Data-Driven or AI-Driven Optimization Algorithms and Their Applications

Dear Colleagues,

Optimization is concerned with developing a set of modeling frameworks and solution techniques that allow practitioners to derive the best performance from a complex system. It is based on interdisciplinary expertise and skills in operations research, management science, industrial and systems engineering, and computer science. Optimization models and algorithms have been widely applied to industries such as manufacturing, mining, robotics, transportation, agriculture, energy grids, e-commerce, and healthcare.

This Special Issue will focus on recent theoretical and applied studies of data-driven optimization problems, models, analysis, algorithms, and real-world implementations. We expect to receive papers that reflect the integration of advanced optimization techniques, technologies, and applications to address increasingly complex problems across various fields.

Topics include—but are not limited to—the following:

• Data-driven or AI-driven optimization with perdition, simulation, and digital twins.
• Planning and scheduling optimization algorithms.
• Optimization algorithms for supply chain management and operations management.
• Reinforcement Learning for Optimization: applying reinforcement learning (RL), which learns to make sequential decisions in complex environments by receiving feedback from interactions with the environment.
• Bayesian Optimization: using Bayesian inference (e.g., for hyperparameter tuning in machine learning models) to build a surrogate objective function model, enabling efficient and effective exploration of the entire solution space.
• New Metaheuristics: development of new metaheuristic algorithms inspired by natural processes, such as social behaviors or physical phenomena.
• Memetic Algorithms: combining local search techniques with population-based ones to enhance performance in solving complex optimization problems.
• Explainable and Interpretable Optimization: a growing trend focuses on making optimization processes and their outcomes more transparent and interpretable because understanding the decision-making process is crucial for fields like healthcare, finance, and autonomous systems.
• Hybrid Optimization Algorithms: combining different optimization methods with local search techniques or gradient-based methods with metaheuristics to leverage the strengths of each approach and overcome their weaknesses.
• Stochastic Optimization: incorporating randomness and uncertainty into the optimization process, particularly in environments where data are incomplete, noisy, or uncertain.
• Robust Optimization: developing algorithms that perform well under various conditions or scenarios, ensuring solutions are not overly sensitive to variations in input data.
• Real-time and Online Optimization: optimize systems in real-time or on the fly by using streaming data for applications such as online advertising, production re-scheduling, emergent patient scheduling, grid network optimization, and real-time pricing in e-commerce.
• Optimization for sustainability: growing emphasis on optimizing systems for sustainability, e.g., minimizing carbon footprints, reducing waste, or optimizing renewable energy systems.
• Distributed Optimization: optimizing large-scale problems across multiple computers or nodes in a network driven by big data and cloud computing growth.
• Queuing theory: the study of queuing phenomena of objects (e.g., people, objects, or packets) waiting for service to optimize the service process.
• Graph Neural Networks: application of Graph Neural Networks (GNN) to explore innovative solutions to combinatorial optimization problems with enhanced consistency and robustness through self-attention mechanisms.
• Contextual optimization: in-depth analysis and consideration of the specific characteristics of the decision environment to customize the optimization strategy to solve the optimization problem in dynamic environments.
• Variational Inequalities and Numerical Approximations with Convex Optimization:  Variational inequalities provide a powerful framework for modeling and solving a wide range of problems in optimization, equilibrium, and game theory. Numerical approximations are key in solving VIs, particularly large-scale convex optimization problems.
• Cross-disciplinary Applications: implementation of optimization techniques in novel fields and various sectors, such as biology, medicine, urban, mining, healthcare, agriculture, ecology, etc.

Prof. Dr. Shiqiang Liu
Dr. Weidong Li
Prof. Dr. Lijun Zhu
Prof. Dr. Yongman Zhao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• planning and scheduling
• supply chain management
• construction heuristics
• metaheuristics
• approximation and randomized algorithms
• mixed integer programming
• algorithmic game theory
• deep reinforcement learning
• graph neural networks
• simulation and digital twins
• real-time and online optimization
• explainable and interpretable optimization
• optimization for sustainability
• stochastic optimization
• robust optimization
• contextual optimization
• distributed optimization
• variational inequalities and numerical approximations
• cross-disciplinary applications