Plant Production. PVSyst guessed it back then.
We can tell you today. With Quadrical Digital Twins.
Commissioning models set financial benchmarks for investors.
By adding real-world conditions, then, automatically calibrating them in RealTime, Quadrical Digital Twin models set a live, personalized, more accurate benchmark. Down to every sensor-ed device.
ML Training with Historical Data · False Positive Limiting Design
Operations need accurate loss calculations
Those Project Finance numbers are now the benchmark for the next 25 years of a plant’s operations. Operations teams need to attribute losses accurately for the next 25 years.
Some losses just may be invisible – hiding – yet still can become expensive problems.
In a 9.26 MW plant audited over 3 months, Quadrical's Digital Twin AI found 620 MWh of undetected generation capacity — $126,078 of recoverable yield. This older plant had high PPA’s and had been continuously monitored.
Losses weren't hidden. Just invisible to the tools being used.
The Solution?
An Accurate Virtual Data Replica. Unique to Every Device. Always On.
A Quadrical Digital Twin is a unique model created for every physical device in your portfolio — inverter, string, battery cell node. It learns exactly how that specific device behaves using peer behavior, age, degradation history, operational characteristics.
A typical 50 MW solar site may have hundreds of individual twins — per device, per job.
When an inverter starts clipping earlier than it should, a string’s performance drops below peers or a battery's round-trip efficiency slips — Quadrical Digital Twins catch it.
Next, they classify the deviation, quantify revenue impact and generate tickets.
All because, our model always knows what that exact device’s normal looks like.
And can compare with Digital Twins from years ago so the comparison flags up unseen issues.
This is the difference between just monitoring and intelligence.
Quadrical builds in this intelligence right into your Asset Management platform not something you pay for separately. This allows you to manage your whole fleet and optimize each asset. Continuously. Automatically. In RealTime.
All of This Is Already Running Inside Your Asset Management Platform.
Quadrical Digital Twin Analytics is not an add-on cost. It's built into the platform — so from the moment you're live, every device in your portfolio is ready for its own twin to track deviations and generate revenue-prioritized tickets.
Inside the models
For those who want to go deeper into wonky details.
For Asset Managers, gradual degradation is both commercially significant and the hardest to see. A module cluster losing a fraction of output monthly — there’s no alarms – just silent, compounding losses multiplying across your portfolio.
How the Structural Twin catches it.
By watching how one device performs relative not only to its peers but also to comparable devices at the same plant within the same conditions. Underperformance is a structural signal.
To ensure accuracy, our baseline recalculates monthly to absorb any seasonal effects.
Deviation Types Detected and Classified
In the field
Case Study 1 — 67 MWdc Solar Plant [8 Months of Digital Twin-driven O&M]
- Baseline: 7.3% total loss [30-day moving average]
- Result: 3.1% total loss — 4.2% sustained reduction
- Trend: downward — each O&M cycle drives losses lower
Case Study 2 — 9.26 MWdc Plant Audit [3 Months]
- 9.26 MWdc · 920 strings · 13 inverters · 33,877 panels.
- 620 MWh = $126,078 of extra energy yield identified in 3 months.
- Digital Twin Benchmark PR: 0.98 vs. Standard PR: 0.88.
- Key finding: severity ranked list of every string with data inconsistencies, long-term underperformers, slackers and strings uncorrelated with the Digital Twin benchmark.
“Quadrical’s Digital Twin approach was instrumental in setting realistic expectations and then pinpointing areas of underperformance.”
All of This Is Already Running Inside Your Asset Management Platform.
15,000+ MW of Solar, Storage, and Wind are already running on it. See what that looks like for yours.