# Introduction

Europeans are used to a constant electricity supply and rarely experience blackouts. TransnetBW’s control room is one of the places where people are working 24/7 to maintain this seemingly inexhaustible flow. The company is one of four transmission system operators in Germany and ensures the stability of our electricity grid. To do this, the same amount of electricity must be fed into the grid as is taken out at any point in time to maintain a frequency of 50 Hertz. To ensure this, TransnetBW uses automated control signals to instruct power plant operators to ramp up or down their infeed. In this challenge, we look at the secondary reserve (a primary and a tertiary version also exists) that must be active after a maximum of 5 minutes.

Until recently, every European state used power plants in their own country to maintain the system balance. This has regularly led to the following situations: In Germany, for example, a power plant is ramped up and a few kilometers further across the border another power plant is ramped down. The costs that are incurred by this inefficient use of reserves are ultimately paid by all electricity customers. Since 2022, TransnetBW has operated the PICASSO platform that coordinates the deployment of secondary reserves in real-time, ensuring optimal usage of reserves in a European domestic balancing market. This makes the PICASSO platform the world`s largest system for real-time optimization of electricity flows. It leads to macroeconomic savings of several hundred million euros per year and contributes to the decarbonization of the balancing market.

To ensure the correct functionality of the platform, information on imbalances, reserves, transmission capacities, and many other time series are constantly monitored. These monitored features sometimes behave strangely, indicating to the control room engineers that it might be necessary to take action. Algorithms that recognize anomalies early and precisely may be of great help here. That’s why TransnetBW, in cooperation with Fraunhofer IEE, provides a previously unpublished data set consisting of various PICASSO platform time series to participants. 

# Challenge

This is an unsupervised learning challenge where we ask you to develop an (AI) algorithm to detect anomalies in the operation of the PICASSO platform. If this is successful, AI-based solutions could support TransnetBW and other transmission system operators in recognizing deviations from the regular operation. The challenge aims at evaluating different solution methodologies in a short period of time and establishing personal contacts between industry and AI developers. You can find a more technical problem description and the data itself in the [data tab](https://www.kaggle.com/competitions/transnetbw-test-challenge/data).

# Important Links 

- If you are not yet registered, please register on the [registration page](https://eveeno.com/anomalydetectionineuropeanenergy) (even if the challenge has already started). 
- Get an even more detailed description of the challenge and information about the final event on our [website](https://hessian.ai/industry-challenge/).
- View the [recording](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) of the kickoff presentations and the [documentation](https://app.mural.co/t/quantchengluckgmbhcokg7492/m/quantchengluckgmbhcokg7492/1699602119184/d836574a2883a4aeb50b480a128b16da5e299882?sender=u6ee4d51e9cc36f12620a7561) of the kickoff event.
- Join us at [discord](https://discord.gg/Q9ZPhTQbS3) to stay up to date and to get in contact with other participants.
- Link to Q&A session on 11.01.2024 at 4pm [here](https://tu-darmstadt.zoom-x.de/j/64122381186?pwd=TXVOMGZhUks0VlFHeDY1WXhGUnB1Zz09)
- Link to final event on 14.02.2024 at 1-3:30pm [here](https://tu-darmstadt.zoom-x.de/j/68385147444?pwd=UmpsRUw1bHI2Z0I2WU16ZUNWM0NjQT09)