KDD CUP 2022 Wind Power Forecasting Team 88VIP Solution

TL;DR

This paper presents Team 88VIP's solution for wind power forecasting in KDD CUP 2022, combining gradient boosting and recurrent neural networks with feature engineering and ensembling to improve prediction accuracy across multiple timescales.

Contribution

The paper introduces a hybrid modeling approach using gradient boosting and RNNs, along with advanced feature engineering and ensembling techniques for wind power forecasting.

Findings

Achieved an online score of -45.213 in Phase 3.

Effectively modeled heterogeneous timescales from minutes to days.

Demonstrated the benefit of combining models for fluctuation mitigation.

Abstract

KDD CUP 2022 proposes a time-series forecasting task on spatial dynamic wind power dataset, in which the participants are required to predict the future generation given the historical context factors. The evaluation metrics contain RMSE and MAE. This paper describes the solution of Team 88VIP, which mainly comprises two types of models: a gradient boosting decision tree to memorize the basic data patterns and a recurrent neural network to capture the deep and latent probabilistic transitions. Ensembling these models contributes to tackle the fluctuation of wind power, and training submodels targets on the distinguished properties in heterogeneous timescales of forecasting, from minutes to days. In addition, feature engineering, imputation techniques and the design of offline evaluation are also described in details. The proposed solution achieves an overall online score of -45.213 in Phase 3.