TY - JOUR AU - Puente, Jorge AB - The growing energy consumption of cloud infrastructure has attained levels that are no longer viable, necessitating the development of energy-aware scheduling algorithms. This work focuses on optimising the scheduling of scientific workflows, which requires extensive computation to achieve time-efficient results, often at the cost of excessive energy consumption. To address this challenge, a multi-fitness evolutionary algorithm that integrates multiple heuristic functions in a cooperative manner to minimise energy consumption is proposed. The approach not only facilitates the reuse of heuristics but also provides novel insights into the interplay between energy consumption and makespan, traditionally viewed as conflicting objectives. This flexible framework demonstrates its adaptability for optimising both total energy consumption and completion time, offering a robust tool for sustainable workflow scheduling. TI - Energy-aware cooperative multi-fitness evolutionary algorithm for workflow scheduling in cloud computing JF - Natural Computing DO - 10.1007/s11047-025-10023-y DA - 2025-06-11 UR - https://www.deepdyve.com/lp/springer-journals/energy-aware-cooperative-multi-fitness-evolutionary-algorithm-for-M3DZl8a0dh SP - 1 EP - 14 VL - OnlineFirst IS - DP - DeepDyve ER -