Co-funded by:
Mentored by:

Optimization and fault forecasting in port logistics processes using artificial intelligence, process mining and operations research

  • PROJECT CODE: BI-HU/21-22-010
  • PROJECT TITLE: Optimization and fault forecasting in port logistics processes using artificial intelligence, process mining and operations research
  • PROJECT LEADER: Miklós Krész, PhD
  • PERIOD: 01.03.2021 – 28.02.2023
  • BUDGET: €2,000
  • FINANCING: Slovenian Research Agency (ARRS)
  • PARTNERS: InnoRenew CoE (Slovenia); University of Pannonia, Faculty of Information Technology (Hungary)

Appropriate resource allocation and logistics scheduling have an impact on both their cost and ecological footprint. However, despite well-scheduled logistics operations, a decrease in resource performance or a faulty resource may have severe consequences that can influence the precision of a distribution operation, the quality of the products to deliver, the number/cost of the required resources or the environmental impact of the process. Thus, decreasing probability and/or minimizing impact of a faulty resource on the schedule are important aspects of logistics planning.  Traditional solutions in logistics apply methodologies of operations research (mathematical programming or heuristics) that provide access to efficient solution packages. However, the dynamically changing environment in port operations needs to adapt these dynamics in the models and methods. Smart logistics is based on data collection from sensors and IoT, a technology that is also available in port operations. Currently, automatic data processing and decision-making face new challenges that result in the emergence of new optimization problems on large data sets.  The objective of this project is to develop smart optimization solutions for logistics in port operations. As expected, results aim to provide a novel approach for a unified framework to develop data-driven solutions for the optimization of port logistics problems through system modelling and analysis, mathematical and data science modelling and integration of operations research machine learning and process mining.

InnoRenew CoE project activities

InnoRenew CoE will identify and study problems in port logistics where smart solutions are possible for monitoring processes, developing system models and a decision support framework for the identified problems with respect to the integration of data analytics and optimization approaches, testing the solutions on real-world and simulated data sets and analyzing the results.