Francisco Javier Díaz Serna
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Francisco Javier Díaz Serna has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Marisol Valencia Cárdenas
Universidad Nacional de Colombia
5 shared publications - Nestor Raul Ortiz Pimiento
Universidad Industrial de Santander
4 shared publications Juan Carlos Correa Morales
Docente asociado, Universidad Nacional de Colombia
3 shared publications- Juan Carlos Correa Morales
Universidad Nacional de Colombia
2 shared publications - Daniel Morillo-Torres
Department of Civil and Industrial Engineering, Pontificia Universidad Javeriana, Cali 760001, Colombia
1 shared publication - David Pozo
Center for Energy Science and Technology, Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia
1 shared publication
Latest Publications
- Open Access
- 1 January 2020
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 87 (212) , 179-188
An optimization model to solve the resource constrained project scheduling problem RCPSP in new product development projects•
New product development projects (NPDP) face different risks that may affect the scheduling. In this article, the purpose was to develop an optimization model to solve the RCPSP in NPDP and obtain a robust baseline for the project. The proposed model includes three stages: the identification of the project’s risks, an estimation of activities’ duration, and the resolution of an integer linear program. Two versions of the model were designed and compared in order to select the best one. The first version uses a method to estimate the activities’ duration based on the expected value of the impact of the risks and the second version uses a method based on the judgmental risk analysis process. Finally, the two version of the model were applied to a case study and the best version of the model was identified using a robustness indicator that analyses the start times of the baselines generated.
- 1 January 2020
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 87 (212) , 179-188
Open AccessAn optimization model to solve the resource constrained project scheduling problem RCPSP in new product development projects•
New product development projects (NPDP) face different risks that may affect the scheduling. In this article, the purpose was to develop an optimization model to solve the RCPSP in NPDP and obtain a robust baseline for the project. The proposed model includes three stages: the identification of the project’s risks, an estimation of activities’ duration, and the resolution of an integer linear program. Two versions of the model were designed and compared in order to select the best one. The first version uses a method to estimate the activities’ duration based on the expected value of the impact of the risks and the second version uses a method based on the judgmental risk analysis process. Finally, the two version of the model were applied to a case study and the best version of the model was identified using a robustness indicator that analyses the start times of the baselines generated.
- Open Access
- 26 September 2019
- Published by Polish Academy of Sciences Chancellery in Management and Production Engineering Review
- Vol. 10 (3) , 73-80
A comparison of different redundancy based methods to solve the project scheduling problemwith probabilistic activivies duration
Redundancy based methods are proactive scheduling methods for solving the Project Scheduling Problem (PSP) with non-deterministic activities duration. The fundamental strategy of these methods is to estimate the activities duration by adding extra time to the original duration. The extra time allows to consider the risks that may affect the activities durations and to reduce the number of adjustments to the baseline generated for the project. In this article, four methods based on redundancies were proposed and compared from two robustness indicators. These indicators were calculated after running a simulation process. On the other hand, linear programming was applied as the solution technique to generate the baselines of 480 projects analyzed. Finally, the results obtained allowed to identify the most adequate method to solve the PSP with probabilistic activity duration and generate robust baselines.
- 26 September 2019
- Published by Polish Academy of Sciences Chancellery in Management and Production Engineering Review
- Vol. 10 (3) , 73-80
Open AccessA comparison of different redundancy based methods to solve the project scheduling problemwith probabilistic activivies duration
Redundancy based methods are proactive scheduling methods for solving the Project Scheduling Problem (PSP) with non-deterministic activities duration. The fundamental strategy of these methods is to estimate the activities duration by adding extra time to the original duration. The extra time allows to consider the risks that may affect the activities durations and to reduce the number of adjustments to the baseline generated for the project. In this article, four methods based on redundancies were proposed and compared from two robustness indicators. These indicators were calculated after running a simulation process. On the other hand, linear programming was applied as the solution technique to generate the baselines of 480 projects analyzed. Finally, the results obtained allowed to identify the most adequate method to solve the PSP with probabilistic activity duration and generate robust baselines.
