Skip to content

ROOFTOP_PV_FORECAST

Regional forecasts of Rooftop Solar generation across the half-hour intervals over 8 days. AEMO plans to remove this table in a Data Model version release after 5.6.

Column Schema

INTERVAL_DATETIME

The forecast half-hour interval (time ending)

SQL Type: DATE Polars Type: pl.Datetime()

This column is mandatory, and a primary key.

Example: 2026/09/01 01:00:00

REGIONID

Region identifier

Warning

Unlike most tables, in older months, REGIONID can include QLDN, QLDC, QLDS, TASN, TASC to refer to north/central/south of the state.

For more information, see the dedicated documentation page.

The SQL type is VARCHAR2(20). This is actually a factor/enum, with values:

  • QLDN

  • QLDC

  • QLDS

  • QLD1

  • TASN

  • TASS

  • TAS1

  • NSW1

  • VIC1

  • SA1

This column is mandatory, and a primary key.

VERSION_DATETIME

Date time this forecast was produced

SQL Type: DATE Polars Type: pl.Datetime()

This column is mandatory, and a primary key.

Example: 2026/09/01 00:30:00

LASTCHANGED

Last date and time record changed

For more information, see the dedicated documentation page.

SQL Type: DATE Polars Type: pl.Datetime()

This column is not mandatory.

Example: 2026/09/01 00:21:58

POWERMEAN

The average forecast value in MW at the interval end

SQL Type: NUMBER(12,3) Polars Type: pl.Float64

This column is not mandatory.

Examples: 3.309, 0, 5394.546

POWERPOE50

50% probability of exceedance forecast value in MW at the interval end

SQL Type: NUMBER(12,3) Polars Type: pl.Float64

This column is not mandatory.

Examples: 0.006, 0, 5380.704

POWERPOEHIGH

10% probability of exceedance forecast value in MW at the interval end

SQL Type: NUMBER(12,3) Polars Type: pl.Float64

This column is not mandatory.

Examples: 0.026, 0, 1907, 5806.39

POWERPOELOW

90% probability of exceedance forecast value in MW at the interval end

SQL Type: NUMBER(12,3) Polars Type: pl.Float64

This column is not mandatory.

Examples: 0.001, 0, 4807.35

New Data Timing

Every 30 minutes over 8 days

Code Examples

Polars

Casting is enums, categoricals etc is not essential, but may speed up parsing. Swapping int for pl.UInt16, pl.Int32 would also speed up parsing. However some of the datatypes are inferred, so they may be wrong.

This code deduplicates for you. Deduplication is normally only required across multiple months.

This code assumes that all columns are present, which may not be true for older files.

import polars as pl
import polars.selectors as cs

# e.g. "2029/03/15 00:05:00"
dt_s_fmt = "%Y/%m/%d %H:%M:%S"

csv_paths = ["SOMEFILE.CSV", "OTHERFILE.CSV"]

lf = (
    pl.concat(
        [
            pl.scan_csv(
                csv_path,  # must be unzipped beforehand
                skip_rows=1,  # skip the header
                infer_schema=False,  # much faster
            )
            .filter(cs.by_index(0) == "D")  # drop the footer
            .select(~cs.by_index(range(4)))  # drop metadata columns
            for csv_path in csv_paths
        ],
        how="diagonal_relaxed",
    )
    .with_columns(
        pl.col("INTERVAL_DATETIME", "VERSION_DATETIME", "LASTCHANGED").str.strptime(
            pl.Datetime, dt_s_fmt
        ),
    )
    .cast(
        {
            "REGIONID": pl.Enum(
                [
                    "QLDN",
                    "QLDC",
                    "QLDS",
                    "QLD1",
                    "TASN",
                    "TASS",
                    "TAS1",
                    "NSW1",
                    "VIC1",
                    "SA1",
                ]
            ),
            "POWERMEAN": pl.Float64,
            "POWERPOE50": pl.Float64,
            "POWERPOEHIGH": pl.Float64,
            "POWERPOELOW": pl.Float64,
        }
    )
    # Deduplicate
    # We want one row per ['INTERVAL_DATETIME', 'REGIONID', 'VERSION_DATETIME']
    # Tie-breaker: greatest value of ['VERSION_DATETIME', 'INTERVAL_DATETIME', 'REGIONID']
    .sort(["VERSION_DATETIME", "INTERVAL_DATETIME", "REGIONID"], descending=False)
    .unique(subset=["INTERVAL_DATETIME", "REGIONID", "VERSION_DATETIME"], keep="last")
)

Nemosis

This table is not yet available in Nemosis.

