As the installation of renewable energy projects grows, so too does the need for smart SCADA tools – the control systems behind the infrastructure – to manage day-to-day operations and optimise performance, writes Jorge Acedo, pictured.
These tools must meet the needs of everyone involved. They must be comprehensive, digital tools that create a full coverage suite, working with real-time data as well as supporting O&M and strategic management decisions. Successful integration into a single product is key in solving the most complex operational challenges.
Each renewable energy project has unique characteristics down to the environmental features and topography of that location. Each asset owner faces different challenges, depending on its mix of assets and systems. There is no one-size-fits-all system; customization is essential.
Digital twins are one of a SCADA solutions most important tools. These advanced analytical models solve problems arising from the management of renewable energy plants to improve performance and extend their life. They use data to gain important insights into assets' health and performance and so support decision making. Understanding the performance, identifying underperformance and taking corrective maintenance creates genuine value through extending asset lifetimes.
Using a data-driven digital twin: a case study
This focuses on data-driven digital twin based on real-time SCADA data using INGETEAM’s INGESYSTM Smart SCADA product. Asset owners can easily analyze this SCADA data using Ingeteam’s analytics tool suite. There are a number of benefits to using this strategy.
An asset owner in Latin America, with a portfolio spanning four countries, including wind farms and photovoltaics plants, needed to unify the data its wind and solar assets generated to create value. The real challenge was to build a central SCADA platform to optimise its O&M decisions across different technologies and countries. Available
data integrated into the INGESYSTM Smart SCADA to build the digital twin. This was performed by:
- Detecting key component behavior changes and trends. KPIs monitor the operational performance of each plant in the portfolio, providing an overview of the health and performance of each unit. The system creates KPIs automatically and uses them across the organisation to measure and direct O&M.
- Integrating machine learning algorithms to detect anomalies. Modules use machine learning models for each key component in the wind farms and solar plants. These learn the normal behavior of the components and continuously track performance, raising alerts to deviations, meaning technicians can focus resource in the right areas.
- Applying visual analytics. Time is a scarce resource for field technicians. Visual analytic tools allow technicians to explore the huge amount of data and identify performance issues without needing data scientist skills.
- Analysis of performance and power curves. Asset performance is a key factor that must be closely watched. Machine learning models and KPIs detect early deviations from the underlying trends.
Identifying underperformance Using the digital twin created for the specific assets of the client, a comprehensive performance analysis was carried out. This analysis detected that one of the wind farms in the portfolio was not performing as expected. The system identified the root causes of this underperformance and the client was able to take action. That's how this works: a problem emerges, the client can concentrate their O&M efforts only on the affected wind turbines.
Enhancing security Applied data science not only provides performance improvements. Security enhancements for aging assets is also a key value driver. For instance, the client was able to spot abnormal thermal behavior in a subset of the transformers. This insight allowed the client to launch an O&M campaign to correct the issue before it escalated.
Curtailment losses In another example, the curtailment losses associated to a specific solar plant were calculated in fine detail and economic savings were achieved by means of joints work with the transmission system operator (TSO).
Overall, the deployment of the Central SCADA improved the internal processes and decision making for managing all the client’s assets.
As a result, in the first year following the implementation of improvements, the client generated estimated savings of over $500,000.
The use of digital twins and advanced analytics enables all users, from operators and O&M technicians to performance and reliability analysts and managers, to have the right tools and the necessary information to meet their specific needs within one central platform. Information is available for each user type without division into difficult to access silos.
Within our Smart SCADA platform, we can optimise a suite of specific tools for each stakeholder. The overall decision-making process improves, beginning with real-time operators, field technicians and ending with skilled O&M analysts and managers.
In the case study presented, we believe that INGESYSTM Smart SCADA was a key factor in the digital transformation of our customer's asset management.
Pictured below: machine learning dashboard
.png)
.png)
