Energise the future with precise grid monitoring. Optimise with CarbonOS.

Carbonova connects SCADA, meter and ERP data to CarbonOS, a platform of AI agents that calculates emissions from generation, network losses and vehicle fleets, flags anomalies in metering and consumption, and ranks measures by cost per tonne of CO₂ avoided. For generation assets, Carbonova Build, in early access, adds prescriptive maintenance. The same dataset feeds GHG Protocol, ISSB-aligned and customer reporting.

In thermal generation, from burning gas, coal or oil; in networks, from energy losses, which the company that owns or controls the transmission or distribution system reports in Scope 2, and from SF₆ leaks in gas-insulated equipment. Each kilowatt-hour generated worldwide emitted 435 gCO₂ on average in 2025 (IEA, 2026), so the same loss weighs far more on fossil-heavy grids.

Power stations with combustion plant above 20 MW are in the EU Emissions Trading System and receive no free allocation for electricity production, except under the Article 10c derogation and for electricity from waste gases. Imported electricity has carried a CBAM obligation since 1 January 2026, with no 50-tonne annual exemption. Large companies report under the CSRD as amended by Omnibus I, and network operators count grid-loss emissions in Scope 2 under the GHG Protocol.

With no free allocation for electricity production, a generator buys an allowance for every tonne it emits, and EU ETS auction prices averaged €82.32 per tonne in the third quarter of 2026. Every tonne avoided through better heat rate, lower auxiliary load, fewer starts or lower network losses saves that cost on top of fuel. Carbonova’s planning agent ranks those measures by cost per tonne avoided.

The GHG Protocol is revising Scope 2: its consultation on hourly matching and deliverability for market-based reporting closed on 31 January 2026, a second consultation is due in 2026 and the final standard is expected in 2027. CarbonOS keeps energy data and versioned emission factors, so the inventory can be recalculated when the rules change without collecting the data again.

Signal Ingest connects SCADA, meters, IoT sensors, ERP systems such as SAP or Oracle and energy and fuel invoices, then normalises and versions generation, loss and consumption data. Proof Engine keeps each number’s lineage back to its source, with versioned emission factors and a change history, in line with the ISO 14064-3 verification standard, which makes third-party verification easier.