Energy

Decision models for siting, queues and market risk, built on public data with reproducible methods.

Siting and planning questions combine market prices, load, interconnection queues and infrastructure data, each in its own format and refresh cycle. DF1 builds models that hold these together, state their assumptions and let your team run scenarios.

Directors of market analytics, development leads and planning engineers at developers, IPPs, utility planning teams, data-center siting teams and consultancies.

Five places to start

  • Siting screens

    Zones or nodes ranked by price volatility, congestion and exposure, re-ranked as load and supply assumptions move.

  • Interconnection queue analysis

    Queue positions, withdrawal rates and timing, with relief counted at a discount rather than at face value.

  • Market risk

    Price volatility modeled from load and system conditions, validated on held-out periods.

  • Load forecasting

    Forecasts that separate weather, growth and large new loads such as data centers.

  • Regulatory filing review

    Questions over tariffs, orders and filings, answered with the cited passage.

Decision Models, after a Discovery Sprint

Energy engagements start with a Discovery Sprint on one siting or market question, in the ComputePower pattern, on public data plus whatever internal data you add.

Discovery Sprint: two weeks, $4,900 fixed. Credited in full against a Build that starts within 60 days.

About Decision Models

Built for how energy works

  • Public data first

    Market, load and queue data are public in most regions; the value is in method and reproducibility.

  • Reproducible runs

    Inputs, periods and parameters stored with each run, so a result can be rebuilt and defended.

  • Stated limits

    Screening models are labeled as screens; they do not replace production cost or power flow studies.

Running examples

Decision Models

Live

ComputePower

Ranks all 21 PJM zones by grid vulnerability as data center load grows, with three methods that check each other.

Data
Public: about a gigabyte of PJM hourly market, load and interconnection-queue data.
Limits
  • Extrapolates historical relationships; it does not simulate transmission or unit commitment.
  • A screening tool for narrowing attention, not a production cost model.

Document Intelligence

Live

Blackletter

Answers questions over statutes and contracts with the source passage for every claim, and declines when the text does not support an answer.

Data
Public legal and regulatory text.
Limits
  • Answers only from the loaded documents; it does not know case law it was not given.
  • Every claim is provisional until a reviewer confirms it.

Data Platform

Live

Marketplace Data Platform

A migration verified by source-to-target parity tests, and a map of more than 35,000 seller-to-buyer trade routes.

Data
Public: a Brazilian e-commerce marketplace dataset.
Limits
  • A historical dataset; the platform shows the method, not current trade.
  • Analytics on a fixed snapshot, not a live feed.

Energy questions

Which markets?

ComputePower covers PJM. The same methods apply to other ISOs and RTOs with public hourly data; the Discovery Sprint confirms data availability.

Does it replace a production cost model?

No. It narrows attention across many options quickly, so the expensive studies run on the right few.

Can we add our own data?

Yes. Internal load, project or cost data can be joined to the public sources, and stays in your environment if required.

How often is data refreshed?

On a schedule set by how fast each source changes, with the last refresh date shown in the application.

Tell us the workflow. We show you the system.

Describe the process and the data. A reply comes within one business day, from the person who would do the work.