GREENDAI: Towards an observability tool for sustainable green distributed artificial intelligence

The growth of intelligent systems based on distributed artificial intelligence has generated an urgent need to assess their environmental impact and sustainability. The expansion of AI technologies has driven an increase in demands for computing resources and has augmented the need to adapt to more efficient forms of computing. such as distributed AI or Edge AI. Additionally, there is growing concern about energy consumption and the environmental footprint of these technologies. In this paper, our main contribution is the definition of a Distributed Artificial Intelligence systems observability tool architecture for green and sustainability perspectives. This tool is designed to report adequate KPIs by measuring the energy consumption, data usage, computational efficiency and carbon footprint of decentralized AI based components. This innovative approach not only promotes the development of more sustainable technologies but also encourages transparency and responsibility in the sustainable use of distributed and large-scale AI systems. To validate the approach, its feasibility and integration have been analyzed in an experimental use case of a Distributed AI system. The use case is a Federated Machine Learning based system, in which the benefits of reporting energy efficiency and sustainability metrics are analyzed.