The installed capacity of solar powerin the U.S. now exceeds all other forms of power generation.
Generating solar power at scale with thousands of panels requires new approaches to monitoring and management. Since 2004, SunPower has designed, constructed, managed and supplied high performance solar power plants around the world. More than 3 gigawatts of solar plants rely on SunPower technology today.
How does SunPower monitor thousands of solar panels across hundreds of power plants? How are performance issues remotely diagnosed and troubleshot in real-time? How are false alerts distinguished from real ones?
Background
SunPower manages 700 power plants from two Remote Operations and Control Centers (ROCC) in Austin, Texas, and the Philippines. These centers operate around the clock and control over 2.5 GW of commercial solar power. Sensors in inverters, trackers, combiner boxes, transformers, weather stations generate enormous streams of data.
Sensors can generate false positives that demand attention even when the systems are working properly. Operators were flooded with alerts, suffering from alert fatigue as they navigated between multiple systems to address each issue. “Our operators were getting too many alerts, and had to make too many clicks to get anything done,” said Sarah Herman, Senior Manager of Monitoring Operations at SunPower. “It was challenging to standardize our operator’s behavior in this kind of environment.”
SunPower initially relied on dedicated servers to process sensor data, but this was costly and created single points of failure. A new approach was needed that could provide scale better and provide better insights and as operations expanded.
The Solution
SunPower chose Krypton’s “Asset Intelligence as a Service” to streamline its operations. It integrates with their existing IBM Maxino (enterprise asset management) and OSIsoft PI (Data Historian) systems.
Krypton Collect data agents were used to integrate data from the enterprise systems as well as SCADA enabled devices. The agents’ distributed architecture makes data accessible and searchable instantly. Both human- and machine-generated data is co-related for better analysis.
Krypton Decision Engine, a real-time stream processing engine to process billions of sensor readings daily. This enables SunPower to process a more data against a complex set of alert rules and performance calculations to better identify and resolve issues.
Results
In the first quarter of deployment, SunPower’s Command Center reported half as many false alarms and nuisance alerts. Response times are reduced as performance issues and alerts are processed faster. When an alarm comes in, operators can quickly see relevant time-series data, search for similar prior events to help diagnose and troubleshoot directly from the Krypton interface.
SunPower measures the effectiveness of its operations by response time needed to resolve issues.“Our data is now all in one place – we don’t have to go look in separate servers for different kinds of information and alerts,” said Sarah Herman, Senior Manager of Monitoring Operations at SunPower.
SunPower and Krypton are now shifting SunPower’s operations and maintenance (O&M) from reactive to predictive. Machine learning algorithms are being applied to SunPower’s historical dataset of system performance, to better predict and diagnose failures.
This article is published as part of the IDG Contributor Network. Want to Join?
