[u' @article{diaz-de-arcaya_orfeon_2022, title = {Orfeon: {An} {AIOps} framework for the goal-driven operationalization of distributed analytical pipelines}, volume = {140}, issn = {0167739X}, url = {https://doi.org/10.1016/j.future.2022.10.008}, doi = {10.1016/j.future.2022.10.008}, abstract = {The use of Artificial Intelligence solutions keeps raising in the business domain. However, this adoption has not brought the expected results to companies so far. There are several reasons that make Artificial Intelligence solutions particularly complicated to adopt by businesses, such as the knowledge gap between the data science and operations teams. In this paper, we tackle the operationalization of distributed analytical pipelines in heterogeneous production environments, which span across different computational layers. In particular, we present a system called Orfeon, which can leverage different objectives and yields an optimized deployment for these pipelines. In addition, we offer the mathematical formulation of the problem alongside the objectives in hand (i.e. resilience, performance, and cost). Next, we propose a scenario utilizing cloud and edge infrastructural devices, in which we demonstrate how the system can optimize these objectives, without incurring scalability issues in terms of time nor memory. Finally, we compare the usefulness of Orfeon with a variety of tools in the field of machine learning operationalization and conclude that it is able to outperform these tools under the analyzed criteria, making it an appropriate system for the operationalization of machine learning pipelines.}, language = {en}, urldate = {2022-10-24}, journal = {Future Generation Computer Systems}, author = {D\xedaz-de-Arcaya, Josu and Torre-Bastida, Ana I. and Mi\xf1\xf3n, Ra\xfal and Almeida, Aitor}, month = jan, year = {2022}, keywords = {AIOps, JCR7.307, MLOps, Q1, analytical pipelines, artificial intelligence, edge computing, machine learning, machine learning operationalization, mlops}, pages = {18--35}, } ']