Benchmarks and Custom Package for Electrical Load Forecasting

Zhixian Wang, Qingsong Wen, Chaoli Zhang, Liang Sun, Leandro Von Krannichfeldt, Shirui Pan, Yi Wang

Keywords: Load forecasting, Forecast evaluation, Feature engineering, Customized loss function

Abstract: Load forecasting is of great significance in the power industry as it can provide a reference for subsequent tasks such as power grid dispatch, thus bringing huge economic benefits. However, there are many differences between load forecasting and traditional time series forecasting. On the one hand, the load is largely influenced by many external factors, such as temperature or calendar variables. On the other hand, load forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch, rather than simply pursuing prediction accuracy. In addition, the scale of predictions (such as building-level loads and aggregated-level loads) can also significantly impact the predicted results. In this paper, we provide a comprehensive load forecasting archive, which includes load domain-specific feature engineering to help forecasting models better model load data. In addition, different from the traditional loss function which only aims for accuracy, we also provide a method to customize the loss function and link the forecasting error to requirements related to subsequent tasks (such as power grid dispatching costs) integrating it into our forecasting framework. Based on such a situation, we conducted extensive experiments on 16 forecasting methods in 11 load datasets at different levels under 11evaluation metrics, providing a reference for researchers to compare different load forecasting models.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4756