Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 33
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Sim-Learnheuristic for the Team Orienteering Problem, Applications to Unmanned Aerial Vehicles

  • Peyman, Mohammad|||0000-0003-4734-2414
  • Martin, Xabier A.|||0000-0003-4182-0120
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
In this paper, we introduce a novel sim-learnheuristic method designed to address the team orienteering problem (TOP) with a particular focus on its application in the context of unmanned aerial vehicles (UAVs). Unlike most prior research, which primarily focuses on the deterministic and stochastic versions of the TOP, our approach considers a hybrid scenario, which combines deterministic, stochastic, and dynamic characteristics. The TOP involves visiting a set of customers using a team of vehicles to maximize the total collected reward. However, this hybrid version becomes notably complex due to the presence of uncertain travel times with dynamically changing factors. Some travel times are stochastic, while others are subject to dynamic factors such as weather conditions and traffic congestion. Our novel approach combines a savings-based heuristic algorithm, Monte Carlo simulations, and a multiple regression model. This integration incorporates the stochastic and dynamic nature of travel times, considering various dynamic conditions, and generates high-quality solutions in short computational times for the presented problem.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Forward-Backward Simheuristic for the Stochastic Capacitated Dispersion Problem

  • Gómez González, Juan Francisco|||0000-0001-7692-9922
  • Martínez-Gavara, Anna|||0000-0001-9995-010X
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A|||0000-0003-1392-1776
  • Martí, Rafael|||0000-0001-7265-823X
In an effort to balance the distribution of services across a given territory, dispersion and diversity models typically aim to maximize the minimum distance between any pair of facilities. Specifically, in the capacitated dispersion problem (CDP), each facility has an associated capacity or level of service, and the objective is to select a set of facilities so that the minimum distance between any pair of them (dispersion) is maximized, while ensuring a user-defined level of service. This problem can be formulated as a linear integer model, where the sum of the capacities of the selected facilities must match or exceed the total demand in the network. Real-life applications often necessitate considering the levels of uncertainty affecting the capacity of the nodes. Failure to account for this uncertainty could lead to low-quality or infeasible solutions in practical scenarios. However, research addressing the stochastic version of the CDP is scarce. This paper introduces two models for the CDP with stochastic capacities, incorporating soft constraints and penalty costs for violating the total capacity constraint. The first model includes a probabilistic constraint to ensure the required level of service with a certain probability, while the second model introduces a soft constraint with penalty costs for violations. To solve both variants of the model, a forward-backward simheuristic algorithm is proposed. Our approach combines a metaheuristic algorithm with Monte Carlo simulation, enabling the efficient handling of the random behavior of node capacities and obtaining reliable solutions regardless of their probability distribution.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm Based on Thompson Sampling for the Heterogeneous and Dynamic Team Orienteering Problem

  • Rodríguez Uguina, Antonio|||0009-0001-5506-1674
  • Gómez González, Juan Francisco|||0000-0001-7692-9922
  • Panadero, Javier|||0000-0002-3793-3328
  • Martínez-Gavara, Anna|||0000-0001-9995-010X
  • Juan, Ángel A|||0000-0003-1392-1776
The team orienteering problem (TOP) is a well-studied optimization challenge in the field of Operations Research, where multiple vehicles aim to maximize the total collected rewards within a given time limit by visiting a subset of nodes in a network. With the goal of including dynamic and uncertain conditions inherent in real-world transportation scenarios, we introduce a novel dynamic variant of the TOP that considers real-time changes in environmental conditions affecting reward acquisition at each node. Specifically, we model the dynamic nature of environmental factors-such as traffic congestion, weather conditions, and battery level of each vehicle-to reflect their impact on the probability of obtaining the reward when visiting each type of node in a heterogeneous network. To address this problem, a learnheuristic optimization framework is proposed. It combines a metaheuristic algorithm with Thompson sampling to make informed decisions in dynamic environments. Furthermore, we conduct empirical experiments to assess the impact of varying reward probabilities on resource allocation and route planning within the context of this dynamic TOP, where nodes might offer a different reward behavior depending upon the environmental conditions. Our numerical results indicate that the proposed learnheuristic algorithm outperforms static approaches, achieving up to 25% better performance in highly dynamic scenarios. Our findings highlight the effectiveness of our approach in adapting to dynamic conditions and optimizing decision-making processes in transportation systems.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

An Agile Adaptive Biased-Randomized Discrete-Event Heuristic for the Resource-Constrained Project Scheduling Problem

  • Martin, Xabier A.|||0000-0003-4182-0120
  • Herrero, Rosa|||0000-0003-3575-0963
  • Juan, Ángel A|||0000-0003-1392-1776
  • Panadero, Javier|||0000-0002-3793-3328
In industries such as aircraft or train manufacturing, large-scale manufacturing companies often manage several complex projects. Each of these projects includes multiple tasks that share a set of limited resources. Typically, these tasks are also subject to time dependencies among them. One frequent goal in these scenarios is to minimize the makespan, or total time required to complete all the tasks within the entire project. Decisions revolve around scheduling these tasks, determining the sequence in which they are processed, and allocating shared resources to optimize efficiency while respecting the time dependencies among tasks. This problem is known in the scientific literature as the Resource-Constrained Project Scheduling Problem (RCPSP). Being an NP-hard problem with time dependencies and resource constraints, several optimization algorithms have already been proposed to tackle the RCPSP. In this paper, a novel discrete-event heuristic is introduced and later extended into an agile biased-randomized algorithm complemented with an adaptive capability to tune the parameters of the algorithm. The results underscore the effectiveness of the algorithm in finding competitive solutions for this problem within short computing times.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A discrete-event simheuristic for enhancing urban mobility

