Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 16
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Solving the time capacitated arc routing problem under fuzzy and stochastic travel and service times

  • Martín, Xabier A.
  • Panadero, Javier
  • Peidro Payá, David|||0000-0001-8678-6881
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Stochastic, as well as fuzzy uncertainty, can be found in most real-world systems. Considering both types of uncertainties simultaneously makes optimization problems incredibly challenging. In this paper we propose a fuzzy simheuristic to solve the Time Capacitated Arc Routing Problem (TCARP) when the nature of the travel time can either be deterministic, stochastic or fuzzy. The main goal is to find a solution (vehicle routes) that minimizes the total time spent in servicing the required arcs. However, due to uncertainty, other characteristics of the solution are also considered. In particular, we illustrate how reliability concepts can enrich the probabilistic information given to decision-makers. In order to solve the aforementioned optimization problem, we extend the concept of simheuristic framework so it can also include fuzzy elements. Hence, both stochastic and fuzzy uncertainty are simultaneously incorporated into the CARP. In order to test our approach, classical CARP instances have been adapted and extended so that customers' demands become either stochastic or fuzzy. The experimental results show the effectiveness of the proposed approach when compared with more traditional ones. In particular, our fuzzy simheuristic is capable of generating new best-known solutions for the stochastic versions of some instances belonging to the tegl, tcarp, val, and rural benchmarks., Spanish Ministry of Science, Grant/Award Number: PID2019-111100RB-C21/AEI/10.13039/501100011033; Barcelona Council and the "la Caixa" Foundation under the framework of the Barcelona Science Plan 2020-2023, Grant/Award Number: 21S09355-001; Generalitat Valenciana,Grant/Award Number: PROMETEO/2021/065
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Enhancing Carsharing Experiences for Barcelona Citizens with Data Analytics and Intelligent Algorithms

  • Herrera, Erika M.
  • Calvet, Laura
  • Ghorbani, Elnaz
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Carsharing practices are spreading across many cities in the world. This paper analyzes real-life data obtained from a private carsharing company operating in the city of Barcelona, Spain. After describing the main trends in the data, machine learning and time-series analysis methods are employed to better understand citizens' needs and behavior, as well as to make predictions about the evolution of their demand for this service. In addition, an original proposal is made regarding the location of the pick-up points. This proposal is based on a capacitated dispersion algorithm, and aims at balancing two relevant factors, including scattering of pick-up points (so that most users can benefit from the service) and efficiency (so that areas with higher demand are well covered). Our aim is to gain a deeper understanding of citizens' needs and behavior in relation to carsharing services. The analysis includes three main components: descriptive, predictive, and prescriptive, resulting in customer segmentation and forecast of service demand, as well as original concepts for optimizing parking station location., This work has been partially funded by the Spanish Ministry of Science (PID2019-111100RB-C21 /AEI/ 10.13039/501100011033), as well as by the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Optimizing Energy Consumption in Smart Cities Mobility: Electric Vehicles, Algorithms, and Collaborative Economy

  • Ghorbani, Elnaz
  • Fluechter, Tristan
  • Calvet, Laura
  • Ammouriova, Majsa
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Mobility and transportation activities in smart cities require an increasing amount of energy. With the frequent energy crises arising worldwide and the need for a more sustainable and environmental friendly economy, optimizing energy consumption in these growing activities becomes a must. This work reviews the latest works in this matter and discusses several challenges that emerge from the aforementioned social and industrial demands. The paper analyzes how collaborative concepts and the increasing use of electric vehicles can contribute to reduce energy consumption practices, as well as intelligent x-heuristic algorithms that can be employed to achieve this fundamental goal. In addition, the paper analyzes computational results from previous works on mobility and transportation in smart cities applying x-heuristics algorithms. Finally, a novel computational experiment, involving a ridesharing example, is carried out to illustrate the benefits that can be obtained by employing these algorithms., This work has been partially funded by the Spanish Ministry of Science, Innovation, and Universities (PID2019-111100RB-C21-C22/AEI/10.13039/501100011033), the SEPIE Erasmus+ Program (2019-I-ES01-KA103-062602), the Barcelona City Council and Fundació ¿la Caixa¿ under the framework of the Barcelona Science Plan 2020-2023 (21S09355-001), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Solving Vehicle Routing Problems under Uncertainty and in Dynamic Scenarios: From Simheuristics to Agile Optimization

