Machine Learning at the Edge to optimise chemical usage in water plants

The monitoring and operation processes of a water network have traditionally been carried out using sensors and SCADAs, but they are largely operator-dependent. Given the criticality and the volumes of data handled, infrastructure managers are now running advanced algorithms at the edge. In this article, we explore the real case of deploying Machine Learning at the Edge to optimise chemical control processes in real time.

Water management
Written by:
Miren Zabaleta

Improved water treatment efficiency with Machine Learning

The reagent dosing control loops target variable elements or chemical compounds in the water that cannot be detected continuously with a probe. Instead, water samples need to be analysed in the lab in order to detect the levels of these elements. Results can take more than a day and by the time they come back they are no longer valid. Before the introduction of advanced ML algorithms the control loops used variables indirectly related to the element in question or even discrete manual intervention.

With the introduction of advanced machine learning (ML) algorithms in the industry, there is now a tremendous opportunity to overcome these challenges. ML algorithms can analyze vast amounts of data and identify patterns that help accurately determine the levels of chemical elements in the water once only detectable through a laboratory analysis.

AI Deployment and Orchestration at the Edge: how Acciona optimized water management

The monitoring and operation processes of a water network have traditionally been carried out using sensors and SCADAs, but they are largely operator-dependent. However, the evolution and democratisation of AI in recent years means that faster, larger-scale analysis can be possible now, including historic data and thus, more accurate results and forecasts can be obtained.

Given the criticality and the volumes of the data handled, infrastructure managers are choosing to run AI algorithms in edge computing platforms to obtain real-time responses without compromising the OT network. Barbara’s proposed solution provided the necessary software infrastructure to deploy and orchestrate AI at the Edge. The project consisted of a system for monitoring communication with water management plant OPC-UA servers and the deployment of intelligence algorithms at the edge, involving:

  1. Connectivity and data processing with alarms in case of an incident.
  2. Running, updating and configuring “dockerized” applications remotely and securely.  
  3. Edge nodes monitoring and management of their entire lifecycle (upgrades, reconfigurations, etc).
  4. A graphic interface to view measurements in real-time

Deploying and Managing Al at the Edge: Acciona's Success Story with Barbara Edge Platform

The main technological challenge was related to the connectivity OPC-UA protocol, and the authentication requirements to connect to the server and read parameters simply and separately, so that it would not affect the normal running of the plant. The data exchanged between the edge node (gateway edge) and by extension, the OPC-UA server/client and Acciona’s remote servers are controlled by the application both, on the Edge gateway and on local servers. At each water plant there is a local OPC-UA server/client with which, via an Edge node loaded with Barbara OS (Secure Operating System), Acciona can access all information related to that specific plant.The data exchanged between the edge node, the OPC-UA server/client and Acciona’s remote servers are controlled by the applications deployed by Acciona both, on the Edge Node and on local servers.

With Barbara Management Panel, ACCIONA can run “dockerized” applications, and upgrade, update and configure them remotely and securely. Acciona can also control the edge node and manage its entire lifecycle.

The monitoring of all installations is carried out in real time and on the same display platform. The use of IoT gateways using Barbara OS, overcomes the equipment fragmentation issues at each site. Regardless of the type or manufacturer of the data reporting devices, all the information collected is received and managed in the same format. Once installed, all tasks are performed remotely. Configuration changes and software adjustments are made remotely during the data collection and review phase. Furthermore, device and data security is never compromised. Data is stored and transmitted in an encrypted format. Access to any software or hardware is secure. The chances of data leakage or device hacking are minimal. Barbara OS allows these security measures to apply across all edge gateways.

Barbara has provided us with a reliable, robust and easy-to-use platform on which to deploy our solution, as well as assisting us with the development of specific software to support our vision. Alejandro Beivide, Chief Digital Officer - ACCIONA

Discover more about Acciona´s success Edge AI deployment . Download it now

  • Reduce the deployment time of its Edge applications by 86%.
  • Optimize its chemical control processes in real-time and in a cybersecure way.
  • Save 250.000 € per plant in its first year.

Want to be ahead about Edge AI? Replay the webinar and learn best practices in implementing Machine Learning (#ML) at the Edge, from optimization, and deployment to monitoring.

🔒 Enhance Data Access, Security and Privacy through Federated Learning

💪 The tools, systems and structures you need to put in place for real-time AI

🚀 Improve model performance for Computer Vision

⚙️ Run successful Machine Learning Model Inference

💡 Optimize ML models for edge devices

🔒 Secure your ML models in the edge

Barbara, the Cybsersecure Edge Platform for Water Plants

Edge Computing is becoming an essential technology for organizations looking to take full advantage of the Internet of Things (IoT) and other edge-oriented technologies. With the explosion of connected devices and the need for real-time data processing, it is no longer practical to send all data to a centralized data centre. An Edge Platform is necessary to orchestrate this infrastructure as it provides the ability to manage and control the edge devices, applications, and data, while also providing security, scalability and flexibility. Barbara helps organizations simplify and accelerate their Edge App deployments, building, orchestrating and maintaining easily container-based or native applications across thousands of distributed edge nodes:

  1. Real-time data processing: Barbara allows for real-time data processing at the edge, which can lead to improved operational efficiency and cost savings. By processing data at the edge, organizations can reduce the amount of data that needs to be transmitted to the cloud, resulting in faster response times and reduced latency.
  2. Improved scalability: Barbara provides the ability to scale up or down depending on the organization´s needs which can be beneficial for industrial processes that have varying levels of demand.
  3. Enhanced security: Barbara offers robust security features to ensure that data is protected at all times. This is especially important for industrial processes that deal with sensitive information.
  4. Flexibility: Barbara is a flexible platform that can be customized to meet the specific needs of an organization. This allows organizations to tailor the platform to their specific use case, which can lead to improved efficiency and cost savings.
  5. Remote management: Barbara allows for remote management and control of edge devices, applications and data, enabling organizations to manage their infrastructure from a centralized location.
  6. Integration: Barbara can integrate with existing systems and platforms, allowing organizations to leverage their existing investments and improve efficiency.