  • Peyman, Mohammad|||0000-0003-4734-2414
  • Martin, Xabier A.|||0000-0003-4182-0120
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A|||0000-0003-1392-1776
This paper addresses a rich variant of the team orienteering problem under uncertainty to improve urban mobility. Specifically, we conduct a case study using real-world data from urban transportation hubs in Barcelona, gathered from Open Data Barcelona. The study involves routing autonomous delivery drones operating within a university campus to deliver items to designated drop-off points. Traditional optimization techniques often fail to account for the stochastic fluctuations inherent in urban traffic and the complex interactions between various transportation activities. To address these challenges, this research employs a simheuristic framework that combines heuristic optimization with commercial simulation software to replicate the dynamic and uncertain nature of urban environments accurately. The efficiency and practical applicability of our simheuristic framework are demonstrated through comprehensive computational experiments in a real-world context.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Biased-Randomized Iterated Local Search with Round-Robin for the Periodic Vehicle Routing Problem

  • Gómez González, Juan Francisco|||0000-0001-7692-9922
  • Rodríguez Uguina, Antonio
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
The periodic vehicle routing problem (PVRP) is a well-known challenge in real-life logistics, requiring the planning of vehicle routes over multiple days while enforcing visitation frequency constraints. Although numerous metaheuristic and exact methods have tackled various PVRP extensions, real-world settings call for additional features such as depot configurations, tight visitation frequency constraints, and heterogeneous fleets. In this paper, we present a two-phase biased-randomized algorithm that addresses these complexities. In the first phase, a round-robin assignment quickly generates feasible and promising solutions, ensuring each customer's frequency requirement is met across the multi-day horizon. The second phase refines these assignments via an iterative search procedure, improving route efficiency and reducing total operational costs. Extensive experimentation on standard PVRP benchmarks shows that our approach is able to generate solutions of comparable quality to established state-of-the-art algorithms in relatively low computational times and stands out in many instances, making it a practical choice for real life multi-day vehicle routing applications.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A biased-randomised iterated local search for the team orienteering arc routing problem allowing different origin and destination

  • Martín, Xabier A.
  • Keenan, Peter
  • Panadero, Javier
  • McGarraghy, Sean
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In this paper, we consider the hybridisation of the team orienteering problem and the arc routing problem, the so-called team orienteering arc routing problem (TOARP). This problem has recently raised interest among researchers and practitioners as it can model new routing problems involving unmanned aerial vehicles or other types of electric vehicles. In the TOARP, a fixed fleet of vehicles, initially located at a depot, has to collect as much reward as possible from visiting a set of arcs, while they must visit a set of required arcs. At the same time, they must return to the depot on or before a given deadline (which can be time-based or distance-based). In this paper, we explore an extension of the TOARP in which the origin depot and the destination depot may be different nodes in a network. To solve this version of the problem, we propose a novel biased-randomised iterated local search algorithm. Computational results show the capability, efficiency and robustness of our approach, which provides competitive solutions to the TOARP in short computing times and outperforms some of the best-known solution approaches in the literature., This work has been partially supported by the Spanish Ministry of Science (PID2022-138860NB-I00, RED2022-134703-T) and the Horizon Europe program (SUN HORIZON-CL4-2022-HUMAN-01-14-101092612). In addition, we would like to acknowledge the support provided by the Michael Smurfit Graduate Business School at University College Dublin.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Analysis of Blockchain Applications in the Supply Chain Field

  • Ponce, Erick
  • Mula, Josefa|||0000-0002-8447-3387
  • Peidro Payá, David|||0000-0001-8678-6881
[EN] The purpose of this paper is to analyse the most important research into the application of blockchain in the supply chains field, the implication of this new technology, the solutions or facilities that it can offer, the symbiosis with other technologies like the Internet of Things (IoT), enterprise resource planning (ERP), customer relationship management (CRM), among others, to address problems by identifying the main approaches and applied tools, implementation and validation, and the direction in which future research will move., This research has received financial support by the i4OPT project (Ref. PROMETEO/2021/065) granted by the Valencian Regional Government; the CADS4.0-II project (Ref. PDC2022 133957-I00) funded by MCIN/AEI /https://doi.org/10.13039/501100011033 and by European Union Next Generation EU/PRTR; and the Horizon Europe Research & Innovation Programme under grant agreement 101092612 (SUN project).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

An Agile Adaptive Biased-Randomized Discrete-Event Heuristic for the Resource-Constrained Project Scheduling Problem

  • Martín, Xabier A.
  • Herrero, Rosa
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In industries such as aircraft or train manufacturing, large-scale manufacturing companies often manage several complex projects. Each of these projects includes multiple tasks that share a set of limited resources. Typically, these tasks are also subject to time dependencies among them. One frequent goal in these scenarios is to minimize the makespan, or total time required to complete all the tasks within the entire project. Decisions revolve around scheduling these tasks, determining the sequence in which they are processed, and allocating shared resources to optimize efficiency while respecting the time dependencies among tasks. This problem is known in the scientific literature as the Resource-Constrained Project Scheduling Problem (RCPSP). Being an NP-hard problem with time dependencies and resource constraints, several optimization algorithms have already been proposed to tackle the RCPSP. In this paper, a novel discrete-event heuristic is introduced and later extended into an agile biased-randomized algorithm complemented with an adaptive capability to tune the parameters of the algorithm. The results underscore the effectiveness of the algorithm in finding competitive solutions for this problem within short computing times., This work has been partially funded by the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612 SUN and HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294 AIDEAS), as well as by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Extended reality and metaverse technologies for industrial training, safety and social interaction

