PJM Hourly Actual Load

Actual hourly electricity demand in PJM, one row per hour with a system total and one column per load area.

Load data PJM market

Query with the agent

Native record

one row per operating hour, wide by sub-area

hourly publication cadence

Evidence

Observed market data

Published observations from the named source

Time basis

Interval-start records

UTC · event_time

Overview

75,672 hours, 2017-12 to now. Columns: system_mw plus aep_mw, ap_mw, atsi_mw, dayton_mw, deok_mw, dominion_mw, duquesne_mw, ekpc_mw, mid_atlantic_mw, northern_illinois_mw. system_mw is DERIVED as the sum of the ten areas, but unlike NYISO it has been checked: against PJM's own published RTO total over 517 overlapping hours the mean difference is 0.009% and the maximum 0.938%. Wide rather than long, so "load right now" and "the 10 load area shares of it" are one row, not 11. 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.

Query contract

One row is the canonical hourly value; the refresh already collapsed the source's restatements. Read the hour you want and use its columns together.

Analysis rules

Take every value for one hour from that hour's single row. Never combine a system total from one hour with area values from another.
An area's share of demand is <area>_mw / system_mw within the same row. Do not sum the 10 area columns and system_mw together — that double-counts the whole market.

Related analysis

forecast error for a delivered hour · join on event_time, one forecast vintage at a time

Interpretation

This is PJM's PRELIMINARY hourly series and PJM restates it; the refresh always takes the latest restatement. It publishes about a day behind, so the newest row is typically 12 to 24 hours old. For PJM demand right now use pjm.inst_load.
system_mw is derived by summing the area columns, so the identity system_mw = sum(areas) proves nothing about either. Do not present it as an independent cross-check.

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.

PJM MCP API reference

HTTP endpoint

POST /api/v1/datasets/pjm_load/query

Need the full history of this dataset in Snowflake, Databricks or your own storage? Data services delivers it on a schedule.

Schema12

Column

Type

event_timeDateTime64(6, 'UTC')

system_mwNullable(Float64)

aep_mwNullable(Float64)

ap_mwNullable(Float64)

atsi_mwNullable(Float64)

dayton_mwNullable(Float64)

deok_mwNullable(Float64)

dominion_mwNullable(Float64)

duquesne_mwNullable(Float64)

ekpc_mwNullable(Float64)

mid_atlantic_mwNullable(Float64)

northern_illinois_mwNullable(Float64)

Sample data

event_time	system_mw	aep_mw	ap_mw	atsi_mw	dayton_mw	deok_mw	dominion_mw	duquesne_mw	ekpc_mw	mid_atlantic_mw	northern_illinois_mw
2026-10-11 03:00:00.000000	78193.59999999999	14394.3	4407.2	6158.7	1479.2	2234.6	14551.6	1116	1223.6	22993	9635.4
2026-10-11 02:00:00.000000	81372.3	14850.4	4613.1	6406.9	1555	2342.8	14935.6	1160.1	1267.8	24208.3	10032.3
2026-10-11 01:00:00.000000	84295.99999999999	15360.7	4790	6622.4	1626.8	2436.9	15303.9	1181.6	1300.6	25302.2	10370.9
2026-10-11 00:00:00.000000	86475	15680.4	4923.2	6809.7	1682	2513.8	15679.9	1216.3	1347.1	26028.9	10593.7
2026-10-10 23:00:00.000000	87519.6	15882.1	4990.7	6882.6	1700.1	2545	15770.5	1231.9	1325	26522.2	10669.5
2026-10-10 22:00:00.000000	86495.20000000001	15733.1	4896.4	6832.3	1678.6	2489.2	15612.7	1220.9	1253.8	26191.6	10586.6
2026-10-10 21:00:00.000000	85253.70000000001	15674.9	4813.5	6794	1684.3	2474.9	15435.5	1214.9	1190.8	25427.5	10543.4
2026-10-10 20:00:00.000000	84286.1	15721.5	4725.7	6735.2	1682.4	2482.2	15347.8	1217.6	1181.1	24730.5	10462.1
2026-10-10 19:00:00.000000	82772.1	15514.8	4696.6	6698.6	1679.4	2483.6	15247.4	1218.9	1181.9	23816.4	10234.5
2026-10-10 18:00:00.000000	81998.79999999999	15505.5	4692.4	6777.7	1695.3	2482.1	15134	1223.6	1201.2	23239.5	10047.5
2026-10-10 17:00:00.000000	81032.1	15498	4690.7	6768.1	1704.5	2498.6	15031.4	1212.5	1280.7	22547.6	9800
2026-10-10 16:00:00.000000	80453.80000000002	15473.1	4684.3	6780	1708.2	2505	15005.5	1204.3	1230.3	22349.5	9513.6
2026-10-10 15:00:00.000000	80081.7	15529.9	4699.8	6824.9	1703.4	2486.6	14904.4	1176.6	1177.3	22374.3	9204.5
2026-10-10 14:00:00.000000	79856.9	15439	4752.4	6744.7	1688.5	2445.8	14765.3	1174.1	1143.2	22755.9	8948
2026-10-10 13:00:00.000000	79431.59999999999	15156.6	4758	6601.4	1659.7	2394.1	14602.2	1163	1134.5	23053.4	8908.7
2026-10-10 12:00:00.000000	78719.5	14759.6	4692.1	6502.3	1602.2	2301.8	14336.9	1140.4	1166.2	23222.7	8995.3
2026-10-10 11:00:00.000000	76891	14450.3	4550.1	6355.3	1546.9	2209	13958.4	1109.1	1116.4	22754.2	8841.3
2026-10-10 10:00:00.000000	74278.1	14002.7	4357.3	6172	1468.4	2114	13545.1	1063.6	1042.7	21935.7	8576.6
2026-10-10 09:00:00.000000	71947.7	13711.2	4192	5931.8	1412.6	2028	13204.1	1057	1043.2	20982.3	8385.5
2026-10-10 08:00:00.000000	70938.3	13415	4098.9	5809.5	1391.2	2002.3	13049.3	1042.9	1006	20714.9	8408.3
2026-10-10 07:00:00.000000	71381.59999999999	13373.6	4075.1	5788.9	1395.2	2018.7	13095.6	1036.2	1009	21002.5	8586.8
2026-10-10 06:00:00.000000	72505.2	13550.3	4100.2	5878.1	1424.3	2071.8	13239.5	1053.2	1093.5	21283.6	8810.7
2026-10-10 05:00:00.000000	73996.29999999999	13767.2	4137.5	6013.9	1465.7	2154.5	13462.9	1047.7	1102.1	21766.4	9078.4
2026-10-10 04:00:00.000000	76293.1	14160.9	4236.4	6225.5	1533.6	2261.8	13841.6	1085.4	1037.1	22487.7	9423.1
2026-10-10 03:00:00.000000	79918.1	14804.4	4431	6408.8	1637.8	2407	14327.8	1128.7	1219.3	23633.8	9919.5

