| Table of Contents |
|---|
Summary
pd4castr is a price forecasting web service that inserts input data into provides a price forecast by running a model to generate a price forecastformulated by a machine learning algorithm (MLA). A model is basically essentially a very big equation that has been formulated by a machine learning algorithm (MLA). Initially pd4castr will consume AEMO predispatch data however in time the User will be able to select the input data source, and/or adjust the data (much like price sensitivities), select the model or even generate their own MLA derives by ‘training’ on historical data. pdView selects the input variables, the training periods and the type of MLA (as well as the hyper parameters used in the MLA) so that price forecasts can accurately predict prices for many energy market scenarios.
Input data can include forecast demand, available generation, interconnector flows and so forth. Input data may vary depending on the model.
The user interface of pd4castr is designed so that the User can quickly inspect and compare forecasts across variations in input data including rundatetime and source as well as the model used. The input data are similarly presented so that forecasts can be calibrated and contextualised by the User. \
Model performance metrics will be provided so that efficacy can be assessed.
Use Case
We anticipate that pd4castr will produce far to provide a clear view and understanding of the price forecasts including model performance, input data and training periods.
Models are routinely retrained and released when there is a clear improvement in performance.
Forecast Time Periods
Currently only the predispatch time horizon is forecast.
Soon to be released is the week ahead forecast.
User Interface
Model re-training process
The pdView Team periodically generates new models by re-training a MLA. The re-training iteration can include any of the following:
Introducing recent historical data,
weighting historical time periods,
changing or adding input variables, or
changing the machine learning algorithm or the hyper parameters that tune the algorithm.
...
The key to retraining is to assess each new model against a known baseline. If a new model performs better than an old model then the new model is uploaded onto pd4castr where it can be used to generate new price forecasts.
| Info |
|---|
A model only takes a few milliseconds to produce a price forecast when presented with new input data. Hence there is no limit to the number of models available to a user. This means that you don’t have to use the latest model. |
Use Case
Early and accurate forecasts
pd4castr generates more accurate forecasts than AEMO’s predispatch price forecast when the forecast period is still some time away. This is because the pd4castr model factors in bidding behaviour and other dynamics whereas AEMO’s price forecast process follows a strict protocol . We also anticipate that as and does not anticipate changes in unit commitment and bidding.
As real time approaches the forecast period approaches , AEMO’s price forecast will provide likey become a better indicator of likely price outcome - if you think about it, dispatch - this is because the dispatch period - which you can think of as forecast period time zero - is kind of like AEMO’s perfect forecast by definition (nearly) perfect since it is (nearly) always a 100% correct.
...
Independent forecast for middle and back office
Ideally risk metrics should be calculated independently of the front office. Where possible why not consume data provided by a reputable third party?
pd4castr is a price forecasting web service that uses a model that consumes input data to generate a price forecast.
...