Latest
...
Machine learning algorithm details
Release Date:
2023-04-04
Algo type:
Type: A
Random Forest Regression
Training period
From March 2018 to 27th of 30th March 2023.
model release
Predispatch model | p7day model | |
|---|---|---|
Modelid | 20221129_171124_CB_1 | |
Model retraining date | 4th April 2023 | |
Machine Learning Algorithm | Random Forecast Regression | Random Forecast Regression |
Training Period | March 2018 to 30th March 2023 | |
Hyper-parameter type | A | A |
Hyper-parameter notes | No weighting across time periods. | No weighting across time periods. |
Target | Dispatchprice (30min resolution) | |
Input (and training) variables | rrp dispatchableload netinterchange rolling_rrp (availablegeneration - uigf) (dispatchablegeneration - scheduled_clearedmw) ss_solar_clearedmw ss_solar_uigf ss_wind_clearedmw ss_wind_uigf totaldemand totalintermittentgeneration | |
Machine learning algorithm details
Hyper parameters:
No weighting across time periods. It is likely that we’ll add weighting to more recent training periods.
To be disclosed with later release stages.
Model_id:
20221129_171124_CB_1
Input variables (features)
Note that more variables are used as inputs into the model than are presented in the Model Input Chart in the Home page of pd4castr. Chart variables are representative of the key variables of the model but changes in other variables may also impact the model forecast.
| Info |
|---|
Variables that imply binding interconnectors (such as limits and marginal values) are currently not included as features. |
Target:
dispatchprice for each region
List of features:
...
Predispatchregionsum fields used (including all regions)
...
hours_out
...
rrp
...
dispatchableload
...
netinterchange
...
rolling_rrp
...
availablegeneration - uigf
...
dispatchablegeneration - scheduled_clearedmw
...
ss_solar_clearedmw
...
ss_solar_uigf
...
ss_wind_clearedmw
...
ss_wind_uigf
...
totaldemand
...
...