Ruiz de Gauna David Eneko, Sánchez Luís Enrique, Ruiz-Iniesta Almudena
International University of La Rioja, Logroño, La Rioja, Spain.
University of Castilla-La Mancha, Ciudad Real, Castilla-La Mancha, Spain.
PeerJ Comput Sci. 2023 Aug 23;9:e1534. doi: 10.7717/peerj-cs.1534. eCollection 2023.
The environmental damage caused by air pollution has recently become the focus of city council policies. The concept of the green city has emerged as an urban solution by which to confront environmental challenges worldwide and is founded on air pollution levels that have increased meaningfully as a result of traffic in urban areas. Local governments are attempting to meet environmental challenges by developing public traffic policies such as air pollution protocols. However, several problems must still be solved, such as the need to link smart cars to these pollution protocols in order to find more optimal routes. We have, therefore, attempted to address this problem by conducting a study of local policies in the city of Madrid (Spain) with the aim of determining the importance of the vehicle routing problem (VRP), and the need to optimise a set of routes for a fleet. The results of this study have allowed us to propose a framework with which to dynamically implement traffic constraints. This framework consists of three main layers: the data layer, the prediction layer and the event generation layer. With regard to the data layer, a dataset has been generated from traffic data concerning the city of Madrid, and deep learning techniques have then been applied to this data. The results obtained show that there are interdependencies between several factors, such as weather conditions, air quality and the local event calendar, which have an impact on drivers' behaviour. These interdependencies have allowed the development of an ontological model, together with an event generation system that can anticipate changes and dynamically restructure traffic restrictions in order to obtain a more efficient traffic system. This system has been validated using real data from the city of Madrid.
空气污染造成的环境破坏最近已成为市议会政策的焦点。绿色城市的概念已作为一种城市解决方案出现，用以应对全球范围内的环境挑战，它基于城市地区交通导致空气污染水平显著上升的情况。地方政府正试图通过制定诸如空气污染协议等公共交通政策来应对环境挑战。然而，仍有几个问题有待解决，比如需要将智能汽车与这些污染协议相连接，以便找到更优路线。因此，我们试图通过对西班牙马德里市的地方政策进行研究来解决这个问题，目的是确定车辆路径规划问题（VRP）的重要性，以及为车队优化一组路线的必要性。这项研究结果使我们能够提出一个动态实施交通限制的框架。该框架由三个主要层次组成：数据层、预测层和事件生成层。关于数据层，已根据马德里市的交通数据生成了一个数据集，然后将深度学习技术应用于该数据。所得结果表明，天气状况、空气质量和当地活动日历等几个因素之间存在相互依存关系，这些因素会影响驾驶员的行为。这些相互依存关系促成了一个本体模型以及一个事件生成系统的开发，该系统能够预测变化并动态调整交通限制，以获得更高效的交通系统。该系统已使用马德里市的真实数据进行了验证。
