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

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. rule-based control (RBC), as well as, advanced control algorithms e.g. model predictive control (MPC) and reinforcement learning control (RLC) can be utilized to intelligently manage flexible resources. The CityLearn Challenge is an opportunity to compete in investigating the potential of artificial intelligence (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.