Machine Learning Drives Unprecedented Solar Efficiencies
Remote Issue Diagnosis | Intelligent Service Responses | Workflow Management
Omnidian’s unique collaboration between solar experts, software engineers, and data scientists across over 1,500 Megawatts of commercial and residential solar power assets has resulted in significant advances in monitoring, diagnostics and remediation of solar assets, driving unprecedented insights and significant operational efficiencies.
In this White Paper, we explore:
The Future of Machine Learning In Solar
- Dramatic improvements in symptom detection, root-cause diagnostics and optimized asset remediation are driving greater efficiencies through remote issue diagnosis and intelligent service responses.
Integrated Performance Assessment and Workflow Management
- Technical advances are enabling real-time forecasts of expected energy generation driven by live satellite imagery.
- Significantly improved workflows through remote diagnosis and targeting of high-priority alerts compared with low actionability noise (snow, temporary soiling).
- Advanced triage tools providing automated diagnosis along with production, service history and past performance, enabling rapid human intervention and service confirmation.
- Unique access to data from hundreds of thousands of solar assets across the U.S. is driving unprecedented performance analytics by manufacturer, geography and local environments.
- Real-time performance analysis goes beyond field measurements which are often performed at the time of installation or activation therefore failing to assess changing conditions.
- Crisis management; the wildfires of 2020 drove analysis by region, tailoring real-time advice to homeowners in the context of fire zones and more urgent homeowner priorities.