Constraint Shift Factor Runs

One row per COMPLETED nightly estimation of PJM constraint shift factors, and the only record that a run finished.

Congestion & Constraints data PJM market

One row per: one completed estimation run; Nightly (one row per completed run) cadence
Evidence: Reference data; Stable context used to interpret other datasets
Time basis: Point-in-time records; UTC · computed_at

Overview

Resolve the latest usable run here — computed_at = (SELECT max(computed_at) FROM atg.pjm_constraint_sensitivity_runs) — and never off max(computed_at) of the sensitivities themselves, because a run writes its rows in blocks that all carry the new timestamp and an unfinished or abandoned run would otherwise look like the newest one. Each row also carries how much evidence that run had: interval_coverage is the fraction of published dispatch intervals that survived admission, intervals_refused_unexplained counts intervals showing congestion with no constraint recorded as binding (an unobserved binding set), constraint_feed_lag_minutes is how far the constraint feed trailed the price feed, and constraints_seen / constraints_in_fit / constraints_reported show how many constraints bound, how many were good enough to control for, and how many earned a published estimate.

Query contract: The newest row is the newest COMPLETE run: computed_at = (SELECT max(computed_at) FROM atg.pjm_constraint_sensitivity_runs). Use that value to filter atg.pjm_constraint_sensitivities.
Analysis rules: One row per run. Counting rows counts runs, not constraints, nodes or intervals — those are columns on each row.
Interpretation: A run appears here only after every one of its node blocks has landed. That is the point of the table: rows go into the sensitivities table block by block, all carrying the new computed_at, so a run still being written — or one that died halfway — would otherwise look like the newest. Absence of a row means the run did not finish, not that it did not happen.This is provenance about an estimation job. Nothing in it measures the grid: it says how much evidence a run had, not what congestion occurred.

Access

Download: Query it in SQL, download it, or read it with an API key. Download data
MCP: Connect an MCP client and load the contract with describe_data before calling query_data.PJM MCP API reference
HTTP endpoint: POST /api/v1/datasets/pjm_constraint_sensitivity_runs/query
Full history: Delivered to Snowflake, Databricks or your own storage on a schedule by Data services.
More coverage

Schema

18 columns

Column	Type
`computed_at`	`DateTime64(3, 'UTC')`
`run_id`	`String`
`iso`	`LowCardinality(String)`
`window_start`	`DateTime64(3, 'UTC')`
`window_end`	`DateTime64(3, 'UTC')`
`rows_written`	`UInt64`
`rows_estimated`	`UInt64`
`constraints_seen`	`UInt32`
`constraints_in_fit`	`UInt32`
`constraints_reported`	`UInt32`
`nodes`	`UInt32`
`n_intervals`	`UInt32`
`intervals_published`	`UInt32`
`intervals_refused_thin`	`UInt32`
`intervals_refused_unexplained`	`UInt32`
`interval_coverage`	`Float32`
`constraint_feed_lag_minutes`	`Float32`
`method_version`	`LowCardinality(String)`