  • Ammouriova, Majsa
  • Herrera, Erika M.
  • Neroni, Mattia
  • Faulin, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Many real-life applications of the vehicle routing problem (VRP) occur in scenarios subject to uncertainty or dynamic conditions. Thus, for instance, traveling times or customers' demands might be better modeled as random variables than as deterministic values. Likewise, traffic conditions could evolve over time, synchronization issues should need to be considered, or a real-time re-optimization of the routing plan can be required as new data become available in a highly dynamic environment. Clearly, different solving approaches are needed to efficiently cope with such a diversity of scenarios. After providing an overview of current trends in VRPs, this paper reviews a set of heuristic-based algorithms that have been designed and employed to solve VRPs with the aforementioned properties. These include simheuristics for stochastic VRPs, learnheuristics and discrete-event heuristics for dynamic VRPs, and agile optimization heuristics for VRPs with real-time requirements., This work was partially funded by the Spanish Ministry of Science, Innovation, and Universities (PID2019-111100RB-C21-C22/AEI/10.13039/501100011033), the SEPIE Erasmus+ Program (2019-I-ES01-KA103-062602), the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (21S09355-001), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Battery Sharing: A Feasibility Analysis through Simulation

  • Neroni, Mattia
  • Herrera, Erika M.
  • Panadero, Javier
  • Ammouriova, Majsa
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Nowadays, several alternatives to internal combustion engines are being proposed in order to reduce CO2 emissions in freight transportation and citizen mobility. According to many experts, the use of electric vehicles constitutes one of the most promising alternatives for achieving the desirable reductions in emissions. However, popularization of these vehicles is being slowed by long recharging times and the low availability of recharging stations. One possible solution to this issue is to employ the concept of battery sharing or battery swapping. This concept is supported by important industrial partners, such as Eni in Italy, Ample in the US, and Shell in the UK. This paper supports the introduction of battery swapping practices by analyzing their effects. A discrete-event simulation model is employed for this study. The obtained results show that battery sharing practices are not just a more environmentally and socially friendly solution, but also one that can be highly beneficial for reducing traffic congestion., This work has been partially supported by the Barcelona City Council and la Caixa Foundation under the framework of the Barcelona Science Plan 2020-2023 (21S09355-001), and the Spanish Ministry of Science and Innovation (RED2022-134703-T, PID2019-111100RB-C21/AEI/ 10.13039/501100011033).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Join Operation for Semantic Data Enrichment of Asynchronous Time Series Data

  • García-Climent, Eloi
  • Peyman, Mohammad
  • Serrat, Carles
  • Xhafa, Fatos
[EN] In this paper, we present a novel framework for enriching time series data in smart cities by supplementing it with information from external sources via semantic data enrichment. Our methodology effectively merges multiple data sources into a uniform time series, while addressing difficulties such as data quality, contextual information, and time lapses. We demonstrate the efficacy of our method through a case study in Barcelona, which permitted the use of advanced analysis methods such as windowed cross-correlation and peak picking. The resulting time series data can be used to determine traffic patterns and has potential uses in other smart city sectors, such as air quality, energy efficiency, and public safety. Interactive dashboards enable stakeholders to visualize and summarize key insights and patterns., This work was partially funded by the Spanish Ministry of Science (PID2019-111100RB-C21/AEI/10.13039/501100011033), as well as by the Barcelona City Council and Fundació la Caixa under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Optimization of vehicular networks in smart cities: from agile optimization to learnheuristics and simheuristics

  • Peyman, Mohammad
  • Fluechter, Tristan
  • Panadero, Javier
  • Serrat, Carles
  • Xhafa, Fatos
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Vehicular ad hoc networks (VANETs) are a fundamental component of intelligent transportation systems in smart cities. With the support of open and real-time data, these networks of inter-connected vehicles constitute an 'Internet of vehicles' with the potential to significantly enhance citizens' mobility and last-mile delivery in urban, peri-urban, and metropolitan areas. However, the proper coordination and logistics of VANETs raise a number of optimization challenges that need to be solved. After reviewing the state of the art on the concepts of VANET optimization and open data in smart cities, this paper discusses some of the most relevant optimization challenges in this area. Since most of the optimization problems are related to the need for real-time solutions or to the consideration of uncertainty and dynamic environments, the paper also discusses how some VANET challenges can be addressed with the use of agile optimization algorithms and the combination of metaheuristics with simulation and machine learning methods. The paper also offers a numerical analysis that measures the impact of using these optimization techniques in some related problems. Our numerical analysis, based on real data from Open Data Barcelona, demonstrates that the constructive heuristic outperforms the random scenario in the CDP combined with vehicular networks, resulting in maximizing the minimum distance between facilities while meeting capacity requirements with the fewest facilities., This work has been partially funded by the Spanish Ministry of Science (PID2019-111100RB-C21 /AEI/ 10.13039/501100011033), as well as by the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A reliability-extended simheuristic for the sustainable vehicle routing problem with stochastic travel times and demands

