Evolutionary Algorithms in Crisis Management of Supply Chains to Enhance Global Food Security During War in Ukraine

Abstract

This paper discusses the use of evolutionary algorithms to optimize food safety, particularly in the case of the ongoing war in Ukraine. Traditional optimization methods appear to be increasingly ineffective due to the complexity of the search space and the massive volume of data available. Notably, the paper recognizes that decision-making efficiency is time-sensitive in emergencies, and evolutionary algorithms, due to their dynamic nature, can generate solutions within a reasonable timeframe. Inspired by biological evolution, evolutionary algorithms can adapt and explore a diverse search space, allowing for more informed decision-making, enhanced operational efficiency, and increased food security. The paper delves into evolutionary algorithms’ theoretical foundations and principles, including genetic algorithms, evolution strategies, and differential evolution. It also discusses mathematical models for transportation optimization using evolutionary algorithms, providing examples of multi-index transportation problems and multi-objective traveling salesman problems. By leveraging these advanced methods, organizations can process and analyze their data more efficiently, leading to improved decision-making, enhanced operational efficiency, and increased food security. The paper provides insights into how these algorithms can be applied in logistics to improve food security, highlighting their potential applications and challenges.