Coverage

100.0% complete0 gap days5,529 days with data

Show coverage history

Coverage: 100.0%Days with data: 5,529Gaps: 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

gaplessmore

Related load data

Related load data
Dataset	Description
7-Day Load ForecastPJM · hourly (7-day horizon)	PJM's seven-day-ahead hourly load forecast by forecast area, refreshed through the day. Rows are keyed by target time (event_time) with the issue time in evaluated_at_utc; take the latest vintage per target hour via an argMax over evaluated_at_utc. Forecast areas match the very-short-term feed (utility names, RTO_COMBINED for the system total). This is the table for tomorrow's peak and the week-ahead demand outlook. Source: PJM Market Data.
Day-ahead hourly demand bidsPJM · day publication	PJM's Day-ahead hourly demand bids. Each row preserves a publisher record, workbook row, or report document with its source member and row index. Source timestamps, units, geographic scope, and revision qualifiers are retained in record_json; event_time is collection time; completed_at is when the entire document became available.
Instantaneous LoadPJM · 5-minute	PJM metered load sampled every five minutes by area, where 'PJM RTO' is the whole-RTO system total and the remaining areas are the transmission-zone operating regions (AEP, COMED, DOM, PSEG, and so on). Because it posts within minutes, this is the live demand signal for PJM — system load, zonal load, and the shape of the daily peak — unlike the hourly metered-load tables that settle on a delay. Source: PJM Market Data.
PJM Seven-Day Load ForecastPJM · hourly (reissued through the day)	PJM's seven-day hourly demand forecast in long form: issued_at (when PJM published the forecast), event_time (the hour being forecast), area, and forecast_mw. 4.14M rows across 2,033 issue vintages and 25 areas, covering forecasts issued since 2026-05-21 and targets out to seven days ahead. Because issue time and target time are separate columns, this table can answer both 'what does PJM expect for tomorrow evening' and 'what did PJM expect for that hour twelve hours before it happened' — the second question needs the issue-time filter, and getting it wrong turns a forecast evaluation into hindsight. The area column mixes three levels of the same hierarchy: the RTO total (RTO_COMBINED), three regional aggregates (MID_ATLANTIC_REGION, SOUTHERN_REGION, WESTERN_REGION), transmission zones (AEP, COMED, DOMINION, ...) and Mid-Atlantic sub-zones (PSE&G/MIDATL, PECO/MIDATL, ...). Summing across areas double-counts, in some cases three times over.