INTERMITTENT_GEN_FCST_P5_RUN
Contains forecast runs for intermittent wind and solar units, with a 5-minute resolution over the hour-ahead P5MIN timeframe. This is the parent table to the child table
INTERMITTENT_GEN_FCST_P5_PRED, which contains the corresponding forecast predictions over the full horizon.
Column Schema
DUID
Dispatchable unit identifier for which this forecast applies.
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
FORECAST_PRIORITY
Priority of forecast run, higher number is used in preference to lower number for the same provider.
SQL Type: NUMBER(10,0)
Polars Type: pl.Int64
This column is mandatory, and a primary key.
FORECAST_RUN_DATETIME
Datetime (interval ending) when this forecast run is valid. It aligns with run_datetime in downstream processes, unless a forecast run is missed, in this case the previous run is used.
SQL Type: DATE
Polars Type: pl.Datetime()
This column is mandatory, and a primary key.
Example: 2026/01/20 00:05:00
OFFERDATETIME
Datetime when this forecast submission was loaded.
SQL Type: DATE
Polars Type: pl.Datetime()
This column is mandatory, and a primary key.
Example: 2026/01/20 00:05:00
PROVIDERID
Forecast provider identifier
SQL Type: VARCHAR2(20)
Polars Type: pl.Categorical
This column is mandatory, and a primary key.
LASTCHANGED
Datetime when the forecast run was written into AEMO database.
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
MODEL_USED
Metadata describing the model used to produce the forecast run. This column is not made available to the public.
SQL Type: VARCHAR2(30)
Polars Type: str
This column is not mandatory.
PROVIDER_TIMESTAMP
Datetime when the provider created the forecast.
SQL Type: DATE
Polars Type: pl.Datetime()
This column is not mandatory.
Example: 2026/01/20 00:05:00
REMARKS
Comments relating to the forecast run. This column is not made available to the public.
SQL Type: VARCHAR2(300)
Polars Type: str
This column is not mandatory.
SUPPRESSED_PROVIDER
Flag indicating if the forecast run was suppressed by the provider when submitted. Suppressed forecasts are not used by downstream systems. Suppressed = 1, Unsuppressed = 0.
SQL Type: NUMBER(1,0)
Polars Type: pl.Boolean
This column is not mandatory.
TRANSACTION_ID
Transaction identifier for receiving the forecast run.
SQL Type: VARCHAR2(100)
Polars Type: str
This column is not mandatory.
New Data Timing
Every 5 minutes when a new intermittent generator forecast is available, covering the 2 hours ahead horizon with 5-minute resolution
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(
"FORECAST_RUN_DATETIME",
"OFFERDATETIME",
"LASTCHANGED",
"PROVIDER_TIMESTAMP",
).str.strptime(pl.Datetime, dt_s_fmt),
)
# Polars can't cast string straight to bool. Need to go via something else.
.cast({"SUPPRESSED_PROVIDER": pl.UInt8})
.cast(
{
"DUID": pl.Categorical,
"FORECAST_PRIORITY": int, # or pl.Int64
"PROVIDERID": pl.Categorical,
"MODEL_USED": str,
"REMARKS": str,
"SUPPRESSED_PROVIDER": pl.Boolean,
"TRANSACTION_ID": str,
}
)
# Deduplicate
# We want one row per ['DUID', 'FORECAST_PRIORITY', 'FORECAST_RUN_DATETIME', 'OFFERDATETIME', 'PROVIDERID']
# Tie-breaker: greatest value of LASTCHANGED
.sort(LASTCHANGED, descending=False)
.unique(
subset=[
"DUID",
"FORECAST_PRIORITY",
"FORECAST_RUN_DATETIME",
"OFFERDATETIME",
"PROVIDERID",
],
keep="last",
)
)
Nemosis
This table is not yet available in Nemosis.
Availability
AEMO's documentation states that this table's visibility is "Private & Public Next-Day". However, it is not available in the public monthly MMSDM archive. AEMO probably call this public because it is available to all market participants over private FTP.
There is a chance that is is still public to non-participants. It may only be available for some months; or (rarely) it may be available in a non-standard location.
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.
| Report Name | Report Subtype | Version |
|---|---|---|
| DEMAND | INTERMITTENT_GEN_FCST_P5_RUN | 1 |
This means that the CSV files start with metadata columns:
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