J. F. Sánchez-Rada, Raquel Vila-Rodríguez, Jesús Montes, Pedro J. Zufiria
{"title":"预测城市图谱中车队的总体流动性","authors":"J. F. Sánchez-Rada, Raquel Vila-Rodríguez, Jesús Montes, Pedro J. Zufiria","doi":"10.3390/a17040166","DOIUrl":null,"url":null,"abstract":"Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":" 35","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph\",\"authors\":\"J. F. Sánchez-Rada, Raquel Vila-Rodríguez, Jesús Montes, Pedro J. Zufiria\",\"doi\":\"10.3390/a17040166\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.\",\"PeriodicalId\":502609,\"journal\":{\"name\":\"Algorithms\",\"volume\":\" 35\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-04-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Algorithms\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/a17040166\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Algorithms","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/a17040166","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
在诸如打车等领域,预测车辆的流动性至关重要,因为在这些领域,供需平衡是最重要的。由于城市道路网络可以很容易地表示为图,最近的研究利用图神经网络(GNN)对真实交通数据进行了更准确的预测。然而,我们需要更好地了解这种方法的特点和局限性。在这项工作中,我们在一个非常受限和受控的模拟场景中,将几种 GNN 聚合流动性预测方案与其他一些方法进行了比较。采用的城市图将道路表示为有向边,将道路交叉口表示为节点。单个车辆的流动性被模拟为图中节点之间的转换。通过计算任意给定时间内每个节点上的车辆数,计算出总流动性的时间序列。构建综合流动性预测器主要采用三种方法。首先,假定移动个体的行为遵循马尔可夫链(MC)模型,该模型的转换矩阵通过最小二乘估算程序进行推断;该 MC 的循环应用提供了聚集移动预测值。其次,对多层感知器(MLP)进行训练,使其能够根据给定时间内的节点占据情况,递归预测时间序列的下一个值。第三,我们通过有监督的学习方法,用时间序列数据训练一个 GNN(根据城市图),通过对图中每个节点的嵌入构造,计算出综合流动预测值。在城市中模拟一些流动模式,生成不同的时间序列进行测试。建议的方案与不同的基准预测程序进行了比较评估。比较结果说明了 GNN 方法在所选场景中的一些局限性,并揭示了未来的研究方向。
Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph
Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.