- Open Access
- 25 June 2019
- Published by Universidad Pedagogica y Tecnologica de Colombia in Revista Facultad de Ingeniería
- Vol. 28 (52) , 77-97
Relative Average Deviation as Measure of Robustness in the Stochastic Project Scheduling Problem
In the Project Scheduling Problem (PSP), the solution robustness can be understood as the capacity that a baseline has to support the disruptions generated by unplanned events (risks). A robust baseline of the project can be obtained from redundancy based methods, which are considered proactive methods to solve the stochastic project scheduling problem. In this research, three redundancy based methods are evaluated and their performance is compared in terms of robustness. These methods add extra time to the original activities duration in order to face the eventualities that may appear during the project execution. In this article a new indicator to analyze the solution robustness to the Project Scheduling Problem with random duration of activities is proposed. This indicator called Relative Average Deviation (RAD) is defined as the margin of deviation of the activities’ start times in relation to their durations. The RAD is based in a traditional concept that seeks to minimize the value of the differences between the planned start times and the real executed start times. The planned start times were obtained from the project baseline generated by each redundancy based method and the real executed start times were obtained from a simulation process based on Monte Carlo technique. The new indicator was used to evaluate the robustness of three baselines generated by different methods but applied to the same case study. Finally, the results suggest that the Relative Average Deviation (RAD) facilitates the interpretation of the robustness concept because it focuses on analyzing the deviation margin associated with an activity.
- 25 June 2019
- Published by Universidad Pedagogica y Tecnologica de Colombia in Revista Facultad de Ingeniería
- Vol. 28 (52) , 77-97
Open AccessRelative Average Deviation as Measure of Robustness in the Stochastic Project Scheduling Problem
In the Project Scheduling Problem (PSP), the solution robustness can be understood as the capacity that a baseline has to support the disruptions generated by unplanned events (risks). A robust baseline of the project can be obtained from redundancy based methods, which are considered proactive methods to solve the stochastic project scheduling problem. In this research, three redundancy based methods are evaluated and their performance is compared in terms of robustness. These methods add extra time to the original activities duration in order to face the eventualities that may appear during the project execution. In this article a new indicator to analyze the solution robustness to the Project Scheduling Problem with random duration of activities is proposed. This indicator called Relative Average Deviation (RAD) is defined as the margin of deviation of the activities’ start times in relation to their durations. The RAD is based in a traditional concept that seeks to minimize the value of the differences between the planned start times and the real executed start times. The planned start times were obtained from the project baseline generated by each redundancy based method and the real executed start times were obtained from a simulation process based on Monte Carlo technique. The new indicator was used to evaluate the robustness of three baselines generated by different methods but applied to the same case study. Finally, the results suggest that the Relative Average Deviation (RAD) facilitates the interpretation of the robustness concept because it focuses on analyzing the deviation margin associated with an activity.
- Open Access
- 6 February 2018
- Published by Omnia Publisher SL in Journal of Industrial Engineering and Management
- Vol. 11 (1) , 116-134
The project scheduling problem with non-deterministic activities duration: A literature review
Purpose: The goal of this article is to provide an extensive literature review of the models and solution procedures proposed by many researchers interested on the Project Scheduling Problem with non-deterministic activities duration.Design/methodology/approach: This paper presents an exhaustive literature review, identifying the existing models where the activities duration were taken as uncertain or random parameters. In order to get published articles since 1996, was employed the Scopus database. The articles were selected on the basis of reviews of abstracts, methodologies, and conclusions. The results were classified according to following characteristics: year of publication, mathematical representation of the activities duration, solution techniques applied, and type of problem solved.Findings: Genetic Algorithms (GA) was pointed out as the main solution technique employed by researchers, and the Resource-Constrained Project Scheduling Problem (RCPSP) as the most studied type of problem. On the other hand, the application of new solution techniques, and the possibility of incorporating traditional methods into new PSP variants was presented as research trends.Originality/value: This literature review contents not only a descriptive analysis of the published articles but also a statistical information section in order to examine the state of the research activity carried out in relation to the Project Scheduling Problem with non-deterministic activities duration.
- 6 February 2018
- Published by Omnia Publisher SL in Journal of Industrial Engineering and Management
- Vol. 11 (1) , 116-134
Open AccessThe project scheduling problem with non-deterministic activities duration: A literature review
Purpose: The goal of this article is to provide an extensive literature review of the models and solution procedures proposed by many researchers interested on the Project Scheduling Problem with non-deterministic activities duration.Design/methodology/approach: This paper presents an exhaustive literature review, identifying the existing models where the activities duration were taken as uncertain or random parameters. In order to get published articles since 1996, was employed the Scopus database. The articles were selected on the basis of reviews of abstracts, methodologies, and conclusions. The results were classified according to following characteristics: year of publication, mathematical representation of the activities duration, solution techniques applied, and type of problem solved.Findings: Genetic Algorithms (GA) was pointed out as the main solution technique employed by researchers, and the Resource-Constrained Project Scheduling Problem (RCPSP) as the most studied type of problem. On the other hand, the application of new solution techniques, and the possibility of incorporating traditional methods into new PSP variants was presented as research trends.Originality/value: This literature review contents not only a descriptive analysis of the published articles but also a statistical information section in order to examine the state of the research activity carried out in relation to the Project Scheduling Problem with non-deterministic activities duration.
