Carlos March
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Carlos March has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Christian Perez
Universitat Politècnica de València
5 shared publications - Miguel A. Salido
Universitat Politècnica de València
4 shared publications - Adriana Giret
Universitat Politècnica de València
1 shared publication - Frederik Schulte
Delft University of Technology
1 shared publication - Kevin Tierney
Department of Business Decisions and Analytics, University of Vienna, Austria
1 shared publication Miguel A. Salido
1 shared publication
Latest Publications
- 9 July 2026
- Published by Springer Nature
- p. 15-26
A Reinforcement Learning Approach for the Dynamic Berth Allocation Problem
- 9 July 2026
- Published by Springer Nature
- p. 15-26
A Reinforcement Learning Approach for the Dynamic Berth Allocation Problem
- Open Access
- 14 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 159-162
IGJSP: A Reproducible Instance Generator for Job Shop Scheduling
- 14 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 159-162
Open AccessIGJSP: A Reproducible Instance Generator for Job Shop Scheduling
- Open Access
- 20 May 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 288
Driving energy efficiency in scheduling manufacturing: An advanced instance generation and a metaheuristic approach
- 20 May 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 288
Open AccessDriving energy efficiency in scheduling manufacturing: An advanced instance generation and a metaheuristic approach
- Open Access
- 22 November 2024
- Published by Elsevier in Information Sciences
- Vol. 693
Optimizing energy efficiency in unrelated parallel machine scheduling problem through reinforcement learning
- 22 November 2024
- Published by Elsevier in Information Sciences
- Vol. 693
Open AccessOptimizing energy efficiency in unrelated parallel machine scheduling problem through reinforcement learning
- Open Access
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
A Q-Learning Proposal for Tuning Genetic Algorithms in Flexible Job Shop Scheduling Problems
Genetic algorithms (GAs) belong to the category of evolutionary algorithms and are frequently utilized for resolving challenging combinatorial problems. However, they typically require customization to suit a particular problem type, and their performance is heavily influenced by numerous hyperparameters and reproduction operators. In this work, we propose a Reinforcement Learning approach for fine-tuning Genetic Algorithms in Flexible Job Shop Scheduling problems (FJSP), where the main parameters involved in the genetic algorithm operators are trained to allocate the most promising values. The approach returns an optimized schedule taking into account given constraints specific to the scenario, such as the relationship among release date, due date, and processing time, which machines must be selected out of a set of alternative machines, or which sequence-dependent setup time can be filtered. The approach takes input data in the form of FJSP instances by varying the numbers of jobs and machines and then uses the NSGA-II algorithm to generate solutions. These solutions are stored in a Solutions module and they are analyzed using a Principal components analysis (PCA) to identify clusters of similar instances and solutions. The Q-Learning module then generates hyperparameters for each iteration of the NSGA-II algorithm based on information from the previous modules. A toy example is presented to better understand the behavior of the proposal and the results obtained for optimizing further instances of the problem in a more efficient way.
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Open AccessA Q-Learning Proposal for Tuning Genetic Algorithms in Flexible Job Shop Scheduling Problems
Genetic algorithms (GAs) belong to the category of evolutionary algorithms and are frequently utilized for resolving challenging combinatorial problems. However, they typically require customization to suit a particular problem type, and their performance is heavily influenced by numerous hyperparameters and reproduction operators. In this work, we propose a Reinforcement Learning approach for fine-tuning Genetic Algorithms in Flexible Job Shop Scheduling problems (FJSP), where the main parameters involved in the genetic algorithm operators are trained to allocate the most promising values. The approach returns an optimized schedule taking into account given constraints specific to the scenario, such as the relationship among release date, due date, and processing time, which machines must be selected out of a set of alternative machines, or which sequence-dependent setup time can be filtered. The approach takes input data in the form of FJSP instances by varying the numbers of jobs and machines and then uses the NSGA-II algorithm to generate solutions. These solutions are stored in a Solutions module and they are analyzed using a Principal components analysis (PCA) to identify clusters of similar instances and solutions. The Q-Learning module then generates hyperparameters for each iteration of the NSGA-II algorithm based on information from the previous modules. A toy example is presented to better understand the behavior of the proposal and the results obtained for optimizing further instances of the problem in a more efficient way.
- Open Access
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Rooster Colony Algorithm: A two-step Multi-Swarm Optimization Approach
Particle Swarm Optimization is a metaheuristic optimization algorithm inspired by the collective behavior of animal swarms where a set of candidate solutions, called particles, are randomly initialized in the search space, and their movements are iteratively updated based on their individual best solutions and the global best solution found by the swarm. This paper proposes a Multi-Swarm rooster colony algorithm (RCA) that considers a set of roosters, each owning a group of hens to compose a team. Each team (rooster and its hens) competes for the resource (food) with the other teams. From the combinatorial optimization point of view, each team analyzes part of the search space by an independent PSO algorithm with the same objective function. The RCA algorithm concurrently executes all PSO algorithms with different inertial weights for exploring different regions and the best solution (Gbest) of each team will compose the initial population for a new further centralized PSO algorithm that will exploit the previous solutions to search for the optimal one. Thus, the proposed RCA is composed of two steps, based on exploration and exploitation strategies to find an optimized solution in the search space. The results show that the proposed algorithm is competitive in solving well-known optimization functions. The objective is to apply this technique to solving real-life scheduling problems.
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Open AccessRooster Colony Algorithm: A two-step Multi-Swarm Optimization Approach
Particle Swarm Optimization is a metaheuristic optimization algorithm inspired by the collective behavior of animal swarms where a set of candidate solutions, called particles, are randomly initialized in the search space, and their movements are iteratively updated based on their individual best solutions and the global best solution found by the swarm. This paper proposes a Multi-Swarm rooster colony algorithm (RCA) that considers a set of roosters, each owning a group of hens to compose a team. Each team (rooster and its hens) competes for the resource (food) with the other teams. From the combinatorial optimization point of view, each team analyzes part of the search space by an independent PSO algorithm with the same objective function. The RCA algorithm concurrently executes all PSO algorithms with different inertial weights for exploring different regions and the best solution (Gbest) of each team will compose the initial population for a new further centralized PSO algorithm that will exploit the previous solutions to search for the optimal one. Thus, the proposed RCA is composed of two steps, based on exploration and exploitation strategies to find an optimized solution in the search space. The results show that the proposed algorithm is competitive in solving well-known optimization functions. The objective is to apply this technique to solving real-life scheduling problems.