  • Abdullahi, Hassana
  • Reyes-Rubiano, Lorena
  • Ouelhadj, Djamila
  • Faulin, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Real-life transport operations are often subject to uncertainties in travel time or customers' demands. Additionally, these uncertainties greatly impact the economic, environmental, and social costs of vehicle routing plans. Thus, analysing the sustainability costs of transportation activities and reliability in the presence of uncertainties is essential for decision makers. Accordingly, this paper addresses the Sustainable Vehicle Routing Problem with Stochastic Travel times and Demands. This paper proposes a novel weighted stochastic recourse model that models travel time and demand uncertainties. To solve this challenging problem, we propose an extended simheuristic that integrates reliability analysis to evaluate the reliability of the generated solutions in the presence of uncertainties. An extensive set of computational experiments is carried out to illustrate the potential of the proposed approach and analyse the influence of stochastic components on the different sustainability dimensions., This work has been developed by the University of Portsmouth, Cardiff Metropolitan University and partially supported by the SEPIE Erasmus+ Program (2019-I-ES01-KA103-062602) in collaboration with the Public University of Navarre, the Petroleum Technology Development Fund (PTDF/E/OSS/PHD/HAH/699/14), and the Spanish Ministry of Science and Innovation (PID2019-111100RB-C21-C22 /AEI/ 10.13039/ 501100011033, RED2018-102642-T, the Barcelona City Council and "La Caixa" (21S09355-001)).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Predictive Analyses of Traffic Level in the City of Barcelona: From ARIMA to eXtreme Gradient Boosting

  • García-Climent, Eloi
  • Calvet, Laura
  • Serrat, Carles
  • Peyman, Mohammad
  • Carracedo-Garnateo, Patricia|||0000-0002-9352-9565
  • Miró Martínez, Pau|||0000-0001-9573-9104
[EN] This study delves into the intricate dynamics of urban mobility, a pivotal aspect for policymakers, businesses, and communities alike. By deciphering patterns of movement within a city, stakeholders can craft targeted interventions to mitigate traffic congestion peaks, optimizing both resource allocation and individual travel routes. Focused on Barcelona, Spain, this paper draws on data sourced from the city council's open data service. Through a blend of exploratory analysis, visualization techniques, and modeling methodologies-including time series analysis and the eXtreme Gradient Boosting (XGBoost) algorithm-the research endeavors to forecast traffic conditions. Additionally, a study of variable importance is carried out, and Shapley Additive Explanations are applied to enhance the interpretability of model outputs. Findings underscore the limitations of traditional forecasting methods in capturing the nuanced spatial and temporal dependencies present in traffic flows, particularly over medium- to long-term horizons. However, the XGBoost model demonstrates robust performance, with the area under ROC curves consistently exceeding 80%, indicating its efficacy in handling non-linear traffic data variables., This work has been partially funded by the Spanish Ministry of Science (PID2019-111100RB-C21-C22/AEI/10.13039/501100011033), as well as by the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001). The authors appreciate the support received from the research group GRBIO under the grant 2021 SGR01421 from the Departament de Recerca i Universitats de la Generalitat de Catalunya (Spain).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Modeling and Optimization of NO2 Stations in the Smart City of Barcelona

  • Soriano-González, Raquel|||0000-0002-1337-9561
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Carracedo-Garnateo, Patricia|||0000-0002-9352-9565
  • Martín-Solano, Xabier Andoni
[EN] The growing problem of nitrogen dioxide (NO2 ) pollution in urban environments is driving cities to adopt smart and sustainable approaches to address this challenge. To quantify and compare the effect of environmental policies, cities must be able to make informed decisions with real-time data that reflect the actual situation. Therefore, the objective of this work is threefold: The first is to study the behavior of the key performance indicator (KPI) of NO2 concentrations per station in Barcelona through exploratory analysis and clustering. The second is to predict NO2 concentration behavior, considering meteorological data. Lastly, a new distribution of current and new stations will be proposed using an optimization algorithm that maximizes the distance between them and covers the largest area of the city. As a result of this study, the importance of the location of measurement points and the need for better distribution in the city are highlighted. These new spatial distributions predict an 8% increase in NO2 concentrations. In conclusion, this study is a comprehensive tool for obtaining an accurate representation of NO2 concentrations in the city, contributing to informed decision-making, helping to improve air quality, and promoting a more sustainable urban environment., : This work has been partially funded by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00 and RED2022-134703-T), the project SUN (HORIZON-CL4-2022-HUMAN01-14-101092612), the project UP2030 (HORIZON-MISS-2021-CIT-02-01-101096405) as well as by the Barcelona City Council and Fundació la Caixa under the framework of the Barcelona Science Plan 2020 2023 (grant 21S09355-001). Funding for open access charge: CRUE-Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Determining Reliable Solutions for the Team Orienteering Problem with Probabilistic Delays

