Current Supply, Demand & Intraday Forecast

ERCOT's public real-time supply and demand dashboard at five-minute resolution.

Load data ERCOT market

Query with the agent

Native record

series x target interval x publication vintage

5-minute publication cadence

Evidence

Mixed evidence

Multiple evidence types kept distinct in the contract

Time basis

Point-in-time records

UTC · event_time

Overview

This is the preferred dataset for a current actual-versus-forecast demand comparison: series='realized' reports observed demand_mw and committed capacity_mw; series='intraday_forecast' reports demand_mw, capacity_mw, and available_mw for the same target event_time at successive source_time vintages; and series='forward_forecast' reports forecasted_demand_mw and avail_cap_gen_mw farther ahead. Operators, traders, and researchers use it to measure current forecast error, headroom, and how forecasts converge toward realized demand.

Query contract

Filter series explicitly. For a current actual-versus-forecast comparison, resolve the latest series='realized' event_time, then select series='intraday_forecast' at that exact event_time with the greatest source_time no later than event_time. Keep target and issue time in the result.

Analysis rules

Never aggregate realized and forecast series together.
series='realized' uses demand_mw as observed gross system demand. series='intraday_forecast' uses demand_mw as forecast gross demand. Compare those values only at the same event_time and report actual minus forecast with its sign.

Related analysis

settled historical demand after the live window · aggregate both series to compatible 15-minute interval-ending buckets before comparison

Interpretation

event_time is the observation or forecast target. source_time is the forecast issue time; realized rows use a 1970 sentinel and do not represent a publication vintage.
A current intraday demand forecast miss is a gross-demand error. Generation output, renewable shortfalls, and available capacity are different quantities and do not directly cause that arithmetic error.

Access

Query from your own tools

Use the guarded HTTP endpoint directly, or connect an MCP client and load the dataset contract with describe_data before calling query_data.

ERCOT MCP API reference

HTTP endpoint

POST /api/v1/datasets/ercot_supply_demand/query

Schema13

Column

Type

event_timeDateTime64(6, 'UTC')

seriesLowCardinality(String)

source_timeDateTime64(6, 'UTC')

demand_mwNullable(Float64)

capacity_mwNullable(Float64)

available_mwNullable(Float64)

forecasted_demand_mwNullable(Float64)

avail_cap_gen_mwNullable(Float64)

hour_endingNullable(Int32)

intervalNullable(Int32)

delivery_dateNullable(String)

dst_flagNullable(Bool)

ingested_atDateTime64(6, 'UTC')

Sample data

event_time	series	source_time	demand_mw	capacity_mw	available_mw	forecasted_demand_mw	avail_cap_gen_mw	hour_ending	interval	delivery_date	dst_flag	ingested_at
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:25:00.000000	∅	∅	∅	62426	95183	24	∅	2026-09-30	false	2026-09-25 02:28:20.206532
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:20:00.000000	∅	∅	∅	62426	95183	24	∅	2026-09-30	false	2026-09-25 02:23:20.568379
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:15:00.000000	∅	∅	∅	62426	95183	24	∅	2026-09-30	false	2026-09-25 02:18:20.642883
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:10:00.000000	∅	∅	∅	62426	95183	24	∅	2026-09-30	false	2026-09-25 02:13:20.065358
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:05:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 02:08:19.742022
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 02:00:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 02:03:20.868951
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:55:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 01:58:20.341411
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:50:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 01:53:20.266820
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:45:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 01:48:20.423750
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:40:00.000000	∅	∅	∅	62362	95183	24	∅	2026-09-30	false	2026-09-25 01:43:20.236635
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:35:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:38:21.351146
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:30:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:33:22.013898
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:25:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:28:20.276549
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:20:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:23:20.003947
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:15:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:18:21.277674
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:10:00.000000	∅	∅	∅	62362	95273	24	∅	2026-09-30	false	2026-09-25 01:13:20.218429
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:05:00.000000	∅	∅	∅	62350	95273	24	∅	2026-09-30	false	2026-09-25 01:08:20.182725
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 01:00:00.000000	∅	∅	∅	62350	95273	24	∅	2026-09-30	false	2026-09-25 01:03:20.288266
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:55:00.000000	∅	∅	∅	62350	95273	24	∅	2026-09-30	false	2026-09-25 00:58:21.724657
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:50:00.000000	∅	∅	∅	62350	95273	24	∅	2026-09-30	false	2026-09-25 00:53:19.703529
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:45:00.000000	∅	∅	∅	62350	95414	24	∅	2026-09-30	false	2026-09-25 00:48:20.942771
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:40:00.000000	∅	∅	∅	62350	95414	24	∅	2026-09-30	false	2026-09-25 00:43:19.779226
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:35:00.000000	∅	∅	∅	62350	94654	24	∅	2026-09-30	false	2026-09-25 00:38:21.000842
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:30:00.000000	∅	∅	∅	62350	94654	24	∅	2026-09-30	false	2026-09-25 00:33:19.788623
2026-10-01 05:00:00.000000	forward_forecast	2026-09-25 00:25:00.000000	∅	∅	∅	62350	94674	24	∅	2026-09-30	false	2026-09-25 00:28:20.530799

