IE-RSME Workshop Series on Applied Mathematics — Sustainable Transportation & Energy Systems: An Optimization and AI Perspective

Salvador Pineda

Universidad de Málaga

Salvador Pineda obtained his degree in Industrial Engineering from the University of Málaga in 2006, and his PhD in Electrical Engineering from the University of Castilla-La Mancha in 2011. From 2011 to 2016, he worked as a professor at the Technical University of Denmark and the University of Copenhagen. Since 2016, he has been a professor in the Department of Electrical Engineering at the University of Málaga. His research interests focus on the operation and planning of energy systems, decision-making under uncertainty, bilevel programming, machine learning, and statistics.

Talk title: Machine-learning aided operation and planning of power systems

Abstract: Power systems are among the most complex engineering structures in modern society, facing significant spatial and temporal challenges due to vast geographical extensions and the inherent variability of renewable energy. However, the proliferation of monitoring infrastructure now enables the massive use of data to enhance system efficiency and reliability. In this talk, we present five machine-learning applications that leverage both unsupervised and supervised learning to address standard power system problems. These include a chronological clustering technique for generation and transmission expansion planning, a nearest-neighbor procedure for screening network constraints in unit commitment, a price-aware regression approach for TSO-DSO coordination, a KNN-based method to accelerate unit commitment solutions, and an interpretable linear approximation for solving non-linear optimal power flow. Together, these works demonstrate that integrating machine learning with optimization (often through simple, interpretable models) can significantly improve the operation and planning of modern electrical grids.

Julio González Díaz

Invited Speaker

University of Santiago de Compostela

Julio González Díaz is a Professor of Operations Research and Mathematical Optimization at the University of Santiago de Compostela, affi liated with the Centre for Mathematical Research and Technology (CITMAga). His work spans mathematical optimization, decision models, game theory, and algorithmic development, with a strong focus on leveraging optimization techniques to solve complex decision problems in networked and competitive environments.



Talk title: Optimizing Multi‑Feedstock Supply Chains for Next‑Generation Compliant Fuels

Abstract: EU regulations and the overarching objective of lifecycle carbon neutrality pose significant economic and logistical challenges to traditional oil industry players. Under the current regulatory framework, companies must satisfy increasingly stringent annual carbon saving targets. To achieve these goals, operators must integrate biogenic and sustainable feedstocks into their existing production processes.This talk presents an optimization model designed to guide strategic provisioning decisions across available feedstocks. The model seeks to minimize incremental costs while ensuring full compliance with EU carbon intensity mandates and maintaining rigorous fuel quality standards.

Bissan Ghaddar

IE University and Ivey Business School

Bissan Ghaddar works at the intersection of smart cities, machine learning, and mathematical optimization, developing data-driven models for sustainable and resilient infrastructure systems. She holds a Ph.D. in Operations Research–Management Science from the University of Waterloo and has experience in both academia and industry, including research at IBM on energy, telecom, water, and transportation network optimization.

Her research focuses on integrating AI and optimization to address large-scale challenges in energy and mobility systems, with publications in leading journals such as Mathematical Programming, INFORMS Journal on Computing, and SIAM Journal on Optimization.


Talk title : Electrification of last-mile delivery services


Abstract: the rapid growth of e-commerce has significantly increased the volume of last-mile delivery operations, intensifying urban congestion, local air pollution, and greenhouse gas emissions. Electrification of last-mile delivery services has emerged as a promising pathway toward decarbonizing urban freight while improving operational efficiency. However, large-scale deployment of electric delivery fleets introduces new challenges related to vehicle routing, charging infrastructure planning, and operational reliability. This talk investigates the electrification of last-mile delivery systems through an integrated optimization framework that jointly considers routing decisions and charging scheduling under different electricity prices.

Manuel Navarro García

Invited Speaker

Optimization Consultant, Decide4AI

Manuel Navarro-García works at the intersection of mathematical optimization and data science, developing advanced decision-support models that integrate predictive analytics with mathematical programming. He holds a Ph.D. in Mathematical Engineering from Universidad Carlos III de Madrid and has a background in Mathematics, Physics, and Statistics for Data Science. Currently, he serves as an Optimization Consultant at Decide4AI, where he designs optimization models that provide quantitative and qualitative insights to improve strategic and operational decision-making in industry.


Talk title: Towards smarter offshore wind farms: Optimization of cable networks and electrical infrastructure


Abstract: This talk presents a mathematical optimization approach to the design of offshore wind farm electrical layouts, with a focus on cable routing, cable type selection, and substation placement under realistic engineering constraints. The problem is formulated as a mixed-integer linear programming model that captures both investment and operational costs, including installation costs, electrical losses, and cable capacities, while also accounting for practical issues such as cable crossings, obstacles, and large-scale instances with more than 100 turbines. Beyond its methodological contribution, this work is part of a real industrial project and has been deployed in production to support decision-making in offshore wind farm design. The approach has been validated through backtesting on real cases.