  • Herrera, Erika M.
  • Panadero, Javier
  • Carracedo-Garnateo, Patricia|||0000-0002-9352-9565
  • Juan, Angel A.|||0000-0003-1392-1776
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
[EN] In the team orienteering problem, a fixed fleet of vehicles departs from an origin depot towards a destination, and each vehicle has to visit nodes along its route in order to collect rewards. Typically, the maximum distance that each vehicle can cover is limited. Alternatively, there is a threshold for the maximum time a vehicle can employ before reaching its destination. Due to this driving range constraint, not all potential nodes offering rewards can be visited. Hence, the typical goal is to maximize the total reward collected without exceeding the vehicle's capacity. The TOP can be used to model operations related to fleets of unmanned aerial vehicles, road electric vehicles with limited driving range, or ride-sharing operations in which the vehicle has to reach its destination on or before a certain deadline. However, in some realistic scenarios, travel times are better modeled as random variables, which introduce additional challenges into the problem. This paper analyzes a stochastic version of the team orienteering problem in which random delays are considered. Being a stochastic environment, we are interested in generating solutions with a high expected reward that, at the same time, are highly reliable (i.e., offer a high probability of not suffering any route delay larger than a user-defined threshold). In order to tackle this stochastic optimization problem, which contains a probabilistic constraint on the random delays, we propose an extended simheuristic algorithm that also employs concepts from reliability analysis., This work has been partially funded by the Spanish Ministry of Science (PID2019-111100RBC21-C22/AEI/10.13039/501100011033), the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Optimizing Transport Logistics under Uncertainty with Simheuristics: Concepts, Review and Trends

  • Castaneda, Juliana
  • Ghorbani, Elnaz
  • Ammouriova, Majsa
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Background: Uncertainty conditions have been increasingly considered in optimization problems arising in real-life transportation and logistics activities. Generally, the analysis of complex systems in these non-deterministic environments is approached with simulation techniques. However, simulation is not an optimization tool. Hence, it must be combined with optimization methods when our goal is to: (i) minimize operating costs while guaranteeing a given quality of service; or (ii) maximize system performance using limited resources. When solving NP-hard optimization problems, the use of metaheuristics allows us to deal with large-scale instances in reasonable computation times. By adding a simulation layer to the metaheuristics, the methodology becomes a simheuristic, which allows the optimization element to solve scenarios under uncertainty. Methods: This paper reviews the indexed documents in Elsevier Scopus database of both initial as well as recent applications of simheuristics in the logistics and transportation field. The paper also discusses open research lines in this knowledge area. Results: The simheuristics approaches to solving NP-hard and large-scale combinatorial optimization problems under uncertainty scenarios are discussed, as they frequently appear in real-life applications in logistics and transportation activities. Conclusions: The way in which the different simheuristic components interact puts a special emphasis in the different stages that can contribute to make the approach more efficient from a computational perspective. There are several lines of research that are still open in the field of simheuristics., This work has been partially funded by the Spanish Ministry of Science (PID2019-111100RBC21-C22/AEI/10.13039/501100011033), the Barcelona City Council and Fundacio "la Caixa" under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Fuzzy Simheuristic for the Permutation Flow Shop Problem under Stochastic and Fuzzy Uncertainty

