The CityLearn Challenge 2022: Overview, Results, and Lessons Learned

Kingsley Nweye, Zoltan Nagy, Sharada Mohanty, Dipam Chakraborty, Siva Sankaranarayanan, Tianzhen Hong, Sourav Dey, Gregor Henze, Jan Drgona, Fangquan Lin, Wei Jiang, Hanwei Zhang, Zhongkai Yi, Jihai Zhang, Cheng Yang, Matthew Motoki, Sorapong Khongnawang, Michael Ibrahim, Abilmansur Zhumabekov, Daniel May, Zhihu Yang, Xiaozhuang Song, Han Zhang, Xiaoning Dong, Shun Zheng, Jiang Bian
Proceedings of the NeurIPS 2022 Competitions Track, PMLR 220:85-103, 2022.

Abstract

The shift to renewable power sources and building electrification to decarbonize existing and emerging building stock present unique challenges for the power grid. Building loads and flexible resources e.g. batteries must be adequately managed simultaneously to unlock the full flexibility potential and reduce costs for all stakeholders. Simple control algorithms based on expert knowledge e.g. RBC, as well as, advanced control algorithms e.g. MPC and RLC can be utilized to intelligently manage flexible resources. The CityLearn Challenge is an opportunity to compete in investigating the potential of AI and distributed control systems to tackle multiple problems within the built-environment. The CityLearn Challenge 2022 is the third of its kind with the overall objective of crowd-sourcing generalizable control policies that improve energy, cost and environmental objectives by taking advantage of batteries for load shifting in a CityLearn digital twin of a real-world grid-interactive neighborhood. Highlighted here are the uniqueness of this third edition, baseline and top solutions, and lessons learned for future editions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v220-nweye23a, title = {The CityLearn Challenge 2022: Overview, Results, and Lessons Learned}, author = {Nweye, Kingsley and Nagy, Zoltan and Mohanty, Sharada and Chakraborty, Dipam and Sankaranarayanan, Siva and Hong, Tianzhen and Dey, Sourav and Henze, Gregor and Drgona, Jan and Lin, Fangquan and Jiang, Wei and Zhang, Hanwei and Yi, Zhongkai and Zhang, Jihai and Yang, Cheng and Motoki, Matthew and Khongnawang, Sorapong and Ibrahim, Michael and Zhumabekov, Abilmansur and May, Daniel and Yang, Zhihu and Song, Xiaozhuang and Zhang, Han and Dong, Xiaoning and Zheng, Shun and Bian, Jiang}, booktitle = {Proceedings of the NeurIPS 2022 Competitions Track}, pages = {85--103}, year = {2022}, editor = {Ciccone, Marco and Stolovitzky, Gustavo and Albrecht, Jacob}, volume = {220}, series = {Proceedings of Machine Learning Research}, month = {28 Nov--09 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v220/nweye23a/nweye23a.pdf}, url = {https://proceedings.mlr.press/v220/nweye23a.html}, abstract = {The shift to renewable power sources and building electrification to decarbonize existing and emerging building stock present unique challenges for the power grid. Building loads and flexible resources e.g. batteries must be adequately managed simultaneously to unlock the full flexibility potential and reduce costs for all stakeholders. Simple control algorithms based on expert knowledge e.g. RBC, as well as, advanced control algorithms e.g. MPC and RLC can be utilized to intelligently manage flexible resources. The CityLearn Challenge is an opportunity to compete in investigating the potential of AI and distributed control systems to tackle multiple problems within the built-environment. The CityLearn Challenge 2022 is the third of its kind with the overall objective of crowd-sourcing generalizable control policies that improve energy, cost and environmental objectives by taking advantage of batteries for load shifting in a CityLearn digital twin of a real-world grid-interactive neighborhood. Highlighted here are the uniqueness of this third edition, baseline and top solutions, and lessons learned for future editions.} }
Endnote
%0 Conference Paper %T The CityLearn Challenge 2022: Overview, Results, and Lessons Learned %A Kingsley Nweye %A Zoltan Nagy %A Sharada Mohanty %A Dipam Chakraborty %A Siva Sankaranarayanan %A Tianzhen Hong %A Sourav Dey %A Gregor Henze %A Jan Drgona %A Fangquan Lin %A Wei Jiang %A Hanwei Zhang %A Zhongkai Yi %A Jihai Zhang %A Cheng Yang %A Matthew Motoki %A Sorapong Khongnawang %A Michael Ibrahim %A Abilmansur Zhumabekov %A Daniel May %A Zhihu Yang %A Xiaozhuang Song %A Han Zhang %A Xiaoning Dong %A Shun Zheng %A Jiang Bian %B Proceedings of the NeurIPS 2022 Competitions Track %C Proceedings of Machine Learning Research %D 2022 %E Marco Ciccone %E Gustavo Stolovitzky %E Jacob Albrecht %F pmlr-v220-nweye23a %I PMLR %P 85--103 %U https://proceedings.mlr.press/v220/nweye23a.html %V 220 %X The shift to renewable power sources and building electrification to decarbonize existing and emerging building stock present unique challenges for the power grid. Building loads and flexible resources e.g. batteries must be adequately managed simultaneously to unlock the full flexibility potential and reduce costs for all stakeholders. Simple control algorithms based on expert knowledge e.g. RBC, as well as, advanced control algorithms e.g. MPC and RLC can be utilized to intelligently manage flexible resources. The CityLearn Challenge is an opportunity to compete in investigating the potential of AI and distributed control systems to tackle multiple problems within the built-environment. The CityLearn Challenge 2022 is the third of its kind with the overall objective of crowd-sourcing generalizable control policies that improve energy, cost and environmental objectives by taking advantage of batteries for load shifting in a CityLearn digital twin of a real-world grid-interactive neighborhood. Highlighted here are the uniqueness of this third edition, baseline and top solutions, and lessons learned for future editions.
APA
Nweye, K., Nagy, Z., Mohanty, S., Chakraborty, D., Sankaranarayanan, S., Hong, T., Dey, S., Henze, G., Drgona, J., Lin, F., Jiang, W., Zhang, H., Yi, Z., Zhang, J., Yang, C., Motoki, M., Khongnawang, S., Ibrahim, M., Zhumabekov, A., May, D., Yang, Z., Song, X., Zhang, H., Dong, X., Zheng, S. & Bian, J.. (2022). The CityLearn Challenge 2022: Overview, Results, and Lessons Learned. Proceedings of the NeurIPS 2022 Competitions Track, in Proceedings of Machine Learning Research 220:85-103 Available from https://proceedings.mlr.press/v220/nweye23a.html.

Related Material