This competition aims to tackle the issue of energy imbalance, a situation where the energy expected to be used doesn't line up with the actual energy used or produced. Prosumers, who both consume and generate energy, contribute a large part of the energy imbalance. Despite being only a small part of all consumers, their unpredictable energy use causes logistical and financial problems for the energy companies.
The number of prosumers is rapidly increasing, and solving the problems of energy imbalance and their rising costs is vital. If left unaddressed, this could lead to increased operational costs, potential grid instability, and inefficient use of energy resources. If this problem were effectively solved, it would significantly reduce the imbalance costs, improve the reliability of the grid, and make the integration of prosumers into the energy system more efficient and sustainable. Moreover, it could potentially incentivize more consumers to become prosumers, knowing that their energy behavior can be adequately managed, thus promoting renewable energy production and use.
Submissions are evaluated on the Mean Absolute Error (MAE) between the predicted return and the observed target.
This is a future data prediction competition with an active training phase and a second period where selected submissions will be evaluated against future ground truth data.
- November 1, 2023 - Start Date.
- January 24, 2024 - Entry Deadline. You must accept the competition rules before this date in order to compete.
- January 24, 2024 - Team Merger Deadline. This is the last day participants may join or merge teams.
- January 31, 2024 - Final Submission Deadline.
Submissions to this competition must be made through Notebooks. In order for the "Submit" button to be active after a commit, the following conditions must be met:
- CPU Notebook <= 9 hours run-time
- GPU Notebook <= 9 hours run-time
- Internet access disabled
- Freely & publicly available external data is allowed, including pre-trained models
- Submission file must be named submission.csv and be generated by the API.