From drift to adaptation to the failed ml model: Transfer Learning in Industrial MLOps
This work addresses model adaptation for MLOps practitioners in industrial settings, but it is incremental as it applies existing transfer learning methods to a specific case study.
The paper tackled the problem of updating failed ML models under data drift in industrial MLOps by comparing transfer learning strategies (ETL, ALTL, LLTL) on a feedforward ANN for flue gas differential pressure in a thermal power plant, finding that ETL provided higher predictive accuracy for a 5-day batch size while ALTL was better for an 8-day batch size.
Model adaptation to production environment is critical for reliable Machine Learning Operations (MLOps), less attention is paid to developing systematic framework for updating the ML models when they fail under data drift. This paper compares the transfer learning enabled model update strategies including ensemble transfer learning (ETL), all-layers transfer learning (ALTL), and last-layer transfer learning (LLTL) for updating the failed feedforward artificial neural network (ANN) model. The flue gas differential pressure across the air preheater unit installed in a 660 MW thermal power plant is analyzed as a case study since it mimics the batch processes due to load cycling in the power plant. Updating the failed ANN model by three transfer learning techniques reveals that ETL provides relatively higher predictive accuracy for the batch size of 5 days than those of LLTL and ALTL. However, ALTL is found to be suitable for effective update of the model trained on large batch size (8 days). A mixed trend is observed for computational requirement (hyperparameter tuning and model training) of model update techniques for different batch sizes. These fundamental and empiric insights obtained from the batch process-based industrial case study can assist the MLOps practitioners in adapting the failed models to data drifts for the accurate monitoring of industrial processes.