Outage Reschedule Model
RESCHEDPredicts which planned outages will actually move — and when.
Planned outages are frequently rescheduled; this model predicts which scheduled maintenance events are likely to shift, and in which direction, from grid-stress and market heuristics.
How it works
A classifier-plus-regressor pair trained on the history of scheduled-versus-actual outage timing: one head estimates whether a given planned event moves at all, the other estimates the expected shift once it does. Both are conditioned on grid stress — including Event Model signals — along with market conditions and seasonal / heuristic factors, so a maintenance calendar becomes a distribution over likely timing instead of a fixed list treated as certain.
Inputs
- Planned outage schedules
- Historical schedule revisions — scheduled vs. actual timing
- Grid-stress and Event Model signals
- Market conditions
Outputs
- Per-event reschedule probability
- Expected direction and magnitude of the timing shift
Three ways to consume it
product · inference · MCPIn the product
The Outage Reschedule Model powers Ask the Grid directly — the live map, the radar, and the grid agent read it in place, so the same model you'd call is the one already reasoning over the grid on screen.
Developer inference service
A direct, typed inference API: request forecasts or embeddings by node and horizon and get structured results back. This is a plain inference endpoint — not MCP — for pipelines, notebooks, and services that want the model output without an agent in the loop.
See the developer surfaceMCP
The same model outputs, exposed as tools your own agent can call. Point a compatible client at the Ask the Grid MCP server and the model becomes a tool in your agent's own loop.
Build with MCPIntended use
- Anyone trading around a maintenance calendar
- Planners stress-testing an outage schedule against likely slippage
Limitations
- Depends on the Event Model and grid-stress signals maturing first
- Heuristic-driven and probabilistic; predicts likelihood, not certainty
- The latest of the preview models to land