Skip to main navigation Skip to search Skip to main content

Energy-Efficient AI-Assisted Evolution: A Case Study on Minimizing the Power Consumption of Deep Neural Crossover

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Deep-learning-based genetic operators can substantially improve evolutionary search quality, but they also introduce significant computational and energy overhead, bringing the Red AI vs. Green AI tension into evolutionary computation. In this work, we study the energy footprint of Deep Neural Crossover, a reinforcement-learning-based multi-parent crossover operator, and evaluate parameter-level strategies to reduce its power consumption without sacrificing solution quality. We profile experiments with process-level energy measurements and analyze two optimization levers: training batch size and a new fitness-based scheduling threshold that triggers backpropagation only after meaningful fitness improvement. Experiments on benchmark Bin-Packing and Graph Coloring instances show that changing batch size alone has little effect on total energy, whereas the proposed scheduling strategy yields substantial savings. In particular, using larger scheduling thresholds considerably reduces energy consumption while keeping fitness close to the best-performing configurations and, in several cases, matching or improving it. These results provide a practical pathway for greener neuro-evolutionary algorithms through adaptive training schedules.

Original languageEnglish
Title of host publicationParallel Problem Solving from Nature – PPSN 19 - 19th International Conference, PPSN 2026, Proceedings
EditorsGiovanni Iacca, Giorgia Nadizar, Anil Yaman, Doina Bucur, Antonio Della Cioppa, Ting Hu, Eric Medvet, Sarah L. Thomson
PublisherSpringer Science and Business Media Deutschland GmbH
Pages417-432
Number of pages16
ISBN (Print)9783032362162
DOIs
StatePublished - 1 Jan 2027
Event19th International Conference on Parallel Problem Solving from Nature, PPSN 2026 - Trento, Italy
Duration: 29 Aug 2026 → 2 Sep 2026

Publication series

NameLecture Notes in Computer Science
Volume16989 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference19th International Conference on Parallel Problem Solving from Nature, PPSN 2026
Country/TerritoryItaly
CityTrento
Period29/08/26 → 2/09/26

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy

Keywords

  • Deep Learning
  • Genetic Algorithm
  • Genetic Operators
  • Green AI
  • Green computing
  • Red AI

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Energy-Efficient AI-Assisted Evolution: A Case Study on Minimizing the Power Consumption of Deep Neural Crossover'. Together they form a unique fingerprint.

Cite this