- Open Access
- 1 July 2016
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 83 (198) , 235
Modelo de inventario multi-producto, con pronósticos de demanda y optimización Bayesiana
La complejidad de las cadenas de suministro exige mejores métodos para programar los inventarios de una empresa. En este trabajo se presenta una comparación entre modelos de pronósticos de demanda de múltiples productos, eligiendo el mejor entre: ARIMA, Suavización exponencial, Regresión Lineal Bayesiana y un Modelo Lineal Dinámico Bayesiano. Para ello, primero se realiza una simulación de casos donde no hay una Distribución Normal en las series de tiempo, segundo, se estiman las predicciones de ventas de tres productos de una estación de servicios de gasolina con los cuatro modelos, encontrando los mejores resultados para la Regresión Lineal Bayesiana. Seguido a esto, se presenta la optimización de un Modelo de Inventarios Multi-Producto. Para definir la política de pedidos, inventarios, costos y ganancias, se utiliza una búsqueda bayesiana, que integra elementos de búsqueda Tabú para mejorar la solución. Dicha Optimización del Modelo de Inventarios se aplica a un caso de una estación de combustibles en Colombia.
- 1 July 2016
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 83 (198) , 235
Open AccessModelo de inventario multi-producto, con pronósticos de demanda y optimización Bayesiana
La complejidad de las cadenas de suministro exige mejores métodos para programar los inventarios de una empresa. En este trabajo se presenta una comparación entre modelos de pronósticos de demanda de múltiples productos, eligiendo el mejor entre: ARIMA, Suavización exponencial, Regresión Lineal Bayesiana y un Modelo Lineal Dinámico Bayesiano. Para ello, primero se realiza una simulación de casos donde no hay una Distribución Normal en las series de tiempo, segundo, se estiman las predicciones de ventas de tres productos de una estación de servicios de gasolina con los cuatro modelos, encontrando los mejores resultados para la Regresión Lineal Bayesiana. Seguido a esto, se presenta la optimización de un Modelo de Inventarios Multi-Producto. Para definir la política de pedidos, inventarios, costos y ganancias, se utiliza una búsqueda bayesiana, que integra elementos de búsqueda Tabú para mejorar la solución. Dicha Optimización del Modelo de Inventarios se aplica a un caso de una estación de combustibles en Colombia.
- Open Access
- 11 May 2015
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 82 (190) , 182-191
Inventory planning with dynamic demand. A state of art review
Inventory planning with dynamic demand. A state of art review
- 11 May 2015
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 82 (190) , 182-191
Open AccessInventory planning with dynamic demand. A state of art review
Inventory planning with dynamic demand. A state of art review
- Open Access
- 11 May 2015
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 82 (190) , 198-207
A branch and bound hybrid algorithm with four deterministic heuristics for the resource constrained project scheduling problem (RCPSP)
A branch and bound hybrid algorithm with four deterministic heuristics for the resource constrained project scheduling problem (RCPSP)
- 11 May 2015
- Published by Universidad Nacional de Colombia in DYNA
- Vol. 82 (190) , 198-207
Open AccessA branch and bound hybrid algorithm with four deterministic heuristics for the resource constrained project scheduling problem (RCPSP)
A branch and bound hybrid algorithm with four deterministic heuristics for the resource constrained project scheduling problem (RCPSP)
- Open Access
- 1 January 2015
- Published by Universidad Nacional de Colombia in Revista de la Facultad de Ciencias
- Vol. 4 (1) , 52-67
MÉTODOS ESTADÍSTICOS CLÁSICOS Y BAYESIANOS PARA EL PRONÓSTICO DE DEMANDA. UN ANÁLISIS COMPARATIVO
Las comparaciones entre modelos de pronóstico son necesarias para la toma de decisiones en la industria, en especial en temas de demanda de productos terminados. En presencia de pocos datos históricos, hay dificultades en premisas de estructuras teóricas. Aquí se presenta una comparación diseñada en el programa R, usando cuatro tipos de modelos: Regresión Lineal Bayesiana con Distribución a priori Normal, Modelo Lineal Dinámico Bayesiano, modelo ARIMA y modelo de Suavización Exponencial, con base en el criterio Media del Error Absoluto de Pronósticos (MAPE) de pronóstico y para ello se simulan diferentes esquemas de datos que reflejan comportamientos de demandas con y sin distribución normal. Se encuentra que los modelos bayesianos estudiados tienen un alto potencial para realizar predicciones, sobre todo para los datos que no se comportan con una distribución normal, siendo más precisos que los otros modelos clásicos comparados, son además, más robustos a premisas teóricas y se pueden utilizar con pocos datos históricos.
