LEARNS YOUR GRID'S PERSONALITY, AND THE MODES IT MOVES BETWEEN

No two nodes behave alike, and each shifts between distinct moods — calm, volatile, congested. SPECTER learns those regimes and how your grid moves between them, so the other engines get the right context. Full-covariance regime clustering with hidden-Markov dynamics.

Regime learning Front-of-Meter

What it does

NOT EVERY HOUR IS THE SAME

Treating every hour as an average hour throws away the structure. SPECTER learns the handful of regimes your grid actually lives in.

Distinct behaviour regimes

It groups your grid's behaviour into a few real regimes rather than treating every hour the same. Full-covariance regime clustering.

Knows how regimes switch

Regimes don't change at random; there's a pattern to the transitions. SPECTER learns it. Hidden-Markov regime dynamics.

Carries what it learns across sites

What it learns at one node bootstraps a new site that behaves like it. Regime embeddings transferable across sites.

Sets the context for the plane

The current regime tells FENRIR how hard to hedge and TARSIS which pattern to expect. Feeds regime context to FENRIR and TARSIS.

How it fits the plane

FENRIR — regime context TARSIS — regime context HELIOS — regime-aware forecast

Available in

Pilot (Free)OperatorFleetEnterprise

Validation

Every claim on this page is proven on your own data first — a 12-month walk-forward before you act on anything live.

The method

BEST-IN-CLASS, NAMED PLAINLY.

These are the real methods behind SPECTER, each in one plain line. We name the method as a credibility signal — we don't publish the recipe.

Full-covariance regime clustering

Learns your grid's distinct behaviour regimes, not just an average.

Hidden-Markov dynamics

Learns how the grid moves between those regimes.

LEARNS YOUR GRID'S PERSONALITY, AND THE MODES IT MOVES BETWEEN

NOT EVERY HOUR IS THE SAME

BEST-IN-CLASS, NAMED PLAINLY.

DEPLOY SPECTER.FREE FOR 90 DAYS.

DEPLOY SPECTER.
FREE FOR 90 DAYS.