  • Mula, Josefa|||0000-0002-8447-3387
  • Sanchis, R.|||0000-0002-5495-3339
  • Torre-Martínez, María Rocío de la|||0000-0002-8662-8901
  • Becerra-Muñoz, Pablo
[EN] The metaverse concept has become much more relevant in recent years. The three pillars of industrial training, safety, and social interaction are the framework around which this article organises evaluates research into extended reality and metaverse technologies. It illustrates how diverse approaches may be used across various applications by highlighting its potential to enhance knowledge acquisition, work protection and well-being, and social engagement in industrial settings. To fully realise the potential of metaverse technologies, further study is necessary to address identified problems, including privacy concerns and the need for adapted policies to guarantee successful acceptance and implementation., This work has been supported by the European Commission SUN HORIZON- CL4 - 2022 - HUMAN - 01 - 14 -101092612 project entitled: Social and hUman ceNtered XR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Biased-Randomized Discrete Event Algorithm to Improve the Productivity of Automated Storage and Retrieval Systems in the Steel Industry

  • Neroni, Mattia
  • Bertolini, Massimo
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In automated storage and retrieval systems (AS/RSs), the utilization of intelligent algorithms can reduce the makespan required to complete a series of input/output operations. This paper introduces a simulation optimization algorithm designed to minimize the makespan in a realistic AS/RS commonly found in the steel sector. This system includes weight and quality constraints for the selected items. Our hybrid approach combines discrete event simulation with biased-randomized heuristics. This combination enables us to efficiently address the complex time dependencies inherent in such dynamic scenarios. Simultaneously, it allows for intelligent decision making, resulting in feasible and high-quality solutions within seconds. A series of computational experiments illustrates the potential of our approach, which surpasses an alternative method based on traditional simulated annealing., This work was partially funded by the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612 SUN and HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294 AIDEAS), as well as by the Generalitat Valenciana (PROMETEO/2021/065)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Computer-Supported Strategic Decision Making for Ecosystems Creation

  • Rodriguez-Garcia, Patricia
  • López-López, David
  • Martin, Jon A.
  • Carracedo-Garnateo, Patricia|||0000-0002-9352-9565
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In the corporate strategy arena, the concept of ecosystems has emerged as a transformative approach to promote competitive advantage, growth, and innovation. Corporate ecosystems enable companies to benefit from interconnections among diverse partners, products, and services to deliver enhanced value to customers. However, the process of ecosystem creation represents a significant challenge for CEOs, as they must analyze a wide number of alternative sectors, partners, business cases, and other critical elements. Particularly, as it is a strategic decision, it lies beyond the traditional approach of risk-return by incorporating other factors, e.g.: the feasibility, desirability and sustainability of each alternative. This paper investigates how computer-supported optimization algorithms can help to solve the complex problem faced by CEOs when making these factors to create a successful and sustainable ecosystem. The paper shows how a CEO can make informed strategic decisions by identifying the best projects to include in the ecosystem portfolio, balancing financial risk and return with technical feasibility, customer appeal, and technical considerations., This work has been partially funded by the European Commission project SUN (HORIZON-CL4-2022-HUMAN-01-14-101092612) and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Tesis doctoral (DoctoralThesis)