Example File

From PUBLIC_ARCHIVE_ROOFTOP_PV_FORECAST_FILE01_202609010000.zip

VERSION_DATETIMEREGIONIDINTERVAL_DATETIMEPOWERMEANPOWERPOE50POWERPOELOWPOWERPOEHIGHLASTCHANGED
2026/09/01 00:30:00NSW12026/09/01 01:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00QLD12026/09/01 01:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00TAS12026/09/01 01:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00SA12026/09/01 01:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00NSW12026/09/01 01:30:0000002026/09/01 00:21:58
2026/09/01 00:30:00QLD12026/09/01 01:30:0000002026/09/01 00:21:58
2026/09/01 00:30:00SA12026/09/01 01:30:0000002026/09/01 00:21:58
2026/09/01 00:30:00TAS12026/09/01 01:30:0000002026/09/01 00:21:58
2026/09/01 00:30:00NSW12026/09/01 02:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00QLD12026/09/01 02:00:0000002026/09/01 00:21:58
2026/09/01 00:30:00SA12026/09/01 02:00:0000002026/09/01 00:21:58
...

CSETP.WORLDDVD_ROOFTOP_PV_FORECASTAEMOPUBLIC2026/10/0916:28:11001791527291380MONTHLY_ARCHIVE001791527291380
IROOFTOPFORECAST1VERSION_DATETIMEREGIONIDINTERVAL_DATETIMEPOWERMEANPOWERPOE50POWERPOELOWPOWERPOEHIGHLASTCHANGED
DROOFTOPFORECAST12026/09/01 00:30:00NSW12026/09/01 01:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00QLD12026/09/01 01:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00TAS12026/09/01 01:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00SA12026/09/01 01:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00NSW12026/09/01 01:30:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00QLD12026/09/01 01:30:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00SA12026/09/01 01:30:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00TAS12026/09/01 01:30:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00NSW12026/09/01 02:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00QLD12026/09/01 02:00:0000002026/09/01 00:21:58
DROOFTOPFORECAST12026/09/01 00:30:00SA12026/09/01 02:00:0000002026/09/01 00:21:58
...
CEND OF REPORT1003

VERSION_DATETIME,REGIONID,INTERVAL_DATETIME,POWERMEAN,POWERPOE50,POWERPOELOW,POWERPOEHIGH,LASTCHANGED
"2026/09/01 00:30:00",NSW1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",QLD1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",TAS1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",SA1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",NSW1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",QLD1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",SA1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",TAS1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",NSW1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",QLD1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
"2026/09/01 00:30:00",SA1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
...

C,SETP.WORLD,DVD_ROOFTOP_PV_FORECAST,AEMO,PUBLIC,2026/10/09,16:28:11,001791527291380,MONTHLY_ARCHIVE,001791527291380
I,ROOFTOP,FORECAST,1,VERSION_DATETIME,REGIONID,INTERVAL_DATETIME,POWERMEAN,POWERPOE50,POWERPOELOW,POWERPOEHIGH,LASTCHANGED
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",NSW1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",QLD1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",TAS1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",SA1,"2026/09/01 01:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",NSW1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",QLD1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",SA1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",TAS1,"2026/09/01 01:30:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",NSW1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",QLD1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
D,ROOFTOP,FORECAST,1,"2026/09/01 00:30:00",SA1,"2026/09/01 02:00:00",0,0,0,0,"2026/09/01 00:21:58"
...
C,"END OF REPORT",1003

Availability

Visibility: Public

This table is in the public monthly MMSDM archive.

I have collated the list of all those files into one place, in this CSV metadata file. (Columns year, month, url, compressed_size in bytes).

The earliest available data is month 8 of 2016. The most recent available data is month 9 of 2026.

Every month in between has a file. (No gaps.)

Data Size

Each year of data is approximately 420 MB when zipped, 4 GB as unzipped CSV.

Deduplication and PDR Loader Configuration

The primary keys are:

The transaction type is "insert", which means that you will usually not see duplicate data. If you do, you can deduplicate based on the primary keys, without sorting first. Rows from different files with the same primary keys should have the same values.

PDR Loader configuration is:

Report Name Report Subtype Version
ROOFTOP FORECAST 1

This means that the CSV files start with metadata columns:

I,ROOFTOP,FORECAST,1,...
D,ROOFTOP,FORECAST,1,...

Indexes

This page as JSON (schema documented here, but may change)

Download a JSON Schema specification for this table.

Official AEMO schema documentation

Other Information

Package: DEMAND_FORECASTS