Skip to content

Surge grid

Day-ahead load forecasts for every EIA-930 demand balancing authority — ranked by utilisation, filterable by interconnection and size. Click a card to open its map-and-chart detail.

Showing 41 of 53 balancing authorities
DOPD

Douglas County PUD

Western

Peak · next 24h

0.3GW

143% of peak

all-time 200 MW

GCPD

Grant County PUD

Western

Peak · next 24h

0.8GW

142% of peak

all-time 550 MW

HST

Homestead

Eastern

Peak · next 24h

0.1GW

113% of peak

all-time 100 MW

WACM

WAPA Rocky Mountain

Western

Peak · next 24h

3.3GW

95% of peak

all-time 4 GW

BANC

BA of N. California

Western

Peak · next 24h

3.1GW

94% of peak

all-time 3 GW

PNM

PNM (New Mexico)

Western

Peak · next 24h

2.0GW

93% of peak

all-time 2 GW

TEC

Tampa Electric

Eastern

Peak · next 24h

4.0GW

87% of peak

all-time 5 GW

FPC

Duke Energy Florida

Eastern

Peak · next 24h

10GW

86% of peak

all-time 12 GW

SC

Santee Cooper

Eastern

Peak · next 24h

4.2GW

84% of peak

all-time 5 GW

NEVP

Nevada Power

Western

Peak · next 24h

6.2GW

83% of peak

all-time 8 GW

AVA

Avista

Western

Peak · next 24h

1.4GW

79% of peak

all-time 2 GW

GVL

Gainesville Utilities

Eastern

Peak · next 24h

0.3GW

78% of peak

all-time 450 MW

BPAT

Bonneville Power

Western

Peak · next 24h

9.0GW

75% of peak

all-time 12 GW

PGE

Portland General Electric

Western

Peak · next 24h

3.0GW

74% of peak

all-time 4 GW

ERCORTO

ERCOT

Texas

Peak · next 24h

63GW

74% of peak

all-time 86 GW

CPLE

Duke Energy Progress East

Eastern

Peak · next 24h

9.9GW

71% of peak

all-time 14 GW

TAL

Tallahassee

Eastern

Peak · next 24h

0.5GW

71% of peak

all-time 650 MW

JEA

JEA (Jacksonville)

Eastern

Peak · next 24h

2.3GW

71% of peak

all-time 3 GW

TEPC

Tucson Electric Power

Western

Peak · next 24h

2.1GW

70% of peak

all-time 3 GW

DUK

Duke Energy Carolinas

Eastern

Peak · next 24h

16GW

70% of peak

all-time 23 GW

SCEG

Dominion Energy SC

Eastern

Peak · next 24h

3.8GW

69% of peak

all-time 6 GW

TIDC

Turlock Irrigation District

Western

Peak · next 24h

0.4GW

69% of peak

all-time 620 MW

NWMT

NorthWestern Energy (MT)

Western

Peak · next 24h

1.3GW

69% of peak

all-time 2 GW

AZPS

Arizona Public Service

Western

Peak · next 24h

5.8GW

68% of peak

all-time 9 GW

EPE

El Paso Electric

Western

Peak · next 24h

1.5GW

66% of peak

all-time 2 GW

TVA

Tennessee Valley Authority

Eastern

Peak · next 24h

22GW

64% of peak

all-time 34 GW

SWPPRTO

Southwest Power Pool

Eastern

Peak · next 24h

33GW

60% of peak

all-time 56 GW

SCL

Seattle City Light

Western

Peak · next 24h

1.1GW

60% of peak

all-time 2 GW

SRP

Salt River Project

Western

Peak · next 24h

4.7GW

59% of peak

all-time 8 GW

TPWR

Tacoma Power

Western

Peak · next 24h

0.5GW

58% of peak

all-time 850 MW

CHPD

Chelan County PUD

Western

Peak · next 24h

0.2GW

56% of peak

all-time 350 MW

PSCO

Xcel Colorado

Western

Peak · next 24h

4.4GW

55% of peak

all-time 8 GW

PJMRTO

PJM Interconnection

Eastern

Peak · next 24h

88GW

53% of peak

all-time 166 GW

LGEE

LG&E / Kentucky Utilities

Eastern

Peak · next 24h

4.0GW

50% of peak

all-time 8 GW

WALC

WAPA Desert SW

Western

Peak · next 24h

1.0GW

39% of peak

all-time 3 GW

IID

Imperial Irrigation District

Western

Peak · next 24h

0.4GW

35% of peak

all-time 1 GW

LDWP

LA Dept of Water & Power

Western

Peak · next 24h

1.7GW

26% of peak

all-time 7 GW

CPLW

Duke Energy Progress West

Eastern

Peak · next 24h

0.6GW

25% of peak

all-time 2 GW

SEC

Seminole Electric Coop

Eastern

Peak · next 24h

0.4GW

15% of peak

all-time 3 GW

WAUW

WAPA Upper Great Plains West

Western

Peak · next 24h

0.1GW

13% of peak

all-time 700 MW

SPA

Southwestern Power Admin

Eastern

Peak · next 24h

0.0GW

1% of peak

all-time 2 GW

What does this all mean?

Balancing authority (BA)

A company or agency that keeps a region's grid in balance — matching electricity generation to demand in real time. PJM runs the DC-to-Chicago corridor; CAISO runs California; ERCOT runs most of Texas. 53 BAs publish a live demand feed to the US Energy Information Administration (EIA-930) — surge forecasts all of them.

Interconnection

The three giant synchronised AC grids of North America — Eastern, Western, and Texas. They barely talk to each other (only a handful of DC ties). A blackout in one can't easily spread to the others.

Day-ahead forecast

How much electricity the model thinks will be consumed over the next 24 hours, made the day before. Grid operators use day-ahead forecasts to decide which power plants to start up, how much fuel to buy, and how to price wholesale electricity.

MW and GW (megawatts, gigawatts)

Units of instantaneous power demand. 1 GW = 1 000 MW ≈ 1 large nuclear reactor at full output, or roughly enough to power 750 000 typical US homes on a hot afternoon. PJM peaks at ~165 GW; a small utility like Homestead, FL peaks at ~100 MW.

Median · p10–p90 (the shaded band)

Surge returns a probability range, not a single number. The median is the middle guess. The p10–p90 band covers the middle 80% of likely outcomes — roughly: there's a 10% chance actual demand comes in below the band, 10% above it. A narrow band means the model is confident; a wide band means weather or weekday uncertainty matters.

% of all-time peak

How close tomorrow's forecasted maximum is to that BA's historical record. 100% = likely to tie or break the peak — that's when grid stress is real. <60% is a comfortable shoulder day.

RTO / ISO

Seven US regions run competitive wholesale electricity markets (PJM, CAISO, ERCOT, MISO, NYISO, ISO-NE, SPP). Generation and retail are separate companies bidding through an auction. Non-RTO BAs are vertically integrated — one utility owns everything from the power plant to your meter.

MASE (model accuracy score)

How well the model does compared to a naive "same as last week" baseline. Lower is better. 1.0 = no better than naive; 0.5 = half the error of naive; 0.0 = perfect. surge-fm-v3 scores 0.52 on the 7 biggest grids — about 10× better than a typical weather-adjusted regression.