  • Castaneda, Juliana
  • Martín, Xabier A.
  • Ammouriova, Majsa
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Stochastic, as well as fuzzy uncertainty, can be found in most real-world systems. Considering both types of uncertainties simultaneously makes optimization problems incredibly challenging. In this paper, we analyze the permutation flow shop problem (PFSP) with both stochastic and fuzzy processing times. The main goal is to find the solution (permutation of jobs) that minimizes the expected makespan. However, due to the existence of uncertainty, other characteristics of the solution are also taken into account. In particular, we illustrate how survival analysis can be employed to enrich the probabilistic information given to decision-makers. To solve the aforementioned optimization problem, we extend the concept of a simheuristic framework so it can also include fuzzy elements. Hence, both stochastic and fuzzy uncertainty are simultaneously incorporated in the PFSP. In order to test our approach, classical PFSP instances have been adapted and extended, so that processing times become either stochastic or fuzzy. The experimental results show the effectiveness of the proposed approach when compared with more traditional ones., This work has been partially supported by the Spanish Ministry of Science (PID2019111100RB-C21/AEI/10.13039/501100011033), as well as by the Barcelona Council and the "la Caixa" Foundation under the framework of the Barcelona Science Plan 2020-2023 (grant 21S09355-001).
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Optimizing Energy Consumption in Smart Cities' Mobility, Electric Vehicles, Algorithms, and Collaborative Economy

  • Ghorbani, Elnaz|||0000-0001-7498-1030
  • Fluechter, Tristan
  • Calvet, Laura|||0000-0001-8425-1381
  • Ammouriova, Majsa|||0000-0002-6118-0389
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
Mobility and transportation activities in smart cities require an increasing amount of energy. With the frequent energy crises arising worldwide and the need for a more sustainable and environmental friendly economy, optimizing energy consumption in these growing activities becomes a must. This work reviews the latest works in this matter and discusses several challenges that emerge from the aforementioned social and industrial demands. The paper analyzes how collaborative concepts and the increasing use of electric vehicles can contribute to reduce energy consumption practices, as well as intelligent x-heuristic algorithms that can be employed to achieve this fundamental goal. In addition, the paper analyzes computational results from previous works on mobility and transportation in smart cities applying x-heuristics algorithms. Finally, a novel computational experiment, involving a ridesharing example, is carried out to illustrate the benefits that can be obtained by employing these algorithms.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Enhancing Carsharing Experiences for Barcelona Citizens with Data Analytics and Intelligent Algorithms

  • Herrera, Erika M.|||0000-0001-9905-2203
  • Calvet, Laura|||0000-0001-8425-1381
  • Ghorbani, Elnaz|||0000-0001-7498-1030
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
Carsharing practices are spreading across many cities in the world. This paper analyzes real-life data obtained from a private carsharing company operating in the city of Barcelona, Spain. After describing the main trends in the data, machine learning and time-series analysis methods are employed to better understand citizens' needs and behavior, as well as to make predictions about the evolution of their demand for this service. In addition, an original proposal is made regarding the location of the pick-up points. This proposal is based on a capacitated dispersion algorithm, and aims at balancing two relevant factors, including scattering of pick-up points (so that most users can benefit from the service) and efficiency (so that areas with higher demand are well covered). Our aim is to gain a deeper understanding of citizens' needs and behavior in relation to carsharing services. The analysis includes three main components: descriptive, predictive, and prescriptive, resulting in customer segmentation and forecast of service demand, as well as original concepts for optimizing parking station location.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Predictive Analyses of Traffic Level in the City of Barcelona, From ARIMA to eXtreme Gradient Boosting

  • Garcia, Eloi|||0000-0002-9503-5091
  • Calvet, Laura|||0000-0001-8425-1381
  • Carracedo, Patricia|||0000-0002-9352-9565
  • Serrat, Carles|||0000-0002-1504-5354
  • Miró, Pau
  • Peyman, Mohammad|||0000-0003-4734-2414
This study delves into the intricate dynamics of urban mobility, a pivotal aspect for policymakers, businesses, and communities alike. By deciphering patterns of movement within a city, stakeholders can craft targeted interventions to mitigate traffic congestion peaks, optimizing both resource allocation and individual travel routes. Focused on Barcelona, Spain, this paper draws on data sourced from the city council's open data service. Through a blend of exploratory analysis, visualization techniques, and modeling methodologies-including time series analysis and the eXtreme Gradient Boosting (XGBoost) algorithm-the research endeavors to forecast traffic conditions. Additionally, a study of variable importance is carried out, and Shapley Additive Explanations are applied to enhance the interpretability of model outputs. Findings underscore the limitations of traditional forecasting methods in capturing the nuanced spatial and temporal dependencies present in traffic flows, particularly over medium- to long-term horizons. However, the XGBoost model demonstrates robust performance, with the area under ROC curves consistently exceeding 80%, indicating its efficacy in handling non-linear traffic data variables.