Applications of X-Heuristics in Complex Combinatorial Optimization Problems

  • Martín Solano, Xabier Andoni
[ES] En muchas industrias, las empresas deben tomar decisiones en situaciones complejas con múltiples variables y restricciones. Estas situaciones a menudo pueden formularse como problemas de optimización combinatoria (COPs). Resolver estos problemas es esencial para mejorar la productividad y la eficiencia. Sin embargo, esto implica encontrar soluciones óptimas, lo cual puede ser extremadamente desafiante debido a la naturaleza \textit{NP-hard} de algunos problemas. Esta tesis propone diferentes \textit{x}-heurísticas para abordar las limitaciones de los enfoques existentes en la resolución de varios COPs. Estas metodologías incluyen diversas extensiones de algoritmos heurísticos, dependiendo de los requisitos específicos del problema. Concretamente, las heurísticas con sesgo aleatorizado combinan algoritmos heurísticos con técnicas de sesgo aleatorizado para resolver problemas con parámetros deterministas. Las heurísticas de eventos discretos combinan algoritmos heurísticos con simulación de eventos discretos para abordar problemas con cuestiones de sincronización, mientras que los métodos de optimización ágil resuelven problemas con restricciones de tiempo real. Las simheurísticas abordan problemas con incertidumbre estocástica, combinando algoritmos heurísticos con simulación. Esto se extiende a las fuzzy-simheurísticas mediante lógica difusa para resolver problemas con incertidumbre estocástica y no estocástica. Además, esta tesis propone una nueva metodología llamada sim-learnheurísticas para resolver problemas con incertidumbre estocástica y factores dinámicos, que combina algoritmos heurísticos, simulación y métodos de aprendizaje automático. El rendimiento de estas metodologías se valida a través de extensos experimentos computacionales. Los resultados destacan su eficiencia en términos de calidad de solución y tiempo computacional, así como su fiabilidad en la resolución de problemas con múltiples variables y restricciones. Finalmente, las futuras líneas de investigación discuten metodologías de optimización en tiempo real para la toma de decisiones inmediatas en contextos dinámicos., [CA] En moltes indústries, les empreses han de prendre decisions en situacions complexes amb múltiples variables i restriccions. Aquestes situacions sovint poden formular-se com a problemes d'optimització combinatòria (COPs). Resoldre aquests problemes és essencial per a millorar la productivitat i l'eficiència. No obstant això, tot allò implica trobar solucions òptimes, la qual cosa pot ser extremadament desafiant a causa de la naturalesa \textit{NP-hard} d'alguns problemes. Aquesta tesi proposa diferents \textit{x}-heurístiques per a abordar les limitacions dels enfocaments existents en la resolució de diversos COPs. Aquestes metodologies inclouen diverses extensions d'algorismes heurístics, segons els requisits específics del problema. Concretament, les heurístiques amb esbiaix aleatoritzat combinen algorismes heurístics amb tècniques d'esbiaix aleatoritzat per a resoldre problemes amb paràmetres deterministes. Les heurístiques d'esdeveniments discrets combinen algorismes heurístics amb simulació d'esdeveniments discrets per a abordar problemes amb qüestions de sincronització, mentre que els mètodes d'optimització àgil resolen problemes amb restriccions de temps real. Les simheurístiques aborden problemes amb incertesa estocàstica, combinant algorismes heurístics amb simulació. Això s'estén a les fuzzy-simheurístiques mitjançant lògica difusa per a resoldre problemes amb incertesa estocàstica i no estocàstica. A més, aquesta tesi proposa una metodologia innovadora anomenada sim-learnheurístiques per a resoldre problemes amb incertesa estocàstica i factors dinàmics, que combina algorismes heurístics, simulació i mètodes d'aprenentatge automàtic. El rendiment d'aquestes metodologies es valida a través d'extensos experiments computacionals. Els resultats destaquen la seua eficiència en termes de qualitat de solució i temps computacional, així com la seua fiabilitat en la resolució de problemes amb múltiples variables i restriccions. Finalment, les futures línies d'investigació discuteixen metodologies d'optimització en temps real per la presa de decisions immediates en contextos dinàmics., [EN] In many industries, businesses need to make decisions in complex situations with multiple variables and constraints. These situations can often be formulated as combinatorial optimization problems (COPs). Solving these problems is essential to improve productivity and efficiency. However, this involves finding optimal solutions, which can be extremely challenging due to the \textit{NP-hard} nature of some problems. This thesis proposes different \textit{x}-heuristics to address the limitations of existing approaches for solving several COPs. These methodologies comprise different extensions of heuristic algorithms depending on the specific requirements of the problem. Specifically, biased-randomized heuristics combine heuristic algorithms with biased-randomization techniques to solve problems with deterministic parameters. Discrete-event heuristics combine heuristic algorithms with discrete-event simulation to address problems with synchronization issues, while agile optimization methods solve problems with real-time constraints. Simheuristics address problems with stochastic uncertainty, which combine heuristic algorithms with simulation. This is extended to fuzzy-simheuristics using fuzzy logic to solve problems with stochastic and non-stochastic uncertainty. In addition, this thesis proposes a novel methodology called sim-learnheuristics to solve problems with stochastic uncertainty and dynamic factors, which combines heuristic algorithms, simulation, and machine learning methods. The performance of these methodologies is validated through extensive computational experiments. The results highlight their efficiency in terms of solution quality and computational time, as well as their reliability in solving problems with multiple variables and constraints. Lastly, future research directions discuss real-time optimization methodologies for immediate decision-making capabilities in dynamic contexts., Finally, I wish to acknowledge the essential support provided by the projects that have been instrumental in advancing this work: the Social and hUman ceNtered XR project (Horizon 2020 Europe program, HORIZON-CL4-2022-HUMAN01-14-101092612) and the Red Española de Transporte, Inteligencia Artificial, y Analítica de Datos (Agencia Estatal de Investigación, Redes de Investigación). And, of course, to the star that guides me and helps me grow not only as an academic but also as a person.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Impact of generative artificial intelligence on workload, efficiency and labour productivity

  • Caamaño-Gordillo, Daniel
  • Mula, Josefa|||0000-0002-8447-3387
  • Torre-Martínez, María Rocío de la|||0000-0002-8662-8901
[EN] In recent years, generative artificial intelligence (GAI) has gained significant importance in production and operations management (POM) due to its potential to enhance worker productivity. This article aims to characterise the impact of GAI on workload, efficiency and labour productivity across various industries. The research question was formulated and, using the CIMO framework (context, intervention, mechanism, outcome), the search and retrieval of articles were conducted in the Scopus and Web of Science (WoS) databases, and yielded 149 articles. After the selection, evaluation and content analysis of each study, 74 articles were ultimately included in the systematic literature review. Seven industries were identified in which GAI has demonstrated impacts on workload, efficiency and labour productivity, with four sectors accounting for 80% of the studies. The impacts of GAI reveal four trends, all of them key in POM: automation and optimisation of workflows; support in decision making; improvement in human-machine interactions; enhancement in communication. To fully apply the potential of this technology, it is necessary to continue researching and addressing the identified issues, including ethical, employment, privacy and information quality challenges., This work has been supported by Horizon Europe Framework Programme (HORIZON) with grant agreements: 101092612 Social and hUman ceNtered XR (SUN XR); and 101177842 Unified Modelling and Automated Scheduling for Manufacturing as a Service (UniMaaS).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm for the Capacitated Dispersion Problem with Dynamic Conditions

