Skip to content

INTERMITTENT_DS_PRED

Unconstrained Intermittent Generation Forecasts (UIGF) for Dispatch

Column Schema

DUID

DUID (or Area for non-scheduled) where 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.

Examples:

  • ADPPV1
  • ALDGASF1
  • ARWF1
  • AVLSF1
  • BALDHWF1
  • BANGOWF1
  • BANGOWF2
  • BANN1
  • BERYLSF1
  • BLUEGSF1

FORECAST_PRIORITY

Unsuppressed forecasts with higher priority values are used in Dispatch in preference to unsuppressed forecasts with lower priority values

SQL Type: NUMBER(10,0) Polars Type: pl.Int64

This column is mandatory, and a primary key.

Examples: 1, 436

INTERVAL_DATETIME

Date and Time when the forecast applies (dispatch interval ending)

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

This column is mandatory, and a primary key.

Example: 2026/09/01 00:05:00

OFFERDATETIME

Date and Time when this forecast submission was loaded

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

This column is mandatory, and a primary key.

Example: 2026/08/31 23:55:00

ORIGIN

Origin of this forecast (PARTICIPANTID, AWEFS/ASEFS, or another vendor)

SQL Type: VARCHAR2(20) Polars Type: str

This column is mandatory, and a primary key.

Examples:

  • ALNTARES
  • ARARATWF
  • AWEFS_ASEFS
  • BERBANKW
  • BOCOROCK
  • BODWF1
  • BOMENSF
  • BULGANA
  • BUNGALA1
  • BUNGALA2

RUN_DATETIME

Date and Time when the forecast applies (dispatch interval ending)

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

This column is mandatory, and a primary key.

Example: 2026/09/01 00:05:00

FORECAST_MEAN

Forecast MW value for this interval_DateTime

SQL Type: NUMBER(18,8) Polars Type: pl.Float64

This column is not mandatory.

Examples: 0.725, 0, 82, 84

FORECAST_POE10

Forecast 10% POE MW value for this interval_DateTime

SQL Type: NUMBER(18,8) Polars Type: pl.Float64

This column is not mandatory.

FORECAST_POE50

Forecast 50% POE MW value for this interval_DateTime. Used in Dispatch.

SQL Type: NUMBER(18,8) Polars Type: pl.Float64

This column is not mandatory.

Examples: 0.000001, 0, 82, 84

FORECAST_POE90

Forecast 90% POE MW value for this interval_DateTime

SQL Type: NUMBER(18,8) Polars Type: pl.Float64

This column is not mandatory.

New Data Timing

Publication of Dispatch solution. Data includes all valid forecasts for that interval

Code Examples

Polars

This table is so large that you should explicitly enumerate and cast every column, which will speed things up and prevents some errors. Although some of the datatypes are inferred, so they may be wrong. In particular, UInt16 vs UInt8 vs Int16 etc. If you get errors, you can swap these for just int.

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", "OFFERDATETIME", "RUN_DATETIME").str.strptime(
            pl.Datetime, dt_s_fmt
        ),
    )
    .cast(
        {
            "DUID": pl.Categorical,
            "FORECAST_PRIORITY": pl.Int64,
            "ORIGIN": str,
            "FORECAST_MEAN": pl.Float64,
            "FORECAST_POE10": pl.Float64,
            "FORECAST_POE50": pl.Float64,
            "FORECAST_POE90": pl.Float64,
        }
    )
    # Deduplicate
    # These files are so large that this step may cause your laptop to run out of memory.
    # We want one row per ['DUID', 'FORECAST_PRIORITY', 'INTERVAL_DATETIME', 'OFFERDATETIME', 'ORIGIN', 'RUN_DATETIME']
    .unique(
        subset=[
            "DUID",
            "FORECAST_PRIORITY",
            "INTERVAL_DATETIME",
            "OFFERDATETIME",
            "ORIGIN",
            "RUN_DATETIME",
        ],
        keep="any",
    )
)

Nemosis

This table is not yet available in Nemosis.

