Renewable Monitoring Platform — SolarNova Tech
Visual: fleet map, yield vs expected curves, and O&M ticketing.
Client Overview
SolarNova Tech operates and services distributed PV installations across Germany and neighbouring EU countries. They needed a robust platform to monitor performance, detect underperformance quickly, and optimize O&M workflows across a geographically distributed fleet.
- Fleet size: 300+ PV sites (utility & commercial)
- Users: O&M engineers, portfolio managers
- Duration: 8 months (PoC → production)
Challenge
Operators lacked fast detection of soiling, inverter faults, or grid-constraint losses. Manual data reconciliation and slow ticketing led to delayed fixes and lost generation. The client needed near-real-time detection, contextual root-cause suggestions, and prioritized actions for limited O&M capacity.
Solution — Fleet Monitoring & Smart O&M
We delivered a monitoring stack with site-level expected yield models, anomaly detection for soiling/inverter issues, alarm prioritization, and integrated ticketing with field-inspector mobile apps. The platform also ingests satellite & weather data to attribute yield variance.
Core features
- Expected yield models (irradiance + temperature correction) for site baselining.
- Anomaly detectors for soiling, shading, inverter derating and curtailment.
- Priority scoring for alarms to focus scarce O&M resources.
- Mobile inspection app for field data capture and ticket closure.
Approach
- Baseline yield models using historical SCADA and weather inputs.
- Run retrospective failure-mode analysis to design detectors and thresholds.
- Integrate with the client's existing ticketing and resource planning systems.
- Deploy pilot across 30 sites and refine prioritization before fleet rollout.
Technology stack
Implementation — Steps
Phase 1 — Baseline & PoC (Weeks 1–8)
Built expected yield baselines and sanity-checked historical deviations to instrument detectors.
Phase 2 — Anomaly Detection & Prioritization (Weeks 9–16)
Implemented detectors for common failure modes and developed priority scoring for tickets.
Phase 3 — Mobile O&M & Integration (Weeks 17–26)
Integrated mobile inspection app and workflows to close the loop between detection and field resolution.
Phase 4 — Fleet Rollout & Optimization (Weeks 27–36)
Scale to full fleet with performance SLAs and automated reporting for asset owners.
Impact & Results
18%
Increase in recovered energy from faster fault resolution
40%
Reduction in time-to-fix for high-priority alarms
25%
Reduction in O&M costs per kW due to prioritization
6 months
Time to fleet-wide benefits post-rollout
Qualitative outcomes
- Prioritization ensured critical yield losses were fixed first, maximizing ROI on limited O&M staff.
- Satellite-informed soiling insights allowed targeted cleaning campaigns instead of fleet-wide actions.
- Field data improved root-cause discovery and reduced repeat failures.
Client Testimonial
Key Highlights & Learnings
- Combine on-site SCADA signals with external weather/satellite data for better attribution.
- Priority scoring yields faster business value than surfacing every alarm equally.
- Mobile inspections are essential to close the loop and build confidence in automated alerts.