  • Gómez, Juan F.
  • Uguina, Antonio R.
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The capacitated dispersion problem, which is a variant of the maximum diversity problem, aims to determine a set of elements within a network. These elements could symbolize, for instance, facilities in a supply chain or transmission nodes in a telecommunication network. While each element typically has a bounded service capacity, in this research, we introduce a twist. The capacity of each node might be influenced by a random Bernoulli component, thereby rendering the possibility of a node having zero capacity, which is contingent upon a black box mechanism that accounts for environmental variables. Recognizing the inherent complexity and the NP-hard nature of the capacitated dispersion problem, heuristic algorithms have become indispensable for handling larger instances. In this paper, we introduce a novel approach by hybridizing a heuristic algorithm with reinforcement learning to address this intricate problem variant., This work has been partially funded by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T), by the SUN project of the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612), and by the i4OPT project of the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Metaverse in Higher Education

  • Sanchis, R.|||0000-0002-5495-3339
  • Mula, Josefa|||0000-0002-8447-3387
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Díaz-Madroñero Boluda, Francisco Manuel|||0000-0003-1693-2876
[EN] The metaverse has significantly changed higher education, providing immersive, interactive, and dynamic learning environments that go beyond the boundaries of the classroom. This emerging digital space includes virtual reality (VR), augmented reality (AR) and other immersive technologies to create virtual campuses, interactive simulations and experiential learning scenarios, fostering hands-on learning in virtual environments. The potential to enhance student engagement, promote collaboration and deliver personalised learning experiences is huge. This article reviews the potential of the metaverse in higher education, taking into account how these technologies can change teaching methodologies and reshape student experiences. The metaverse allows students to engage in real-world practical scenarios without physical constraints, facilitating deeper understanding through learning-by-doing approaches. It also offers opportunities for global collaboration, allowing students and lecturers to interact across geographical boundaries. The paper also reviews the main challenges associated with the adoption of the metaverse in academia and proposes strategies for integrating the metaverse into university curricula., This work has been supported by the European Commission SUN HORIZON- CL4 - 2022 - HUMAN - 01 - 14 -101092612 project entitled: Social and hUman ceNtered XR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm Based on Thompson Sampling for the Heterogeneous and Dynamic Team Orienteering Problem

  • Uguina, Antonio R.
  • Gomez, Juan F
  • Panadero, Javier
  • Martínez-Gavara, Anna
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The team orienteering problem (TOP) is a well-studied optimization challenge in the field of Operations Research, where multiple vehicles aim to maximize the total collected rewards within a given time limit by visiting a subset of nodes in a network. With the goal of including dynamic and uncertain conditions inherent in real-world transportation scenarios, we introduce a novel dynamic variant of the TOP that considers real-time changes in environmental conditions affecting reward acquisition at each node. Specifically, we model the dynamic nature of environmental factors-such as traffic congestion, weather conditions, and battery level of each vehicle-to reflect their impact on the probability of obtaining the reward when visiting each type of node in a heterogeneous network. To address this problem, a learnheuristic optimization framework is proposed. It combines a metaheuristic algorithm with Thompson sampling to make informed decisions in dynamic environments. Furthermore, we conduct empirical experiments to assess the impact of varying reward probabilities on resource allocation and route planning within the context of this dynamic TOP, where nodes might offer a different reward behavior depending upon the environmental conditions. Our numerical results indicate that the proposed learnheuristic algorithm outperforms static approaches, achieving up to 25% better performance in highly dynamic scenarios. Our findings highlight the effectiveness of our approach in adapting to dynamic conditions and optimizing decision-making processes in transportation systems., This work has been partially funded by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T) as well as by the SUN (HORIZON-CL4-2022-HUMAN01-14-101092612) and AIDEAS (HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294) projects of the Horizon Europe program.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations

  • Leon, Jonas F.
  • Li, Yuda
  • Martin, Xabier A.
  • Calvet, Laura
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator., This work has been supported by the European Commission (SUN HORIZON-CL4-2022-HUMAN-01-14-101092612 and AIDEAS HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294),FlexSim, Spindox, the Industrial Doctorate Program of the Catalan Government (2020-DI-116), and the Investigo Program of the Generalitat Valenciana (INVEST/2022/342).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning in a Dynamic Team Orienteering Problem with Electric Batteries

