Energy QC clean AI-training-safe

US Electricity Grid Balance by Region

The full hourly grid-balance picture for every US region, 2021-present, cleaned from the EIA API: electricity demand, the EIA day-ahead demand forecast, net generation, and total interchange (signed net flow between regions). Pair demand vs forecast for forecast error, demand vs net generation for the local supply gap, and interchange for import/export balance - the complete demand+supply side of every US power model in one table.

2.5M
rows
13
zones
2021-2026
coverage
22.3 MB
download
Source
U.S. EIA
Licence
Redistributable open data
Updates
Intraday
Data through
2026-08-02
Quality
QC clean · 0 failures
Format
Apache Parquet + dictionary

Safe to train on

Built only from a named, redistributable official source under a documented open licence - not scraped web data. No copyright grey zone, no personal data. Ships machine-readable Croissant metadata (ML Commons - loads in Hugging Face / Kaggle / Google), an AI training-licence manifest documenting source, licence and provenance for your model's data governance, and a machine-readable data dictionary (drop it into an agent / RAG prompt so the model knows every column) - all inspectable before you buy.

What's included

  • Hourly demand + day-ahead forecast + net generation + total interchange × 13 US regions, 2021-present
  • series = Demand / Day-ahead forecast / Net generation / Total interchange (interchange is signed: - = net importer)
  • Demand vs forecast → error; demand vs net generation → supply gap; interchange → import/export balance
  • Source: U.S. Energy Information Administration (public domain)

Schema

ColumnTypeDescriptionFilledDistinct
zone str EIA region 100.0% 13
ts timestamp (UTC) Hour 100.0% 48,944
series str Demand / Day-ahead forecast / Net generation / Total interchange 100.0% 4
mwh float MWh (interchange is signed) 100.0% 138,369
unit str Unit 100.0% 1
res_min int Native resolution (hourly) 100.0% 1

Sample & preview

Every purchase ships as Apache Parquet with a data dictionary and the full QC report. A free sample (first rows + schema) is downloadable here - confirm fit before you buy. Source: U.S. EIA (redistributable open data; attribution passes through - see our Licence).

Don't trust screenshots - drop the sample into your notebook right now.

import pandas as pd
df = pd.read_parquet("us-electricity-demand_sample.parquet")
df.info()   # typed columns, gap-aware, ready to join
⬇ Download free Parquet sample or CSV for Excel
Coverage: 13 zones

CAL · CAR · CENT · FLA · MIDA · MIDW · NE · NW · NY · SE · SW · TEN · TEX