Example File

From PUBLIC_ARCHIVE_INTERMITTENT_DS_PRED_FILE01_202609010000.zip

RUN_DATETIMEDUIDOFFERDATETIMEINTERVAL_DATETIMEORIGINFORECAST_PRIORITYFORECAST_MEANFORECAST_POE10FORECAST_POE50FORECAST_POE90
2026/09/01 00:05:00ADPPV12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS30100
2026/09/01 00:05:00ADPPV12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS30200
2026/09/01 00:05:00ADPPV12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS30100
2026/09/01 00:05:00ADPPV12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS30200
2026/09/01 00:05:00ALDGASF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10100
2026/09/01 00:05:00ALDGASF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10200
2026/09/01 00:05:00ALDGASF12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS10100
2026/09/01 00:05:00ALDGASF12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS10200
2026/09/01 00:05:00ARWF12026/08/31 23:58:472026/09/01 00:05:00ARARATWF10180.5370636
2026/09/01 00:05:00ARWF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10181.681.6
2026/09/01 00:05:00ARWF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10281.681.6
...

CSETP.WORLDDVD_INTERMITTENT_DS_PREDAEMOPUBLIC2026/10/0915:37:57001791524277942MONTHLY_ARCHIVE001791524277942
IDEMANDINTERMITTENT_DS_PRED1RUN_DATETIMEDUIDOFFERDATETIMEINTERVAL_DATETIMEORIGINFORECAST_PRIORITYFORECAST_MEANFORECAST_POE10FORECAST_POE50FORECAST_POE90
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ADPPV12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS30100
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ADPPV12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS30200
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ADPPV12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS30100
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ADPPV12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS30200
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ALDGASF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10100
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ALDGASF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10200
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ALDGASF12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS10100
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ALDGASF12026/08/31 23:59:412026/09/01 00:05:00AWEFS_ASEFS10200
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ARWF12026/08/31 23:58:472026/09/01 00:05:00ARARATWF10180.5370636
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ARWF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10181.681.6
DDEMANDINTERMITTENT_DS_PRED12026/09/01 00:05:00ARWF12026/08/31 23:59:162026/09/01 00:05:00AWEFS_ASEFS10281.681.6
...
CEND OF REPORT1003

RUN_DATETIME,DUID,OFFERDATETIME,INTERVAL_DATETIME,ORIGIN,FORECAST_PRIORITY,FORECAST_MEAN,FORECAST_POE10,FORECAST_POE50,FORECAST_POE90
"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,301,0,,0,
"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,302,0,,0,
"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,301,0,,0,
"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,302,0,,0,
"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,101,0,,0,
"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,102,0,,0,
"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,101,0,,0,
"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,102,0,,0,
"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:58:47","2026/09/01 00:05:00",ARARATWF,101,,,80.5370636,
"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,101,81.6,,81.6,
"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,102,81.6,,81.6,
...

C,SETP.WORLD,DVD_INTERMITTENT_DS_PRED,AEMO,PUBLIC,2026/10/09,15:37:57,001791524277942,MONTHLY_ARCHIVE,001791524277942
I,DEMAND,INTERMITTENT_DS_PRED,1,RUN_DATETIME,DUID,OFFERDATETIME,INTERVAL_DATETIME,ORIGIN,FORECAST_PRIORITY,FORECAST_MEAN,FORECAST_POE10,FORECAST_POE50,FORECAST_POE90
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,301,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,302,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,301,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ADPPV1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,302,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,101,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,102,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,101,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ALDGASF1,"2026/08/31 23:59:41","2026/09/01 00:05:00",AWEFS_ASEFS,102,0,,0,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:58:47","2026/09/01 00:05:00",ARARATWF,101,,,80.5370636,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,101,81.6,,81.6,
D,DEMAND,INTERMITTENT_DS_PRED,1,"2026/09/01 00:05:00",ARWF1,"2026/08/31 23:59:16","2026/09/01 00:05:00",AWEFS_ASEFS,102,81.6,,81.6,
...
C,"END OF REPORT",1003

Availability

Visibility: Private & Public Next-Day

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 2024. 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 3 GB when zipped, 30 GB as unzipped CSV.

Tip

This table is large. Simply calling pd.read_csv() might fill up all the memory on your laptop. (As a rule of thumb, you need double the amount of memory as the size of the CSV.) You will need to think hard about memory optimisation. e.g. consider using Polars instead of Pandas, and selecting only the columns you care about.

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
DEMAND INTERMITTENT_DS_PRED 1

This means that the CSV files start with metadata columns:

I,DEMAND,INTERMITTENT_DS_PRED,1,...
D,DEMAND,INTERMITTENT_DS_PRED,1,...

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