  • Ammouriova, Majsa
  • Guerrero, Antoni
  • Tsertsvadze, Verónika
  • Schumacher, Christin
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] This paper addresses the team orienteering problem (TOP) with vehicles equipped with electric batteries under dynamic travel conditions influenced by weather and traffic, which impact travel times between nodes and hence might have a critical effect on the battery capacity to cover the planned route. The study incorporates a novel approach for solving the dynamic TOP, comparing two solution methodologies: a merging heuristic and a reinforcement learning (RL) algorithm. The heuristic combines routes using calculated savings and a biased-randomized strategy, while the RL model leverages a transformer-based encoder-decoder architecture to sequentially construct solutions. We perform computational experiments on 50 problem instances, each subjected to 200 dynamic conditions, for a total of 10,000 problems solved. The results demonstrate that while the deterministic heuristic provides an upper bound for rewards, the RL model consistently yields robust solutions with lower variability under dynamic conditions. However, the dynamic heuristic, with a 20 s time limit for solving each instance, outperformed the RL model by 3.35% on average. The study highlights the trade-offs between solution quality, computational resources, and time when dealing with dynamic environments in the TOP., The present work has been partially funded by the Spanish Government (IA4TES project 'Artificial Intelligence for Sustainable Energy Transition'), the Spanish Ministry of Science-AEI (PID2022- 138860NB-I00 and RED2022-134703-T), as well as the European Commission (SUN HORIZON-CL4- 2022-HUMAN-01-14-101092612, AIDEAS HORIZON-CL4- 2021-TWIN-TRANSITION-01-07-101057294).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Biased-Randomized Iterated Local Search with Round-Robin for the Periodic Vehicle Routing Problem

  • Gomez, Juan F.
  • Antonio
  • Uguina, Antonio R.
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The periodic vehicle routing problem (PVRP) is a well-known challenge in real-life logistics, requiring the planning of vehicle routes over multiple days while enforcing visitation frequency constraints. Although numerous metaheuristic and exact methods have tackled various PVRP extensions, real-world settings call for additional features such as depot configurations, tight visitation frequency constraints, and heterogeneous fleets. In this paper, we present a two-phase biased-randomized algorithm that addresses these complexities. In the first phase, a round-robin assignment quickly generates feasible and promising solutions, ensuring each customer's frequency requirement is met across the multi-day horizon. The second phase refines these assignments via an iterative search procedure, improving route efficiency and reducing total operational costs. Extensive experimentation on standard PVRP benchmarks shows that our approach is able to generate solutions of comparable quality to established state-of-the-art algorithms in relatively low computational times and stands out in many instances, making it a practical choice for real life multi-day vehicle routing applications., This work was partially funded by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T) and by the SUN project of the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Smart Strategies for Project Scheduling: An Adaptive BR-DEH Approach

  • Martín, Xabier A.
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In recent years, management of multiple complex projects has become increasingly common among large-scale companies, posing significant challenges for company managers. These projects are often identified by numerous tasks that have precedence relations and share a set of limited resources. The main goal of project scheduling is to minimize the total time required to complete these projects. However, this requires careful consideration of resource allocation, careful scheduling choices, and exact sequencing to maximize efficiency while managing the complex interactions between task dependencies. A novel discrete-event heuristic is presented to solve this project scheduling problem, which is later extended into a probabilistic algorithm using biased-randomization techniques. In addition, an adaptive mechanism was introduced to tune the parameters of the algorithm for optimal scheduling in different problem instances. Computational results demonstrate the effectiveness of our approach, finding high-quality solutions for difficult problem sets in short computational times. This intuitive and efficient approach can empower company managers to efficiently improve operational efficiency, reduce project costs, and ultimately increase their business¿s success., This work was partially funded by the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication 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
Publication Artículo científico (JournalArticle)

Bibliometric Analysis of Immersive Technologies in Supply Chain Strategy: Knowledge-Based Systems Case

  • Andres, B.|||0000-0002-7920-7711
  • Torre-Martínez, María Rocío de la|||0000-0002-8662-8901
  • Mojica, Ana
[EN] This bibliometric analysis explores the application of immersive technologies in supporting strategic supply chain decisions. Emphasizing the impact in sustainability, human-centered, and antifragile, the study highlights the significance of collaborative approaches in enhancing supply chain strategies. The analysis reveals trends and research gaps, offering insights into the integration of advanced algorithms for sustainable, antifragility supply chain strategic decisions. This work contributes to a deeper understanding of how immersive technology development with knowledge-based tools can drive sustainable and antifragile supply chains at the strategic level of decision., The research leading to these results received funding from the Horizon Europe Research & Innovation Programme under grant agreement No. 101092612 Social and hUman ceNtered XR (SUN XR) and grant agreement No. 101070181 Autonomous and Selforganized Artificial Intelligent Orchestrator for a Greener Industry 4.0 (TALON).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Forward-Backward Simheuristic for the Stochastic Capacitated Dispersion Problem

  • Gómez, Juan F.
  • Martínez-Gavara, Anna
  • Panadero, Javier
  • Martí, Rafael
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In an effort to balance the distribution of services across a given territory, dispersion and diversity models typically aim to maximize the minimum distance between any pair of facilities. Specifically, in the capacitated dispersion problem (CDP), each facility has an associated capacity or level of service, and the objective is to select a set of facilities so that the minimum distance between any pair of them (dispersion) is maximized, while ensuring a user-defined level of service. This problem can be formulated as a linear integer model, where the sum of the capacities of the selected facilities must match or exceed the total demand in the network. Real-life applications often necessitate considering the levels of uncertainty affecting the capacity of the nodes. Failure to account for this uncertainty could lead to low-quality or infeasible solutions in practical scenarios. However, research addressing the stochastic version of the CDP is scarce. This paper introduces two models for the CDP with stochastic capacities, incorporating soft constraints and penalty costs for violating the total capacity constraint. The first model includes a probabilistic constraint to ensure the required level of service with a certain probability, while the second model introduces a soft constraint with penalty costs for violations. To solve both variants of the model, a forward¿backward simheuristic algorithm is proposed. Our approach combines a metaheuristic algorithm with Monte Carlo simulation, enabling the efficient handling of the random behavior of node capacities and obtaining reliable solutions regardless of their probability distribution., This work has been partially funded by the European Commission via projects UP2030 (HORIZON-MISS- 2021-CIT-02-01-101096405) and SUN (HORIZON-CL4- 2022-HUMAN-01-14- 101092612), as well as by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00 and RED2022-134703-T). The authors have been also supported by grant PID2021-125709OB-C21 funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe. They also received financial support from the Generalitat Valenciana (code CIAICO/2021/224).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Tokenized Markets Using Blockchain Technology: Exploring Recent Developments and Opportunities

