{"id":21874732,"url":"https://github.com/longxingtan/kddcup2022-wpf","last_synced_at":"2025-04-15T01:25:38.072Z","repository":{"id":47798065,"uuid":"516191153","full_name":"LongxingTan/KDDCup2022-WPF","owner":"LongxingTan","description":"3rd Place Solution of KDD Cup 2022-Spatial Dynamic Wind Power Forecasting","archived":false,"fork":false,"pushed_at":"2023-09-21T05:23:16.000Z","size":83,"stargazers_count":116,"open_issues_count":0,"forks_count":19,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-28T13:21:16.081Z","etag":null,"topics":["bert","deep-learning","kdd2022","kddcup","spatio-temporal","time-series","wind-power-forecasting"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/LongxingTan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2022-07-21T01:58:48.000Z","updated_at":"2025-03-24T08:38:57.000Z","dependencies_parsed_at":"2023-07-24T08:03:13.314Z","dependency_job_id":null,"html_url":"https://github.com/LongxingTan/KDDCup2022-WPF","commit_stats":null,"previous_names":["longxingtan/kddcup2022-wpf"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LongxingTan%2FKDDCup2022-WPF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LongxingTan%2FKDDCup2022-WPF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LongxingTan%2FKDDCup2022-WPF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LongxingTan%2FKDDCup2022-WPF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LongxingTan","download_url":"https://codeload.github.com/LongxingTan/KDDCup2022-WPF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248987332,"owners_count":21194209,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert","deep-learning","kdd2022","kddcup","spatio-temporal","time-series","wind-power-forecasting"],"created_at":"2024-11-28T07:13:12.636Z","updated_at":"2025-04-15T01:25:38.054Z","avatar_url":"https://github.com/LongxingTan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# KDD Cup 2022 - Baidu Spatial Dynamic Wind Power Forecasting\n[![Open in Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/code/tanlongxing/kdd-cup-2022-wind-power-forecast)\n[![arxiv](https://img.shields.io/badge/cs.ML-2307.09248-red?logo=arxiv\u0026logoColor=red)](https://arxiv.org/abs/2307.09248)\n\nThis is the 3rd place solution in Baidu KDD Cup 2022. The task is to predict the wind farm's future 48 hours active power for every 10 minutes.\n\n\u003ch1 align=\"center\"\u003e\n\u003cimg src=\"./data/user_data/model.png\" width=\"700\" align=center/\u003e\n\u003c/h1\u003e\u003cbr\u003e\n\n\n## Solution summary\n- A single Transformer/ BERT model is made from [the tfts library](https://github.com/LongxingTan/Time-series-prediction). Follow its latest development [here](https://github.com/LongxingTan/Time-series-prediction)\n- Using sliding window to generate more samples\n- Only 2 raw features are used, wind speed and direction\n- The daily fluctuation is added by post-processing to make the predicted result in line with daily periodicity\n\n\n## How to use it\n\n0. Prepare the tensorflow environment\n```shell\npip install -r requirements.txt\n```\n1. Download the data from [Baidu AI studio](https://aistudio.baidu.com/aistudio/competition/detail/152/0/introduction), and put it in `./data/raw`\n2. Train the model, the file `result.zip` in `./weights/` can be used for submit. \n```shell\ncd src/train\npython nn_train.py\n```\n\n\n## Citation\n\nIf you find it useful in your research, please consider cite:\n\n```\n@article{tan2023application,\n  title={Application of BERT in Wind Power Forecasting-Teletraan's Solution in Baidu KDD Cup 2022},\n  author={Tan, Longxing and Yue, Hongying},\n  journal={arXiv preprint arXiv:2307.09248},\n  year={2023}\n}\n```\n\n\n## Reference\n\n```\n[1] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).\n[2] Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: De-composition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems 34 (2021), 22419–22430.\n[3] JingboZhou,ShuangliLi,LiangHuang,HaoyiXiong,FanWang,TongXu,Hui Xiong, and Dejing Dou. 2020. Distance-aware molecule graph attention network for drug-target binding affinity prediction. arXiv preprint arXiv:2012.09624 (2020).\n[4] HaoyiZhou,ShanghangZhang,JieqiPeng,ShuaiZhang,JianxinLi,HuiXiong, and Wancai Zhang. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 11106–11115.\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flongxingtan%2Fkddcup2022-wpf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flongxingtan%2Fkddcup2022-wpf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flongxingtan%2Fkddcup2022-wpf/lists"}