Implemented imbalance price reconstruction

Result-Reports/December.md

@@ -2,7 +2,7 @@
 - [ ] Quantiles zelf breder maken na fitten, literatuur bekijken (overconfident voor ondergrens) (Validation set januari 2023)
 Eerst literatuur bekijken ofdat probleem al voorkomt
 
-- [ ] compare reconstructed prices with real imbalance prices (on figure and metrics on whole test set)
+- [x] compare reconstructed prices with real imbalance prices (on figure and metrics on whole test set)
 
 - [ ] Baseline policy (Eche imbalanceprijzen):
   - Batterij:

Result-Reports/Imbalance_price_reconstruction.md

@@ -0,0 +1,27 @@
+# Imbalance Price Reconstruction
+Some things to note: \
+SI = ACE - NRV but we only know NRV. We take the SI as the -NRV.\
+There is also some uncertainty on how the bid ladder is constructed and what factors are taken into account to calculate the imbalance price. We will try some different methods to reconstruct the imbalance price and see which one is the best.\
+
+The following examples were reconstructed by only using the real NRV values and the bids published by Elia.
+
+Method 1: Sort bids on price
+Method 2: Sort bids on activation order and then on price (Elia says they use this method)
+
+![](imbalance_prices_images/imbalance_price_reconstruction_04-07-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_04-11-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_04-12-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_06-08-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_14-02-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_14-03-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_16-02-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_17-08-2023.png)
+![](imbalance_prices_images/imbalance_price_reconstruction_29-08-2023.png)
+
+From these examples we can see that just sorting based on price is given better reconstructions than the method used by Elia???????? This is something weird.
+
+# Mean Absolute Error
+| Method | MAE |
+| --- | --- |
+| Method 1 | 1842235.14 |
+| Method 2 | 4461725.94 |