# AI Serving Grid Stability — Data

来源：https://www.kaggle.com/competitions/ai-serving-grid-stability/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

*   **train.csv** - the training set. Use this to develop and/or train your algorithm. Note that the training set does not contain any information on when anomalies are present. Nevertheless, we can assure you that there are anomalies. This is an unsupervised learning challenge🚨. 
*   **test.csv** - the test set consists of 21 disjunct data segments that all have the same length (1800 time steps). Note that data segments with the same `test_data_segment_id` belong together. All but one data segments contain at least one anomaly. You are asked to spot the anomalies🔎. Your submission should only contain information if an anomaly is present at a certain time step or not. Additional Information: The test set contains the same features as the training set (except the additional `test_data_segment_id`).
*   **sample_submission.csv** - a sample submission file in the correct format.Your submission should look like this. Except that the predictions may be better 😉.  Note that the `id` column of your submission matches the `id` column of the test set.

A visual representation of the structure of the `train.csv` and `test.csv` as it was explained during the kick-off can be found [here](https://miro.com/app/board/uXjVND-YN_Y=/?share_link_id=813876208475). Additionally, you can find further explanations of the features in the [recording of the kick-off](https://tu-darmstadt.zoom.us/rec/play/bioWA7CnZFIXCWuUgrKvRe18gtM31VJPyIVSnBuPMvPDFfxs37OBNXjDX8uk2KHY6rknE0o5CV8jMo6J.3cr37bYPyXI3ngKK?canPlayFromShare=true&from=my_recording&continueMode=true&componentName=rec-play&originRequestUrl=https%3A%2F%2Ftu-darmstadt.zoom.us%2Frec%2Fshare%2Fpyuas5ZK8xA6v68P03OCdEr5PLyJR307We7uZWSNL17zJpFpcOqGz25yT6n_qMYS.3QusCIA4t1A74Epu%20Kenncode%3A%20a%23OS8EVq) from the minute 19:00.

## Task

Can you spot all time steps in which anomalies are present in the `test.csv` file? Since this is an unsupervised challenge and you have no information about what anomalies are and what they are not, we describe some examplary anomaly types in [the challenge overview](overview/example-anomalies). You can use those descriptions to double-check if the anomalies you discovered are valid.

## Features

| Parameter | Description | Unit |
|------- |----------------|------- |
| `aFRRactivation` | The automatic Frequency Restoration Reserve (aFRR) **activation** is the actual reserve capacity that has been brought online and is actively contributing to the grid's frequency restoration. | MW |
| `correctedDemand` / `correctedAFRR` | CorrectedAFFR refers to the actual amount of Frequency Restoration Reserve that is required to maintain the grid's frequency stability. It can be interpreted as the target value of the automatic Frequency Restoration Reserve. | MW |
|`aFRRrequest`|The automatic Frequency Restoration Reserve (aFRR) **request** is the actual requested reserve capacity that has been requested from the PICASSO system.|MW|
|`controlBandPos` and `controlBandNeg`| Maximum or minimum of the Frequency Restoration Reserve. |MW|
|`LFCInput`| LFCInput is the control variable of frequency restoration controllers, reflecting the imbalance of the respective control area. |MW|
|`FRCE`| FRCE is the "Frequency Restoration Control Error", reflecting the system imbalance that is caused within the respective control area. |MW|
|`Demand`| `Demand = correctedDemand - correction` |MW|
|`correction`| `correction = correctedDemand - Demand`  |MW|
|`correctionEcho`| `correction` 4-8s shifted  |MW|
|`participationCMO`| Represents a preliminary stage of participation |Bool|
|`participationIN`| Represents full participation |Bool|
|`BandLimitedCorrectedDemand`| Corrected demand limited by the control bands |MW|
|`controlArea`| ID or the control area |int|