mlsanityData to 14 Oct 2026

A Synthesis of Green Architectural Tactics for ML-Enabled Systems

arXiv 2312.09610 ↗First posted 15 Dec 2023cs.SE cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

The rapid adoption of artificial intelligence (AI) and machine learning (ML) has generated growing interest in understanding their environmental impact and the challenges associated with designing environmentally friendly ML-enabled systems. While Green AI research, i.e., research that tries to minimize the energy footprint of AI, is receiving increasing attention, very few concrete guidelines are available on how ML-enabled systems can be designed to be more environmentally sustainable. In this paper, we provide a catalog of 30 green architectural tactics for ML-enabled systems to fill this gap. An architectural tactic is a high-level design technique to improve software quality, in our case environmental sustainability. We derived the tactics from the analysis of 51 peer-reviewed publications that primarily explore Green AI, and validated them using a focus group approach with three experts. The 30 tactics we identified are aimed to serve as an initial reference guide for further exploration into Green AI from a software engineering perspective, and assist in designing sustainable ML-enabled systems. To enhance transparency and facilitate their widespread use and extension, we make the tactics available online in easily consumable formats. Wide-spread adoption of these tactics has the potential to substantially reduce the societal impact of ML-enabled systems regarding their energy and carbon footprint.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 27 of its 69 references that are in the map. First posted on arXiv 15 Dec 2023.

Builds on

27 of 69 references.

References · 27

  1. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  2. 2019Green AIcited by 627
  3. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  4. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 249
  5. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  6. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  7. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 134
  8. 2023A Systematic Review of Green AIcited by 77
  9. 2019Requirements Engineering for Machine Learning: Perspectives from Data Scientistscited by 49
  10. 2019Optimizing the energy consumption of spiking neural networks for neuromorphic applicationscited by 37
  11. 2019E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savingscited by 36
  12. 2022Data-Centric Green AI: An Exploratory Empirical Studycited by 25
15 more
  1. 2019Energy-Aware Analog Aggregation for Federated Learning with Redundant Datacited by 23
  2. 2020Towards Guidelines for Assessing Qualities of Machine Learning Systemscited by 16
  3. 2023Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AIcited by 16
  4. 2023Energy Efficiency of Training Neural Network Architectures: An Empirical Studycited by 15
  5. 2021Software Architecture for ML-based Systems: What Exists and What Lies Aheadcited by 13
  6. 2018Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Maskingcited by 11
  7. 2021IrEne: Interpretable Energy Prediction for Transformerscited by 11
  8. 2021On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networkscited by 10
  9. 2022Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Modelscited by 6
  10. 2023Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repositorycited by 4
  11. 2023Estimating Deep Learning energy consumption based on model architecture and training environmentcited by 4
  12. 2019NeuPart: Using Analytical Models to Drive Energy-Efficient Partitioning of CNN Computations on Cloud-Connected Mobile Clientscited by 3
  13. 2020Sparse Optimization for Green Edge AI Inferencecited by 3
  14. 2021Energy-Efficient AI over a Virtualized Cloud Fog Networkcited by 3
  15. 2020Energy-Aware DNN Graph Optimizationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 8; 2026: 3.

17 papers.

Sort:

By area:

  1. 2025Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practicescited by 8
  2. 2024How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detectioncited by 3
  3. 2024Innovating for Tomorrow: The Convergence of SE and Green AIcited by 3
  4. 2024Balancing Progress and Responsibility: A Synthesis of Sustainability Trade-Offs of AI-Based Systemscited by 2
  5. 2024Towards Green AI: Current status and future researchcited by 2
  6. 2024Impact of ML Optimization Tactics on Greener Pre-Trained ML Modelscited by 2
  7. 2025Choosing to Be Green: Advancing Green AI via Dynamic Model Selectioncited by 2
  8. 2026On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experimentcited by 2
  9. 2024The More the Merrier? Navigating Accuracy vs. Energy Efficiency Design Trade-Offs in Ensemble Learning Systemscited by 1
  10. 2025Aggregating empirical evidence from data strategy studies: a case on model quantizationcited by 1
  11. 2025How Do Companies Manage the Environmental Sustainability of AI? An Interview Study About Green AI Efforts and Regulationscited by 1
  12. 2025Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracycited by 1
5 more
  1. 2025SpecDetect4ML: Detecting Non-Local ML Code Smells with Code Property Graphscited by 1
  2. 2025HarmonE: A Self-Adaptive Approach to Architecting Sustainable MLOpscited by 0
  3. 2025SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Modelscited by 0
  4. 2026KGroups: A Versatile Univariate Max-Relevance Min-Redundancy Feature Selection Algorithm for High-dimensional Biological Datacited by 0
  5. 2026RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystemscited by 0