Live market data
ISO-NE solar forecast
ISO-NE's published solar forecast against actual output over the next day — the visible tip of a fleet that mostly hides behind the meter.
Fetching the latest published forecast…
01
ISO-NE's published solar forecast against actual output over the next day — the visible tip of a fleet that mostly hides behind the meter.
How much solar power will New England get?
ISO-NE solar output peaks at 992 MW on Sun, 2 PM, against a low of 0 MW — a swing of 992 MW across the window. Solar forecast is the heaviest area at 992 MW.
Every line above, and who produced it.
What settled — the realized values every forecast here is scored against.
The grid operator's own published forecast for these hours. Source: ISO New England.
Each day of the window on its own.
Every hour of the window, shaded by load.
| 0 | 6 | 12 | 18 | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fri, 8/28 |
| Series | Peak (MW) | Peak hour | Low (MW) | Average (MW) |
|---|---|---|---|---|
| Solar forecast | 992 | Sun, 2 PM | 0 | 198 |
| Solar settled (recent) | 810 | Thu, 1 PM | 1 | 345 |
| Forecast | Produced by | Method | Horizon |
|---|---|---|---|
| Solar forecast | ISO New England | ISO-NE seven-day solar power forecast and actual solar output | 7 days ahead, hourly |
ISO-NE publishes a point forecast with no confidence interval. Coastal cloud cover is the dominant error source, and behind-the-meter effects mean solar misses surface partly as demand misses.
ISO-NE publishes a solar power forecast from its seven-day forecast process, and this page plots the whole of it against actual metered output, with the settled hours scored below.
New England's defining solar fact: the majority of its capacity is behind-the-meter rooftop systems that never appear as generation. They appear as missing demand — a midday dip in the load curve that deepens every year. The metered utility-scale output plotted here is the visible tip; the full fleet's effect shows up on the load forecast page.
For ISO-NE, forecasting solar means forecasting demand correctly. A cloudier-than-expected afternoon raises metered demand at the same moment this metered output falls — the errors compound. That coupling is why the ISO forecasts solar explicitly at all.
curl "https://askthegrid.com/api/v1/grid/radar/curves?iso=ISONE&horizon=extended"
Connect your agent to mcp.askthegrid.com and this forecast is a tool call away — the same host Claude and ChatGPT connectors already use.
Several gigawatts — but the majority is behind-the-meter rooftop capacity that never registers as generation. It shows up instead as a midday dip in metered demand, which is why the load forecast page is the other half of this story.
Because a cloud bank moves two numbers at once: metered solar output falls and metered demand rises, since the rooftops stop serving their own buildings. The ISO must forecast the weather's effect on both sides of the meter simultaneously.
The scorecard above shows the recent record directly. Clear days verify well; marine cloud and fast-moving fronts drive the misses, and winter's low sun angle keeps absolute errors small but percentage errors large.
Plotted window Aug 28, 4:00 AM EDT → Sep 3, 10:00 AM EDT. Updated daily by ISO-NE; the latest vintage is shown.
| Sat, 8/29 |
|---|
| Sun, 8/30 |
|---|
| Mon, 8/31 |
|---|
| Tue, 9/1 |
|---|
| Wed, 9/2 |
|---|
| Thu, 9/3 |
|---|
Darkest cells are the tightest hours. The window peaks at 992 MW on Sun, 2 PM, local to the market.