All Tags
AWS
algorithm-design
architecture
cloud-principles
cost-reduction
data-centric
data-compression
data-processing
deployment
design
edge-computing
energy-footprint
hardware
libraries
locality
machine-learning
management
measured
migration
model-optimization
model-training
performance
queries
rebuilding
scaling
services
strategies
template
workloads
Tactic: Set Energy Consumption as a Model Constraint
Tactic sort:
Awesome Tactic
Type: Architectural Tactic
Category: green-ml-enabled-systems
Title
Set Energy Consumption as a Model Constraint
Description
This tactic concerns setting a predetermined energy consumption threshold for the ML model optimization process. The optimization considers the energy consumption of the model during both the optimization and training phases. The objective is to train the model in a way that it stays within the specified energy consumption threshold. This approach views model optimization as an optimization problem, where for instance hyperparameters and the model itself are optimized based on the predetermined limits.
Participant
Data Scientist
Related software artifact
Machine Learning Algorithm
Context
Machine Learning
Software feature
< unknown >
Tactic intent
Improve energy efficiency by setting energy consumption as a constraint such that the model will stay below the threshold during training
Target quality attribute
Energy Efficiency
Other related quality attributes
Accuracy, Performance
Measured impact
< unknown >
Source
Qu Wang, Yong Xiao, Huixiang Zhu, Zijian Sun, Yingyu Li, and Xiaohu Ge. 2021. Towards Energy-Efficient Federated Edge Intelligence for IoT Networks. In 2021 IEEE 41st International Conference on Distributed Computing Systems Workshops. [DOI](https://doi.org/10.1109/ICDCSW53096.2021.00016); Haichuan Yang, Yuhao Zhu, and Ji Liu. 2019. Energy-Constrained Compression for Deep Neural Networks Via Weighted Sparse Projection and Layer Input Masking. International Conference on Learning Representations (ICLR) (2019) (ICDCSW). 55–62. [DOI](https://doi.org/10.48550/arXiv.1806.04321)Graphical representation
