Performance+ is Bazefield's native advanced-analytics product for utility-scale solar PV. It turns raw plant SCADA and meteorological data into a complete, auditable picture of how a site is performing, why, and what it is costing - production, losses attributed to their root cause, revenue impact, degradation, and prioritised O&M actions.

This document is the entry point to the Performance+ solar documentation. It summarises what the product does, what makes it different, and how the underlying pipeline fits together, then links out to the detailed technical notes for each capability.

What Performance+ delivers

From the same input data and the same status-detection layer, Performance+ produces:

  • A physics-based expected-power reference per inverter - the yardstick every loss is measured against.
  • A full loss breakdown that attributes every lost kWh (and its revenue) to a specific root cause - curtailment, clipping, downtime, soiling, DC faults, tracker, thermal, inverter efficiency, and more.
  • Health analytics at every level: irradiance sensors, inverters, DC strings and combiner boxes, trackers.
  • Long-term degradation and Performance Loss Rate (PLR) trending.
  • Structured events and cases that feed the O&M workflow.

All of it runs unattended, per site, on native plant data - no manual modelling step per asset.

What makes Performance+ unique

Highlight Why it matters
Physics-based expected power - a transparent, per-inverter model incorporating degradation, thermal effects and system losses (not a black-box regressor). Explainable reference that asset owners and OEMs can audit line by line. See Physics-based Expected DC and AC Power.
Automatic sensor-health KPI & daily sensor selection - rates every irradiance sensor and picks the best one per inverter, per day. Bad or drifting sensors no longer silently corrupt performance numbers. See Sensor Health KPI & Sensor Selection.
Row-to-row sensor-shading detection & correction on single-axis trackers. Recovers otherwise-lost irradiance data instead of discarding shaded periods. See Irradiance Sensor Shading.
Inverter-based soiling - no soiling station required. Detects soiling rate, cleaning events, level and loss from inverter signals alone. Soiling quantified on every site, not just the few with dedicated hardware. See Soiling: Inverter Method.
Dual loss breakdown - actual and potential. The actual view reconciles exactly against the observed production gap (the financial view); the potential "what-if" view exposes DC-side losses that primary factors like curtailment would otherwise hide (the O&M view). Answers both "where did my revenue go?" and "what should I fix first?" from one engine. See Operational vs. Potential Loss Breakdown.
Peer-to-peer DC health at MPPT / combiner-box / string level - separates underperforming from down DC inputs. Pinpoints DC faults that never trip an alarm.
Sandia-model inverter efficiency fitted per inverter for a smooth, physical conversion-loss curve. Robust efficiency KPI instead of noisy instantaneous AC/DC ratios. See Inverter Efficiency.
Weather-normalised production waterfall that bridges P50 budget to achievable production, where every bar maps to a real upstream data point - no fabricated values. Trustworthy budget-vs-actual bridge for asset-management reporting.
Events & cases workflow - raw condition flags are assembled into structured events, then clustered into trackable cases with impact bands. Turns analytics into prioritised, actionable maintenance. See the Solar Events Catalog and Solar Cases Catalog.
Runs on under-configured and sensor-sparse sites - virtual objects, cross-object inference and a transposed-GHI fallback let the pipeline produce results even before every device is configured. Fast time-to-value; graceful degradation instead of hard failure.
Domain-aware extras - snow detection & loss, bifacial rear-irradiance handling, and single-axis tracker modelling. Correct physics across climates and module technologies.

How it works - the pipeline at a glance

Performance+ executes as an ordered pipeline of steps, grouped into phases. Each phase consumes the outputs of the previous one, so data quality and modelling propagate cleanly downstream.

Phase Name What happens
0 Setup & validation Package-version logging, settings validation, point-similarity checks.
1 Input data Ingests plant SCADA, TMY, budget, satellite and tracker data; builds reference curves.
2 Environment & market Solar-position/environment modelling, market/PPA prices, budget downscaling.
3 Data quality Per-object DQ for site, weather stations, inverters, combiner boxes and meters; communication status.
4 Irradiance & DC prep Tracker modelling, clear-sky detection, DC-input power calculation (MPPT & combiner box).
5 Sensors & weather Sensor shading, sensor checks, sensor-health KPI & selection, weather imputation, snow probability.
6 Expected power Inverter power preparation, bifacial prep, physics-based expected power.
7 Consolidation Consolidated inverter and site datasets (measured + modelled permutations).
8 Inverter status & efficiency Status consolidation, Sandia inverter efficiency, soiling rate.
9 DC health DC status, capacity detection and peer-to-peer DC health (MPPT/CBX).
10 Soiling Soiling KPI, wash detection, rate estimation, analysis and loss.
11 Loss breakdown Per-inverter, site-aggregated, total and revenue loss breakdowns.
12 Weather adjustment Actual weather vs TMY deviation for GHI and ambient temperature.
13 KPIs DC / inverter / site KPIs, degradation KPI and PLR (long- and short-term).
14 Events & cases Event detection, soiling-event detection, cases workflow.
15 Waterfall Daily P50-budget -> achievable-production waterfall.

Deep-dive technical notes

Performance+ results surface directly in the Bazefield interface - as KPIs, events and cases - giving asset managers and O&M teams one consistent, auditable view of plant performance.