- 1 January 2015
- Published by Universidad Nacional de Colombia in Revista de la Facultad de Ciencias
- Vol. 4 (1) , 52-67
Open AccessMÉTODOS ESTADÍSTICOS CLÁSICOS Y BAYESIANOS PARA EL PRONÓSTICO DE DEMANDA. UN ANÁLISIS COMPARATIVO
Las comparaciones entre modelos de pronóstico son necesarias para la toma de decisiones en la industria, en especial en temas de demanda de productos terminados. En presencia de pocos datos históricos, hay dificultades en premisas de estructuras teóricas. Aquí se presenta una comparación diseñada en el programa R, usando cuatro tipos de modelos: Regresión Lineal Bayesiana con Distribución a priori Normal, Modelo Lineal Dinámico Bayesiano, modelo ARIMA y modelo de Suavización Exponencial, con base en el criterio Media del Error Absoluto de Pronósticos (MAPE) de pronóstico y para ello se simulan diferentes esquemas de datos que reflejan comportamientos de demandas con y sin distribución normal. Se encuentra que los modelos bayesianos estudiados tienen un alto potencial para realizar predicciones, sobre todo para los datos que no se comportan con una distribución normal, siendo más precisos que los otros modelos clásicos comparados, son además, más robustos a premisas teóricas y se pueden utilizar con pocos datos históricos.
- Open Access
- 20 December 2014
- Published by Universidad Pedagogica y Tecnologica de Colombia in Ingeniería Investigación y Desarrollo
- Vol. 15 (1) , 39-47
Inventory model using bayesian dynamic linear model for demand forecasting
Un factor importante de los procesos de manufactura es la administración de los inventarios de productoterminado. Constantemente la industria está en busca de mejores alternativas para establecer adecuados planes de cantidades por producir y almacenar, a costo óptimo, logrando con ello un horizonte que permita definir con anticipación la logística y los recursos necesarios para la entrega a tiempo de sus productos. La ausencia de datos históricos, requeridos por muchos modelos estadísticos para pronosticar, exige la búsqueda de nuevas técnicas de estimación de demanda con precisión. Este trabajo presenta una alternativa que no solo permite pronosticar de forma ajustada a la realidad, sino dar cantidades óptimas para producir y almacenar inventarios a costo óptimo, usando estadística bayesiana. Se ilustra la propuesta con datos reales.
- 20 December 2014
- Published by Universidad Pedagogica y Tecnologica de Colombia in Ingeniería Investigación y Desarrollo
- Vol. 15 (1) , 39-47
Open AccessInventory model using bayesian dynamic linear model for demand forecasting
Un factor importante de los procesos de manufactura es la administración de los inventarios de productoterminado. Constantemente la industria está en busca de mejores alternativas para establecer adecuados planes de cantidades por producir y almacenar, a costo óptimo, logrando con ello un horizonte que permita definir con anticipación la logística y los recursos necesarios para la entrega a tiempo de sus productos. La ausencia de datos históricos, requeridos por muchos modelos estadísticos para pronosticar, exige la búsqueda de nuevas técnicas de estimación de demanda con precisión. Este trabajo presenta una alternativa que no solo permite pronosticar de forma ajustada a la realidad, sino dar cantidades óptimas para producir y almacenar inventarios a costo óptimo, usando estadística bayesiana. Se ilustra la propuesta con datos reales.
- Open Access
- 1 June 2014
- Published by Universidad del Norte in Ingeniería y Desarrollo
- Vol. 32 (2) , 179-199
Bayesian modeling application and optimization to demand forecasting
- 1 June 2014
- Published by Universidad del Norte in Ingeniería y Desarrollo
- Vol. 32 (2) , 179-199
Open AccessBayesian modeling application and optimization to demand forecasting