Back to Success Stories
Automatic fine-tuning of distributed predictive models

ACCIONA spent significant time and resources manually testingwater samples in a laboratory to determine chemicalconcentrations. Due to the time it took to obtain these results,they were often outdated and unreliable. This resulted inadditional costs related to chemical supply and regulatory penalties.

By implementing real-time optimized Machine Learning control algorithms at each of its desalination plants, ACCIONA was able to minimize the use of reactive chemicals, eliminate associated regulatory penalties, and provide an efficient edge infrastructureto implement new applications for predictive maintenance, energy efficiency, sensing, optimization or reinforcement learning.