Versions Compared

Version Old Version 39 New Version 40
Changes made by

brett gebert

brett gebert

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Model updated

...

8th May 2024

Summary

The retraining process resulted in two new models, one for PD and one for 7day price forecast. After experimentation we retrained the price forecasting models using existing features and hyper parameter settings. The increase in accuracy (using Absolute Mean Error, AME) was approximately 5%4%. (see validation results table below comparing the previous models with the new models).

...

Both PD and 7day price forecast models were trained on data between 01-0104-2021 and 1508-0104-2024.

The market suspension period and a period after the Callide explosion were removed from the training data.

...

The model was validated by predicting the price between 1609-0104-2024 and 30-0104-2024.

New features (input data) exceptions

  • The feature set is the same as the previous model. The main benefit of the new model is that more recent market data are consumed in the training process. The training does not weight the most recent market data.

    • A number of experiments were conducted by changing the feature list and some hyper parameters however this didn’t not achieve a significant benefit to the model tests. Hence for consistency we have not made changes to the model other than extending the training period to the most recent market data. Unlike the August model update included significant changes to both the feature set and the hyper parameters.

    Validation set is from the 1st of November to the 7th of November

    • .

    Oddly enough the impact of the Melbourne Cup did not have a significant impact on the performance metrics.

Predispatch model

p7day model

Model_id

2023110820240503_142510090016_CB_2

2023110820240503_140809085256_CB_7D_2

Previous model release date

9th November 2023

9th November 20235th February 2024

5th February 2024

Latest release date (after retraining)

5th February 6th May 20245th February

6th May 2024

Machine Learning Algorithm

Ensemble predictor: gradient boosting

Ensemble predictor: gradient boosting

Training Period

1st January 2021 to 15th January A2021 to 8th April 2024

1st January April 2021 to 15th January 8th April 2024

Hyper-parameter type

A

A

Hyper-parameter notes

No weighting across time periods

No weighting across time periods

Target

Dispatchprice (30min resolution)

Dispatchprice (30min resolution)

Input (and training) variables

PREDISPATCHPRICE

rrp

DISPATCHPRICE

last 3 day average actual RRP for same time

PREDISPATCHREGIONSUM (intervention = 0)

hours_out

time_of_day

day_type (weekday_or_weekend)

dispatchableload

netinterchage

(availablegeneration - uigf)

(dispatchablegeneration - scheduled_clearedmw)

ss_solar_clearedmw

ss_solar_uigf

ss_wind_clearedmw

ss_wind_uigf

totaldemand

totalintermittentgeneration

STPASA_REGIONSOLUTION

hours_out

time_of_day

day_type (weekday_or_weekend)

aggregatepasaavailability

aggregatescheduledload

netinterchangeunderscarcity

aggregatecapacityavailable

ss_solar_cleared

ss_wind_uigf

ss_wind_cleared

ss_solar_uigf

demand10

demand50

totalintermittentgeneration

demand_and_nonschedgen

...

All error metrics are in $/MWhr.

PD Results

Metric/

Region

Actual Mean Price

Mean Prediction New Model

Mean Prediction Previous Model

Absolute Mean Error New Model

Absolute Mean Error Previous Model

Average Error New Model

Average Error Previous Model

NSW1

9298.226592

105.3738

91106.7044

8327.8753

8528.0256

06.1573-0

7.5279

QLD1

21488.7352

23899.0905

202100.7732

22526.1659

20627.2249

2310.3654

-11.9581

SA1

3689.87

8651.1648

4683.389746

31.3739

4531.4913

14-3.3039

9-5.5290

TAS1

3781.4332

4282.4995

3986.7990

1929.241419

32.9299

51.0663

25.3658

VIC1

1792.3466

2584.2551

2182.7598

2528.9264

2729.5014

7-8.9114

4-9.4168

7 Day Results

89070860672274618228420341756424820263915278221331145479051883014347935444532222623391311303052481388174117

Metric/

Region

Actual Mean Price

Mean Prediction New Model

Mean Prediction Previous Model

Absolute Mean Error New Model

Absolute Mean Error Previous Model

Average Error New Model

Average Error Previous Model

NSW1

94.

66

88.

83

82.

20

29.

92

31.

71

-

5.

82

-

12.

45

QLD1

83.

54

80.

40

73.

41

29.

42

30.

35

-

3.

14

-10.

13

SA1

86.

50

110.

71

91.

75

58.

95

51.

48

24.

20

5.

25

TAS1

80.

56

71.

65

70.

37

31.

70

35.

30

-8.

91

-

10.

19

VIC1

89.

89

78.

89

68.

39

37.

20

39.

75

-11.

00

-21.

50

Info

Variables that imply binding interconnectors (such as limits and marginal values) are currently not included as features.

...