SPP Load Forecast

SPP's demand forecast in long form: issued_at (when SPP published it), event_time (the hour or interval being forecast), horizon, baa (SPP East or SWPW West), and forecast_mw.

Load data SPP market

Query with the agent

Native record

BAA x horizon x target interval x issue vintage

reissued per vintage; two products at different resolutions publication cadence

Evidence

Forecast data

Forward-looking values with an explicit issue time

Time basis

Interval-start records

UTC · event_time

Overview

History reaches 2017, with named East/West footprints available around the 2026 expansion; older blank BAA rows have unknown footprint. Targets run out to seven days ahead. The horizon column separates SPP's two published products: 'short_term' (STLF, five-minute targets) and 'mid_term' (MTLF, hourly targets out seven days). They are different forecasts at different resolutions and must never be mixed in one series. Issue time and target time are separate columns, so this table supports both 'what does SPP expect' and 'what did SPP expect N hours out'.

Query contract

Filter baa and horizon first — it is the product selector, not a detail. Then take one issued_at: the latest for the current expectation, or the latest earlier than event_time for forecast accuracy.

Analysis rules

Choose exactly one horizon before aggregating. short_term and mid_term are separate SPP products at different resolutions; a series that mixes them is not a forecast SPP ever published.
Never average or sum across issue vintages or balancing authorities.

Interpretation

Historical archive vintages may be reconstructed from source filenames or delivery time. Validate issue-time provenance before using old rows in a forecast-skill evaluation.
Select baa=SPP for East or baa=SWPW for West. Blank baa is unknown, not a combined-market total.

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.

SPP MCP API reference

HTTP endpoint

POST /api/v1/datasets/spp_load_forecast/query

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

Schema5

Column

Type

baaLowCardinality(String)

issued_atDateTime64(6, 'UTC')

event_timeDateTime64(6, 'UTC')

horizonLowCardinality(String)

forecast_mwNullable(Float64)

Sample data

baa	issued_at	event_time	horizon	forecast_mw
SPP	2026-10-12 07:00:00.000000	2026-10-19 07:00:00.000000	mid_term	25638
SWPW	2026-10-12 07:00:00.000000	2026-10-19 07:00:00.000000	mid_term	2282
SWPW	2026-10-12 07:00:00.000000	2026-10-19 06:00:00.000000	mid_term	2377
SPP	2026-10-12 07:00:00.000000	2026-10-19 06:00:00.000000	mid_term	26185
SWPW	2026-10-12 06:00:00.000000	2026-10-19 06:00:00.000000	mid_term	2377
SPP	2026-10-12 06:00:00.000000	2026-10-19 06:00:00.000000	mid_term	26185
SPP	2026-10-12 06:00:00.000000	2026-10-19 05:00:00.000000	mid_term	27574
SPP	2026-10-12 05:00:00.000000	2026-10-19 05:00:00.000000	mid_term	27559
SWPW	2026-10-12 05:00:00.000000	2026-10-19 05:00:00.000000	mid_term	2616
SWPW	2026-10-12 07:00:00.000000	2026-10-19 05:00:00.000000	mid_term	2638
SWPW	2026-10-12 06:00:00.000000	2026-10-19 05:00:00.000000	mid_term	2638
SPP	2026-10-12 07:00:00.000000	2026-10-19 05:00:00.000000	mid_term	27574
SWPW	2026-10-12 07:00:00.000000	2026-10-19 04:00:00.000000	mid_term	2882
SPP	2026-10-12 07:00:00.000000	2026-10-19 04:00:00.000000	mid_term	28770
SWPW	2026-10-12 06:00:00.000000	2026-10-19 04:00:00.000000	mid_term	2882
SPP	2026-10-12 06:00:00.000000	2026-10-19 04:00:00.000000	mid_term	28770
SWPW	2026-10-12 05:00:00.000000	2026-10-19 04:00:00.000000	mid_term	2881
SPP	2026-10-12 05:00:00.000000	2026-10-19 04:00:00.000000	mid_term	28754
SWPW	2026-10-12 04:00:00.000000	2026-10-19 04:00:00.000000	mid_term	2880
SPP	2026-10-12 04:00:00.000000	2026-10-19 04:00:00.000000	mid_term	28772
SPP	2026-10-12 06:00:00.000000	2026-10-19 03:00:00.000000	mid_term	29884
SWPW	2026-10-12 06:00:00.000000	2026-10-19 03:00:00.000000	mid_term	2975
SWPW	2026-10-12 05:00:00.000000	2026-10-19 03:00:00.000000	mid_term	2975
SWPW	2026-10-12 07:00:00.000000	2026-10-19 03:00:00.000000	mid_term	2975
SPP	2026-10-12 07:00:00.000000	2026-10-19 03:00:00.000000	mid_term	29884

Coverage

100.0% complete0 gap days3,580 days with data

Show coverage history

Coverage: 100.0%Days with data: 3,580Gaps: 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

gaplessmore

Related load data

Related load data
Dataset	Description
Actual System LoadSPP · 5-minute	SPP's realized system-wide demand in MW at five-minute resolution, the actual-load counterpart to the short-term and mid-term load forecasts. Note that the feed republishes the same event_time on successive polls with a fresh ingested_at, so a read should collapse repeats on ingested_at before use.
Mid-Term Load Forecast (MTLF)SPP · Hourly, out ~7 days	SPP's mid-term load forecast in MW, running roughly seven days ahead, carried alongside the realized actual for the same interval so forecast error can be computed within the table. Bitemporal: each row records the delivery interval and the vintage the forecast was published at, retaining every successive forecast for a given hour.
Short-Term Load Forecast (STLF)SPP · 5-minute, frequent vintages	SPP's short-term load forecast in MW. Bitemporal: each row carries both the delivery interval (event_time) and the vintage the forecast was issued at (publish_time), so successive forecasts for the same interval are retained rather than overwritten. That makes the table usable for forecast-error and forecast-convergence analysis, not only for the latest view.
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.