A Synthesis of Green Architectural Tactics for ML-Enabled Systems

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 footprintCCS CONCEPTS• Software and its engineering → Designing software; Software architectures; • Social and professional topics → Sustainability; • Computing methodologies → Machine learningLay Abstract: Machine learning (ML) is a technology field that wants to provide software with functionality similar to humanlike intelligence, e.g., for understanding text or describing images. However, creating and using systems with ML needs a lot more computing power than non-ML systems, which is bad for the environment. Companies therefore need concrete advice on how they can create ML systems that are environmentally sustainable. In this paper, we provide a catalog of 30 green architectural tactics for these systems. An architectural tactic is a high-level design technique to improve software quality, in our case environmental sustainability. To achieve this, we analyzed 51 scientific papers and later discussed with 3 experts to improve and extend our catalog. If many companies start using these tactics, the energy footprint of systems with ML can be greatly reduced.