Sign up to know more
The client deals with planning, design, and construction management of water and wastewater-related projects – from clean water treatment, storage, and distribution to wastewater and stormwater collection, treatment, and reuse.
The client developed an algorithm to predict water stream speeds hourly, essential for optimizing resources in their water treatment plant. However, they faced challenges with collaboration, model versioning, and capturing model performance due to the algorithm being isolated in a silo.
To address these issues, the client needed a comprehensive data model that included model development, tuning, versioning, and deployment. They also required an automated workflow using Azure for orchestrating production data. Specifically, they wanted a scheduled job to run hourly, fetching data from an Azure SQL database, feeding it to the deployed model, and storing predictions back in the database.
SNP utilized Azure Machine Learning Service to deploy the client’s algorithm in the cloud, ensuring a cost-effective and scalable data platform. They implemented an Azure Data Factory pipeline to automate the hourly job, which now generates Power BI reports. This allows the client to effectively analyze predictions and make informed resource planning decisions for their water treatment operations.
The client has started using the Data Factory pipeline (scheduled as an hourly job) to generate Power BI reports to cater to their BI needs and to plan resources in their water treatment plant by looking at the predictions coming from the model sitting on Azure.
