## Files

*   **train.csv** - the training set. Use this to develop and/or train your algorithm. 
*   **test.csv** - the test set. Use this dataset to make predictions that you will upload as submissions. The `test.csv` includes most of the parameters from `train.csv` but misses `P`, `load`, and `residual_load`. You are asked to forecast the `residual_load`. This can either be done directly **or** by forecasting `P` and `load` individually and calculating `residual_load` (`residual_load`= `load`-`P`). Your submission should only contain information about the `residual_load` ( see `sample_submission.csv`). 
*   **sample_submission.csv** - a sample submission file in the correct format. Your submission should look like this. Except that the predictions may be better 😉.

## Parameters

|    Name      |       Contained in Set (Train, Test)     | Description   | Unit  | 
|----------|------------------|------|------|
| Time       | Train; Test |  Timestamp    | YYYY-MM-DD HH:MM:SS  | 
| P       | Train | Amount of power generated by the photovoltaic system.   | Watt [W]  | 
| Gb(i)       | Train; Test | Direct in-plane irradiance. It is the fraction of the solar radiation that directly reaches the ground. It is only available if clouds do not block the sun.  | Watt per square meter [W/m^2] | 
| Gd(i)       | Train; Test | Diffuse in-plane irradiance. It is the fraction of solar radiation that reaches the ground after being reflected or scattered by the atmosphere. Its a also available if clouds block the sun. | Watt per square meter [W/m^2] | 
| H_sun       | Train; Test | Sun height (elevation)   | Angle [°]  | 
| T2m       | Train; Test | Air temperature at 2m	  |  [°C]  | 
| WS10m       | Train; Test | Wind speed at 10m	  | [m/s]	 | 
| load       | Train | Amount of power required by the plant at this timestep. | Watt [W] | 
| residual_load       | Train | `residual_load` = `load`-`P`. If this value is positive: The amount of power that has to be taken from the grid. If this value is negative: The amount of energy which is fed into the electricity grid.  | Watt [W] | 
| dataset_id       | Train; Test | Train and Test data with the same `dataset_id` belong together  | id | 

## Train Test Splits

To make sure that your algorithm is working well and has not just randomly produced one good prediction, we created multiple train test splits. There are 11 disjunct train test splits in total. To make it easier for you we have marked related Train Test data with a common `dataset_id`.

## Task

Can you predict the `residual_load` for the times contained in the `test.csv` file?