Presentation Description: The solar asset class is distinct from traditional power generation equipment and from wind power assets. The quality and granularity of data sensors is different, and the energy conversion process takes place in a hermetically sealed semiconductor package with no moving parts. How, then, do you approach performance monitoring for this type of asset?
If renewables are going to change the way the world is powered, owners and operators need to know how they are performing relative to bank models and expected performance. Just because it’s challenging doesn’t mean it’s not worth doing.
Whether the core monitoring methods use first principle physical models, artificial intelligence or machine learning, they all rely on a foundation of good quality process data. This foundation of trustworthy data can be very difficult to achieve—especially when you’re talking solar assets.
This presentation will lay out the top four challenges of developing and implementing asset monitoring software: 1. The challenge of scale 2. The challenge of granularity 3. The challenge of selecting the right model 4. The challenge of real-world data
Any one of these challenges can cause a solar monitoring application to fall flat on its face—and once operators lose confidence in the application, it is doomed. Is there hope for any solar monitoring application? The second half of the presentation will show ways to address and overcome these challenges.
Upon completion, participants will be able to identify the main challenges for solar asset monitoring with practical examples.
Upon completion, participants will be able to understand the best approaches to overcome these challenges.
Upon completion, participants will be able to directly connect these lessons to their own portfolio, based on real-world case studies that exemplify common industry-wide issues.