Sample data

computed_at	run_id	iso	window_start	window_end	rows_written	rows_estimated	constraints_seen	constraints_in_fit	constraints_reported	nodes	n_intervals	intervals_published	intervals_refused_unexplained	interval_coverage	constraint_feed_lag_minutes	method_version
2026-11-01 10:11:03.962	d8b17fb2-6829-4fc6-adeb-72b4d275a386	PJM	2026-09-02 10:11:03.000	2026-11-01 10:11:03.000	7251048	2301920	504	373	160	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-31 10:10:59.529	2c8ed6e8-aefb-4ccf-a012-b58b98b5ad20	PJM	2026-09-01 10:10:59.000	2026-10-31 10:10:59.000	7308596	2359468	508	376	164	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-30 10:10:58.835	efc1768f-4bd6-4f5a-9684-38f4b3506118	PJM	2026-08-31 10:10:58.000	2026-10-30 10:10:58.000	7308596	2359468	508	378	164	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-29 10:34:18.289	40078562-ecb8-4a47-8c71-7fe8fea21ec0	PJM	2026-08-30 10:34:18.000	2026-10-29 10:34:18.000	7265435	2359468	505	377	164	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-28 10:10:58.880	9972604b-4dad-4a29-ab02-f26d87c18d4d	PJM	2026-08-29 10:10:58.000	2026-10-28 10:10:58.000	7121565	2301920	495	368	160	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-27 10:56:28.736	5bda9f01-cbf2-44e8-8c96-f6feb6801f4c	PJM	2026-08-28 10:56:28.000	2026-10-27 10:56:28.000	7020856	2301920	488	363	160	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-26 10:10:58.837	4acf9074-7903-40c6-a95b-43eff64f99b1	PJM	2026-08-27 10:10:58.000	2026-10-26 10:10:58.000	7064017	2301920	491	363	160	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-25 10:11:03.728	f424c584-9bb5-40b5-91b1-82a7aa384cf3	PJM	2026-08-26 10:11:03.000	2026-10-25 10:11:03.000	7064017	2229985	491	361	155	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-24 10:11:03.070	c1fb76c7-0c01-4098-a453-0c46f2069b07	PJM	2026-08-25 10:11:03.000	2026-10-24 10:11:03.000	6977695	2215598	485	357	154	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-23 10:10:58.514	493ec5d9-4c51-4613-a011-8b6519f9f914	PJM	2026-08-24 10:10:58.000	2026-10-23 10:10:58.000	6876986	2201211	478	352	153	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-22 10:11:00.276	783a4482-cbda-4948-b7f3-796c6bdecf58	PJM	2026-08-23 10:11:00.000	2026-10-22 10:11:00.000	6848212	2201211	476	352	153	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-21 10:10:58.450	8198851f-f5d6-4453-9a02-d958fb8f5cff	PJM	2026-08-22 10:10:58.000	2026-10-21 10:10:58.000	6833825	2172437	475	350	151	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-20 10:10:58.653	742c6087-3981-4c85-9b5b-10402ab215a5	PJM	2026-08-21 10:10:58.000	2026-10-20 10:10:58.000	6761890	2172437	470	348	151	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-19 10:11:00.456	2722add6-6694-46de-bed7-ec6d79821809	PJM	2026-08-20 10:11:00.000	2026-10-19 10:11:00.000	6790664	2158050	472	348	150	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-18 10:10:59.639	aeaf21b6-c9f6-4d96-8ad4-0461706759ec	PJM	2026-08-19 10:10:59.000	2026-10-18 10:10:59.000	6805051	2229985	473	351	155	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-17 10:10:59.918	341f3065-58dc-4fc6-b564-2cc828c67c04	PJM	2026-08-18 10:10:59.000	2026-10-17 10:10:59.000	6934534	2258759	482	355	157	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-16 10:10:58.424	1c23fcca-7692-4b9a-80f0-029dcda17828	PJM	2026-08-17 10:10:58.000	2026-10-16 10:10:58.000	6862599	2244372	477	353	156	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-15 10:10:59.713	0bd3d91f-7e1d-48b3-908d-a129397cdb58	PJM	2026-08-16 10:10:59.000	2026-10-15 10:10:59.000	6819438	2244372	474	349	156	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-14 10:10:59.778	60bba889-62c2-4b84-8d1e-1edf72118de2	PJM	2026-08-15 10:10:59.000	2026-10-14 10:10:59.000	6733116	2186824	468	343	152	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-13 10:10:58.310	7af42d0f-948d-4fa6-85e9-aa60e30cca8e	PJM	2026-08-14 10:10:58.000	2026-10-13 10:10:58.000	6646794	2158050	462	336	150	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-12 10:11:01.603	5b3b90fe-7f79-460c-a3b3-4321f8c37e4c	PJM	2026-08-13 10:11:01.000	2026-10-12 10:11:01.000	6546085	2129276	455	331	148	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-11 10:10:58.437	a41a5d8c-19d8-4069-9258-6eba20ab4165	PJM	2026-08-12 10:10:58.000	2026-10-11 10:10:58.000	6531698	2129276	454	332	148	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-10 10:10:59.197	bff8d2f4-2cbe-457f-81cf-a417ba13a24e	PJM	2026-08-11 10:10:59.000	2026-10-10 10:10:59.000	6574859	2143663	457	335	149	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-09 10:11:00.179	034ec30c-c079-467d-bc5b-35ea14b885a9	PJM	2026-08-10 10:11:00.000	2026-10-09 10:11:00.000	6502924	2158050	452	333	150	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2
2026-10-08 10:10:58.500	17ac76a2-8522-4b89-b0bd-d930811f9502	PJM	2026-08-09 10:10:58.000	2026-10-08 10:10:58.000	6430989	2129276	447	330	148	14387	1439	1440	1	0.99930555	1440	ols-blockboot-v2

