VERTICAL · ENERGY & STORAGE
2,461 mappings·1,027-field schema·ISA-95 categorized·deterministic
A renewables portfolio is a mixed fleet by construction: the inverters, the meters and the batteries were bought in different years from different vendors.
A single site commonly runs one vendor's inverters, another's meters and a third's storage. Each speaks a dialect: SunSpec-conformant registers on one, a proprietary REST payload on the next, Modbus holding registers with an offset table on the third.
Energy makes unit errors uniquely expensive because the quantities span orders of magnitude. Watts against kilowatts against megawatt-hours is a factor of a million from end to end, and an unconverted value looks entirely plausible on a dashboard. The AC/DC distinction is the other trap: on a storage device the battery current is genuinely DC while the line current beside it is AC, and a model that conflates them reports confident nonsense.
The energy vertical resolves at 100% coverage on SunSpec payloads, with every scale factor and unit conversion reported.
| Raw vendor tag | Canonical field | ISA-95 category | |
|---|---|---|---|
| AC_Power | → | inverter_output_kw | energy_consumption |
| DCA | → | dc_current_a | electrical_measurement |
| ACCurrent | → | line_current_a | electrical_measurement |
| AC_Energy_WH | → | energy_delivered_kwh | energy_consumption |
| AC_Frequency | → | grid_frequency_hz | electrical_measurement |
Every row above is produced by the shipping engine, not written by hand. This page fails to build if any of them stops resolving to the field shown.
Resolution is a lookup, not an inference. A tag is matched against a curated corpus of 2,461 confirmed vendor mappings; only if that misses does it fall to weaker layers: a normalized fold that strips unit suffixes and separators, then a signal classifier that reads structure and unit evidence. Each layer carries a lower confidence, and the layer that answered is named in the response. A mapping you disagree with is visible rather than buried.
Below a confidence threshold the engine abstains. An evidence gate refuses a match it cannot justify and reports the tag unresolved, by name, with the score and the reasons, because a wrong field at high confidence is far more expensive than an honest miss. Six read-time validators then check what survives: sentinel detection, physics bounds, stuck sensors, dropout, operating mode and correlation.
Units are converted to SI where the source unit is known, and every conversion is reported with its factor. A value that fails a physics bound is nulled with the bound it violated attached, not silently dropped.
It does not invent fields. A tag outside the corpus that the signal layer cannot justify comes back unresolved and counted, and those names feed the roadmap for the next pack rather than a plausible guess in your data. It is a translation layer, not a historian: it holds no time series and replaces no SCADA system. And the container is a sandbox: it ships the deterministic layers and the canonical schema, not the production embedding, research and corpus-learning layers.
No key, no account, no sales call. The sandbox runs locally and answers with the same canonical schema production does.
Send a Model 103 block with its scale factors, or a storage payload, and check the arithmetic. Conversions are shown with their exponents, not asserted.
Inverter, meter and battery in one payload. See platform licensing for embedding the canonical data model in your own product, or pricing for usage-based API access.