Since this is an unsupervised challenge and you have no information about what anomalies are and what they are not, we will describe some examples of anomaly types. Once you have developed your algorithm and discovered the first potential anomalies, you can use the descriptions to check if your algorithm detects valid anomalies. But beware, we do not list all anomalies that are present in the data here ;) 

Note that you can find additional information on example anomalies 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) around minute 14:00 and 23:00.

# Example Anomaly 1

The values of `aFRRrequest` and `aFRRactivation`usually follow a time-delayed relationship. In this example, you can see that the values are even partially asynchronous.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1811734%2Ff853ce426a65698240c155c19cd5049a%2Fexample_anomaly1.png?generation=1702454220906675&alt=media)

# Example Anomaly 2

Due to transmission errors, freezes of signals can occur in some of the features.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1811734%2Fb7e732ddced53655398d85335376db9d%2Fexample_anomaly2.png?generation=1702454513763275&alt=media)

# Example Anomaly 3

Anomalies can also occur in the other variables, as can be seen here for `FRCE` and `LFCInput`. Yet the relationship of these two variables is unknown.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1811734%2Fe32af38e1185d1e46ca70dbc7e72ed6e%2Fexample_anomaly3.png?generation=1702454739170118&alt=media)