網路資料之交通資訊估計方法

Abstract

近年來隨著經濟的快速發展及科技的進步，智慧型運輸系統(Intelligent Transportation System, ITS)透過先進科技的協助，獲得了有效的改善。其中，運用基於細胞流動車輛資料(Cellular Floating Vehicle Data, CFVD)的方式來產生交通資訊將可以比傳統的方式有更好的成本效益。本研究提出三種車速估計方法(包含有交遞基礎(Handover (HO)-based)方法、指紋定位演算法基礎(Fingerprint Positioning Algorithm (FPA)-based)方法、蜂巢探針基礎(Cell Probe (CP)-based)方法)來分析蜂巢網路訊號。並且，提出數個分析模型估計蜂巢網路訊號(如：接收訊號強度(Received Signal Strength Indication, RSSI)、通話到達(Call Arrival, CA)、交遞(HO)、一般性位置更新(Normal Location Update, NLU)、週期性位置更新(Periodic Location Update, PLU))和交通資訊(如：交通流量、交通密度、車速)之間的關聯來取得交通資訊。在實驗中，本研究根據高速公路上車輛偵測器(Vehicle Detector, VD)的資料來比較真實的交通資訊和估計的交通資訊。由實驗結果顯示，本研究提出之蜂巢探針基礎方法的車速估計正確率可以達到97.48%，其正確率比交遞基礎方法和指紋定位演算法基礎方法高。因此，蜂巢探針基礎方法將可以分析基於細胞流動車輛資料來提供即時且可靠的車速資訊，予以用路人參考。

Information and communication technologies have improved the quality of Intelligent Transportation Systems (ITS). By estimating from Cellular Floating Vehicle Data (CFVD) is more cost-effective, and easier to acquire than traditional ways. This study proposes three vehicle speed estimation methods which include Handover (HO)-based method, Fingerprint Positioning Algorithm (FPA)-based method, and Cell Probe (CP)-based method to analyze the cellular network signalings. Moreover, some analytical models are proposed to evaluate the ration of cellular network signalings (e.g., received signal strength indication, call arrival, HO, normal location update, and periodic location update) and traffic information (e.g., traffic flow, traffic density, and vehicle speed). In experiments, this study compares the real traffic information of Vehicle Detector (VD) with the estimated traffic information by the proposed methods. The experiment results show that the accuracy of vehicle speed estimation by CP-based method which is 97.48% is higher than HO-based method and FPA-based method. Therefore, the CP-based method can be used to estimate vehicle speed from CFVD for ITS.