Coverage

Complete: 100.0%
Gap days: 0
Days with data: 45

Show coverage history

Coverage: 100.0%Days with data: 45Gaps: 0

2026

gaplessmore

Related data

Related congestion & constraints data
Dataset	Description
Constraint Shift Factors (Estimated)PJM · nightly (60-day rolling estimation window)	Estimated sensitivity of every PJM pricing location's price to every binding transmission constraint: one row per constraint, contingency, and location, recomputed nightly over a rolling 60-day window. This is what answers 'which nodes drive this constraint' and 'which constraints is this node exposed to'. THE DAY-AHEAD MARKET, not real time: this estimate is fitted to day-ahead marginal values against day-ahead nodal congestion and it describes day-ahead congestion. It covers PJM's day-ahead binding constraints with their contingency over roughly 14,450 pricing nodes. PJM names no terminals, so from_station and to_station are always empty. PJM's real-time shadow prices ARE ingested now (pjm_rt_marginal_value, pjm_transmission_limits) and a real-time estimate is fitted separately; it is not this dataset and is not available here, so do not answer a real-time PJM question from this one. shift_factor is in the ISO's orientation — POSITIVE means an incremental MW injected at that node increases loading on the constraint and the node is paid below system lambda while it binds; NEGATIVE means generation there relieves the constraint and earns a premium. These are ESTIMATES recovered from the price identity LMP = energy - sum(shift_factor x shadow_price), not a published PTDF matrix. They are measured RELATIVE TO THE MARKET'S REFERENCE — the identity yields SF(node) - SF(reference), so a single absolute value should be quoted as 'relative to the system reference' rather than as the node's PTDF, while DIFFERENCES between nodes are exact because the reference term cancels. Three further differences from a published matrix: they describe a NODE (a generator at that node inherits its location's value, and two units at one node are indistinguishable), they reflect the topology actually in effect across the window including outages rather than a stated base case, and every one carries a std_error from a 200-draw block bootstrap that resamples whole days. Read std_error before quoting shift_factor: an estimate whose absolute value is not at least twice its standard error is not distinguishable from zero. estimation_status says why a row has no number — 'thin_support' (in the fit, so it is controlled for, but under 12 binding intervals or under 3 distinct binding days), 'no_support' (under 3 binding intervals; not a regressor), or 'collinear' (it bound in lockstep with another constraint, so the two cannot be separated). Where from_station and to_station are populated they identify the monitored element and are NOT the constrained direction — the sign of shift_factor is what says which way. Every read must pin computed_at to one run, and must resolve that run through the companion atg.<iso>_constraint_sensitivity_runs ledger rather than off max(computed_at) here — rows are written in blocks that all carry the new timestamp, so an unfinished or abandoned run would otherwise look like the newest. Mixing runs averages a node across different network topologies.
Day-Ahead Constraint Marginal ValuesPJM · hourly (day-ahead)	What each binding day-ahead transmission constraint cost in PJM, hour by hour: the monitored facility, the contingency facility, and the constraint's marginal value — its shadow price, the saving from one more MW of headroom. This is the table that says how hard a constraint bound, where pjm_da_transconstraints says only that it did. PJM PUBLISHES THIS VALUE AS A NEGATIVE NUMBER: 2,654,985 negative rows against 43 positive over the table's full history, which reaches back to 2010. Read its magnitude as the cost of the constraint and do not compare its sign against another market's. This answers day-ahead congestion only; for real-time, see pjm_transmission_limits and pjm_rt_marginal_value. Source: PJM Market Data.
Day-Ahead Transmission ConstraintsPJM · daily (day-ahead)	The transmission constraints that bound in PJM's day-ahead market: the monitored facility, the contingency facility, the duration, and the congestion event. It names which elements are expected to limit flows for the next operating day. What it does not carry is what the constraint COST: the marginal value is published separately, in pjm_da_marginal_value. For real-time binding constraints, see pjm_transmission_limits (the live tip, ~9 minutes behind) and pjm_rt_marginal_value (the settled record, ~20 hours behind). Source: PJM Market Data.
PJM Day-Ahead Binding ConstraintsPJM · hourly	Which transmission facilities bound in PJM's day-ahead market and what each one cost, one row per interval and constraint. 2.65M rows, 2010-01 to the next delivery day. Columns: event_time, constraint_name, shadow_price_usd_mwh, plus contingency. The shadow price is the marginal cost of the binding limit — what the market would have saved from one more megawatt of capability on that element. This is the table that answers WHY congestion appeared; a price spread between two locations shows that they separated but not which facility separated them.