  • Juan, Angel A.|||0000-0003-1392-1776
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Li, Yuda
  • Martín, Xabier A.
  • Ammouriova, Majsa
  • Barrios, Barry B.
[EN] The popularity of blockchain technology stems largely from its association with cryptocurrencies, but its potential applications extend beyond this. Fungible tokens, which are interchangeable, can facilitate value transactions, while smart contracts using non-fungible tokens enable the exchange of digital assets. Utilizing blockchain technology, tokenized platforms can create virtual markets that operate without the need for a central authority. In principle, blockchain technology provides these markets with a high degree of security, trustworthiness, and dependability. This article surveys recent developments in these areas, including examples of architectures, designs, challenges, and best practices (case studies) for the design and implementation of tokenized platforms for exchanging digital assets., This work has received financial support from the Horizon Europe Research & amp; Innovation Programme under Grant agreement N. 101092612 (Social and hUman ceNtered XR-SUN project), as well as from the Regional Department of Innovation, Universities, Science and Digital Society of the Generalitat Valenciana "Programa Investigo" (INVEST/2022/342), within the framework of the Plan de Recuperacion, Transformacion y Resiliencia funded by the European Union-NextGenerationEU.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Simulation of Heuristics for Automated Guided Vehicle Task Sequencing with Resource Sharing and Dynamic Queues

  • Leon, Jonas F.
  • Peyman, Mohammad
  • Martín, Xabier A.
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Automated guided vehicles (AGVs) stand out as a paradigmatic application of Industry 4.0, requiring the seamless integration of new concepts and technologies to enhance productivity while reducing labor costs, energy consumption, and emissions. In this context, specific industrial use cases can present a significant technological and scientific challenge. This study was inspired by a real industrial application for which the existing AGV literature did not contain an already well-studied solution. The problem is related to the sequencing of assigned tasks, where the queue formation dynamics and the resource sharing define the scheduling. The combinatorial nature of the problem requires the use of advanced mathematical tools such as heuristics, simulations, or a combination of both. A heuristic procedure was developed that generates candidate task sequences, which are, in turn, evaluated in a discrete-event simulation model developed in Simul8. This combined approach allows high-quality solutions to be generated and realistically evaluated, even graphically, by stakeholders and decision makers. A number of computational experiments were developed to validate the proposed method, which opens up some future lines of research, especially when considering stochastic settings., This work was supported by the European Commission (AIDEAS HORIZON-CL4-2021- TWIN-TRANSITION-01-07-101057294 and SUN HORIZON-CL4-2022-HUMAN-01-14-101092612), Simul8, Spindox, AGAUR (2020-DI-116), and the Spanish Ministry of Science and Innovation (PRE2020-091842).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A discrete-event simheuristic for enhancing urban mobility

  • Peyman, Mohammad
  • Martín, Xabier A.
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] This paper addresses a rich variant of the team orienteering problem under uncertainty to improve urban mobility. Specifically, we conduct a case study using real-world data from urban transportation hubs in Barcelona, gathered from Open Data Barcelona. The study involves routing autonomous delivery drones operating within a university campus to deliver items to designated drop-off points. Traditional optimization techniques often fail to account for the stochastic fluctuations inherent in urban traffic and the complex interactions between various transportation activities. To address these challenges, this research employs a simheuristic framework that combines heuristic optimization with commercial simulation software to replicate the dynamic and uncertain nature of urban environments accurately. The efficiency and practical applicability of our simheuristic framework are demonstrated through comprehensive computational experiments in a real-world context., This work was partially funded by the Spanish Ministry of Science and Innovation (PRE2020-091842, PID2022-138860NB-I00, RED2022-134703-T) and the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning to Solve a Dynamic Orienteering Problem with Random Rewards Affected by the Battery Status

  • Juan, Angel A.|||0000-0003-1392-1776
  • Marugan, Carolina A.
  • Ahsini, Yusef
  • Fornes, Rafael
  • Panadero, Javier
  • Martín, Xabier A.
[EN] This paper discusses an orienteering optimization problem where a vehicle using electric batteries must travel from an origin depot to a destination depot while maximizing the total reward collected along its route. The vehicle must cross several consecutive regions, with each region containing different types of charging nodes. A charging node has to be selected in each region, and the reward for visiting each node¿in terms of a `satisfactory¿ charging process¿is a binary random variable that depends upon dynamic factors such as the type of charging node, weather conditions, congestion, battery status, etc. To learn how to efficiently operate in this dynamic environment, a hybrid methodology combining simulation with reinforcement learning is proposed. The reinforcement learning component is able to make informed decisions at each stage, while the simulation component is employed to validate the learning process. The computational experiments show how the proposed methodology is capable of design routing plans that are significantly better than non-informed decisions, thus allowing for an efficient management of the vehicle¿s battery under such dynamic conditions., This work was partially funded by the European Commission projects SUN (HORIZONCL4-2022-HUMAN-01-14-101092612), and AIDEAS (HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Sim-Learnheuristic for the Team Orienteering Problem: Applications to Unmanned Aerial Vehicles

