UpSynQ.

Half the imbalance cost lives in the handoff,
not the model.

Forecasters at mid-market power desks spend 40–50% of the shift reconciling SCADA telemetry, ISO settlement feeds, weather, and overnight positions before judgement starts. The model is usually fine. The loss originates in the manual rebuild between forecast, dispatch, and the bid stack.

SUBSTATION-04 · 138kV BESS-A · 4MW / 8MWh BESS-B · 4MW / 8MWh BESS-C · 8MW / 16MWh
FIGURE I · The grid that the desk sees only through screens Illustration: UpSynQ, 2026

When imbalance cost is high, the model is rarely the cause

At most power desks, the forecast lives in one tool, dispatch in another, the trading position in a third, and the bid stack in a fourth. A misfire in one propagates through manual rebuilds, spreadsheet copies, and Teams chats. A day later, a settlement spike or a BSUoS hit appears and gets attributed to “the forecast” — when the loss was actually downstream of it.1

The audit walks back from the cost. Below is the typical attribution we observe across desks once we trace it properly: the model contributes less than a third of avoidable imbalance loss. The rest lives in the reconciliation, the rebuild, and the handoff.

Where imbalance loss originates Walked back across 4 desks
Reconciliation lag 47%
Forecast → dispatch handoff 18%
Bid stack manual rebuild 11%
Model error (residual) 17%
Market volatility (unavoidable) 7%

MAPE is the wrong metric

For imbalance-exposed desks, asymmetric loss matters more than average error. The model refit improves MAPE by a few points; settlement exposure barely moves.

The handoff is the loss centre

Reconciliation + the forecast-to-dispatch handoff + manual bid rebuild together accounted for 76% of avoidable cost across the desks we audited.

Structural fix is upstream

UpSynQ holds the single forecast that feeds dispatch, trading, and the bid stack, with asymmetric loss functions per horizon. Your engines stay; the loop closes.

The four questions we ask every desk

60-minute call with whoever owns forecast and trading. 4-page diagnostic returned within 48 hours, including an imbalance-cost attribution walked back from your last four weeks of settlement.

Where does the trading desk actually see operational state?

Live SCADA, or handed-over schedule? In what format, with what latency, and where does it diverge from what dispatch sees?

What is the model-error vs handoff-error split?

The attribution above, but for your desk specifically. Built from your last four weeks of settlement data and operational logs.

Where does the forecast-to-bid handoff actually break?

We trace the path: forecast tool → dispatch → bid stack → settlement. Each step where data is rebuilt, reformatted, or re-interpreted by hand is named.

What is the settlement cadence, and where is manual reconciliation happening?

ERCOT 5-min, BSC half-hourly, ISP 15-min. The cadence determines how loss compounds per cycle.

A vertically integrated generator with ~2,100 MW thermal

The customer is a vertically integrated power generator running roughly 2,100 MW of thermal generation across four stations, with captive coal mining feeding the largest. Five workflows lived in five tools: demand forecasting, schedule intelligence, dispatch and procurement, fuel value-chain optimisation, and ash management. None of them talked to the others.

We built the decision OS as a single 96-block engine sitting above the existing systems. Schedule intelligence at the centre, with forecast, dispatch, fuel, and market participation feeding into it and learning from it. The same product spine now ports to merchant generators, battery IPPs, and VPP operators in Western markets.

What we found, anonymised Spine ported to ERCOT in 12 weeks
Operator
Vertically integrated gen.
Scale
~2,100 MW thermal
Granularity
96 blocks / day
Loss function
Asymmetric per horizon
Workflows integrated 5 tools 1 layer
Reconciliation cadence Once, upstream
Western market readiness ERCOT · BSC · ISP
The original deployment was a vertically integrated 2,100 MW thermal generator with captive coal. The product spine ported to a UK battery storage operator within twelve weeks; the same core engine now serves ERCOT, BSC, and ISP markets.

Tell us about your desk

One of the founders will respond within two business days with available 60-minute slots and a short note on the operational logs we would want to look at together.

FORM · The forecast audit · 60 min · 4-page diagnostic · 48 hr turnaround
The audit is not contingent on becoming a customer.