All Tags AWS ai algorithm-design architecture browser cloud cloud-efficiency cloud-principles cost-reduction data-centric data-compression data-processing deployment design documentation edge-computing email-sharing energy-efficiency energy-footprint enterprise-optimization green-ai hardware libraries llm locality machine-learning maintainability management measured microservices migration mobile model-optimization model-training multi-objective network-traffic parameter-tuning performance queries rebuilding scaling services storage-optimization strategies tabs template testing workloads

Tactic: [Using Energy-Efficient Multi-Objective Optimization for AI Training and Inference]

Tactic sort: Awesome Tactic

Type: Architectural Tactic

Category: green-ml-enabled-systems

Tags: algorithm-design machine-learning performance

Title

[Using Energy-Efficient Multi-Objective Optimization for AI Training and Inference]

Description

Applying a dynamic, phase-aware multi-objective optimization algorithm to AI model training and inference. It balances energy consumption and model accuracy by using gradient-based optimization techniques, Pareto front analysis, and real-time performance feedback. The system dynamically adjusts learning rate, quantization levels, and trade-off weights to minimize energy usage without degrading accuracy beyond an acceptable threshold

Participant

AI engineers

Related software artifact

AI models integrated within enterprise applications (e.g.,deep learning pipelines, inference services)

Context

Large-scale enterprise environments where AI models are deployed for operational decision-making or automation, and where energy usage is a cost or sustainability concern

Software feature

Model training and inference phases with support for dynamic optimization (e.g., adjustable learning rates, quantization strategies, gradient sparsity)

Tactic intent

To reduce the overall energy consumption of AI systems while ensuring model performance remains within acceptable bounds

Target quality attribute

Energy efficiency

Other related quality attributes

Performance

Measured impact

Energy consumption, Accuracy, Task execution time

Source

S. Dash, Green AI: Enhancing Sustainability and Energy Efficiency in AI-Integrated Enterprise Systems, in IEEE Access, vol. 13, pp. 21216-21228, 2025 (DOI: https://doi.org/10.1109/ACCESS.2025.3532838.)