INTERMITTENT_GEN_FCST_DATA

Stores the forecast generation (MW) for each interval within a given forecast of an intermittent generator. AEMO plans to remove this table in a Data Model version release after 5.6.

Source

INTERMITTENT_GEN_FCST_DATA updates every 30 minutes when AEMO issues a new 30-minute forecast of wind generation out to 8 days ahead.

Volume

~1,500,000 rows per generator per year

Column Schema

DUID

Identifier of the intermittent generator

Warning

This column may contain funny characters such as / (slash) or # (hash). This may break hive-style partitioning.

For more information, see the dedicated documentation page.

SQL Type: VARCHAR2(20) Polars Type: pl.Categorical

This column is mandatory, and a primary key.

Example: W/HOE#2

INTERVAL_DATETIME

Date Time (AEST) of the halfhour interval being forecast

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

This column is mandatory, and a primary key.

Example: 2026/01/20 00:05:00

RUN_DATETIME

Date Time of forecast (AEST).

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

This column is mandatory, and a primary key.

Example: 2026/01/20 00:05:00

LASTCHANGED

Date Time record was created

For more information, see the dedicated documentation page.

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

This column is not mandatory.

Example: 2026/01/20 00:05:00

POWERMEAN

The average forecast value in MW at the interval end

SQL Type: NUMBER(9,3) Polars Type: pl.Float64

This column is not mandatory.

POWERPOE50

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

SQL Type: NUMBER(9,3) Polars Type: pl.Float64

This column is not mandatory.

POWERPOEHIGH

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

SQL Type: NUMBER(9,3) Polars Type: pl.Float64

This column is not mandatory.

POWERPOELOW

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

SQL Type: NUMBER(9,3) Polars Type: pl.Float64

This column is not mandatory.

New Data Timing

Every 30 minutes when AEMO issues a new 30-minute forecast of wind generation out to 8 days ahead

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", "RUN_DATETIME", "LASTCHANGED").str.strptime(
            pl.Datetime, dt_s_fmt
        ),
    )
    .cast(
        {
            "DUID": pl.Categorical,
            "POWERMEAN": pl.Float64,
            "POWERPOE50": pl.Float64,
            "POWERPOEHIGH": pl.Float64,
            "POWERPOELOW": pl.Float64,
        }
    )
    # Deduplicate
    # We want one row per ['DUID', 'INTERVAL_DATETIME', 'RUN_DATETIME']
    # Tie-breaker: greatest value of LASTCHANGED
    .sort(LASTCHANGED, descending=False)
    .unique(subset=["DUID", "INTERVAL_DATETIME", "RUN_DATETIME"], keep="last")
)

Nemosis

This table is not yet available in Nemosis.

Availability

Visibility: Private

This table is not available in the public monthly MMSDM archive. Is is only available to registered market participants over FTP inside a VPN.

Deduplication and PDR Loader Configuration

The primary keys are:

• DUID

• INTERVAL_DATETIME

• RUN_DATETIME

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
FORECAST	INTERMITTENT_GEN_DATA	1

This means that the CSV files start with metadata columns:

I,FORECAST,INTERMITTENT_GEN_DATA,1,...
D,FORECAST,INTERMITTENT_GEN_DATA,1,...

Links

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

Copy as Markdown