Coverage

100.0% complete0 gap days133 days with data

Show coverage history

Coverage: 100.0%Days with data: 133Gaps: 0

2026

gaplessmore

Related load data

Related load data
Dataset	Description
ERCOT Hourly Actual LoadERCOT · hourly	Actual hourly electricity demand in ERCOT, one row per hour with a system total and one column per weather zone. 119,475 hours, 2013-01 to now. Columns: system_mw plus coast_mw, east_mw, far_west_mw, north_mw, north_central_mw, south_central_mw, southern_mw, west_mw. system_mw is ERCOT's own published total, and the eight zones sum to it to within 0.03 MW — so a zone share is simply zone_mw / system_mw. Wide rather than long, so "load right now" and "the 8 weather zone shares of it" are one row, not 9. Every market's load table in this catalog shares the system_mw column and the same hourly grain, so a cross-market demand comparison needs no reshaping.
Hourly Historical System LoadERCOT · hourly	Hourly weather-zone actual-load history for ERCOT, including the eight weather zones and a system total. Use it for zonal and historical hourly analysis; for current system-wide demand and intraday forecast error, prefer Current Supply, Demand & Intraday Forecast (ercot_supply_demand). Analysts use this archive to study load shape and peaks, normalize demand against temperature, and contextualize price moves and reserve conditions. It comes from ERCOT report NP6-345-CD.
Load Forecast (MTLF)ERCOT · hourly (7-day forecast)	ERCOT's mid-term load forecast (MTLF) for the Texas grid, giving the expected electricity demand for each of the next seven days at hourly resolution. The forecast is broken out by ERCOT's eight weather zones plus a system-wide total, and a new vintage is issued every hour, so you can also see how the outlook for a given day shifts as it approaches. Operators use this to plan generation and reserves, while traders and researchers use it to anticipate price and tightness conditions and to study how forecasts evolve and where they miss. The official source is ERCOT report NP3-565-CD, Seven-Day Load Forecast by Weather Zone.
SCED Load Resource Data (60-Day)ERCOT · 5-minute (SCED), 60-day disclosure	Per-resource, per-interval telemetry for ERCOT's controllable Load Resources — large loads that curtail or provide ancillary services — from the 60-Day SCED Disclosure Reports. Each row is one SCED run (roughly every five minutes) for one load resource and its QSE, showing its real power consumption alongside its maximum and low consumption, its high and low dispatch limits (HDL, LDL), its SCED dispatch target (base point) and telemetered status, and its ancillary services. What ERCOT discloses about ancillary services changed with Real-Time Co-optimization plus Batteries (RTC+B) on 5 December 2025. Before it, each row carries the load's ancillary limits (HASL, LASL) and how much of each service it was responsible for (Reg-Up, Reg-Down, RRS, RRS-FFR, Non-Spin, ECRS). From it, those columns are empty and each row instead carries the load's ramp rates, its per-service ancillary capability, the ancillary services SCED awarded it in that interval (RRS by under-frequency relay, ECRS, Non-Spin and, rarely, RRS-PFR), and how much RRS and ECRS its QSE self-provided on it. Because Load Resources are how demand-side capacity participates in ERCOT's real-time market and reserves, this dataset shows demand response actually happening at five-minute resolution — how much load was armed for responsive reserve, when it was deployed, and how it followed dispatch. Like the gen file it is published on a 60-day regulatory delay, making it a historical record for studying demand-side flexibility, reserve provision, and load participation in scarcity events. The official source is ERCOT report NP3-965-ER, 60-Day SCED Disclosure Reports.