  • Peyman, Mohammad
  • Martín-Solano, Xabier Andoni
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In this paper, we introduce a novel sim-learnheuristic method designed to address the team orienteering problem (TOP) with a particular focus on its application in the context of unmanned aerial vehicles (UAVs). Unlike most prior research, which primarily focuses on the deterministic and stochastic versions of the TOP, our approach considers a hybrid scenario, which combines deterministic, stochastic, and dynamic characteristics. The TOP involves visiting a set of customers using a team of vehicles to maximize the total collected reward. However, this hybrid version becomes notably complex due to the presence of uncertain travel times with dynamically changing factors. Some travel times are stochastic, while others are subject to dynamic factors such as weather conditions and traffic congestion. Our novel approach combines a savings-based heuristic algorithm, Monte Carlo simulations, and a multiple regression model. This integration incorporates the stochastic and dynamic nature of travel times, considering various dynamic conditions, and generates high-quality solutions in short computational times for the presented problem., This work was partially funded by the Spanish Ministry of Science and Innovation (PRE2020-091842, PID2022-138860NB-I00, RED2022-134703-T) and the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612).
O2, repositorio institucional de la UOC
Publication Artículo científico (JournalArticle)

Simulation of heuristics for automated guided vehicle task sequencing with resource sharing and dynamic queues

  • Fuentes Leon, Jonas
  • Peyman, Mohammad
  • Martin Solano, Xabier Andoni
  • Juan, Angel A.
Automated guided vehicles (AGVs) stand out as a paradigmatic application of Industry 4.0, requiring the seamless integration of new concepts and technologies to enhance productivity while reducing labor costs, energy consumption, and emissions. In this context, specific industrial use cases can present a significant technological and scientific challenge. This study was inspired by a real industrial application for which the existing AGV literature did not contain an already well-studied solution. The problem is related to the sequencing of assigned tasks, where the queue formation dynamics and the resource sharing define the scheduling. The combinatorial nature of the problem requires the use of advanced mathematical tools such as heuristics, simulations, or a combination of both. A heuristic procedure was developed that generates candidate task sequences, which are, in turn, evaluated in a discrete-event simulation model developed in Simul8. This combined approach allows high-quality solutions to be generated and realistically evaluated, even graphically, by stakeholders and decision makers. A number of computational experiments were developed to validate the proposed method, which opens up some future lines of research, especially when considering stochastic settings.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning to Solve a Dynamic Orienteering Problem with Random Rewards Affected by the Battery Status

  • Juan, Ángel A|||0000-0003-1392-1776
  • Marugan, C.A.|||0009-0008-9076-0906
  • Ahsini, Y.|||0009-0006-5582-6725
  • Fornes, R.|||0009-0001-6956-9137
  • Panadero, Javier|||0000-0002-3793-3328
  • Martin, Xabier A|||0000-0003-4182-0120
This paper discusses an orienteering optimization problem where a vehicle using electric batteries must travel from an origin depot to a destination depot while maximizing the total reward collected along its route. The vehicle must cross several consecutive regions, with each region containing different types of charging nodes. A charging node has to be selected in each region, and the reward for visiting each node-in terms of a 'satisfactory' charging process-is a binary random variable that depends upon dynamic factors such as the type of charging node, weather conditions, congestion, battery status, etc. To learn how to efficiently operate in this dynamic environment, a hybrid methodology combining simulation with reinforcement learning is proposed. The reinforcement learning component is able to make informed decisions at each stage, while the simulation component is employed to validate the learning process. The computational experiments show how the proposed methodology is capable of design routing plans that are significantly better than non-informed decisions, thus allowing for an efficient management of the vehicle's battery under such dynamic conditions.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations

  • Leon, Jonas F.
  • Li, Yuda|||0000-0001-8031-6555
  • Martin, Xabier A.|||0000-0003-4182-0120
  • Calvet, Laura|||0000-0001-8425-1381
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm for the Capacitated Dispersion Problem under Dynamic Conditions

  • Gómez González, Juan Francisco|||0000-0001-7692-9922
  • Rodríguez Uguina, Antonio|||0009-0001-5506-1674
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
The capacitated dispersion problem, which is a variant of the maximum diversity problem, aims to determine a set of elements within a network. These elements could symbolize, for instance, facilities in a supply chain or transmission nodes in a telecommunication network. While each element typically has a bounded service capacity, in this research, we introduce a twist. The capacity of each node might be influenced by a random Bernoulli component, thereby rendering the possibility of a node having zero capacity, which is contingent upon a black box mechanism that accounts for environmental variables. Recognizing the inherent complexity and the NP-hard nature of the capacitated dispersion problem, heuristic algorithms have become indispensable for handling larger instances. In this paper, we introduce a novel approach by hybridizing a heuristic algorithm with reinforcement learning to address this intricate problem variant.