CityLearn v2: Energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities

TL;DR

CityLearn v2 extends CityLearn v1 by providing a stand-alone simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create grid-interactive communities for resilient, multi-agent, and objective control of distributed energy resources with dynamic occupant feedback.

Abstract

As more distributed energy resources become part of the demand-side infrastructure, it is important to quantify the energy flexibility they provide on a community scale, particularly to understand the impact of geographic, climatic, and occupant behavioral differences on their effectiveness, as well as identify the best control strategies to accelerate their real-world adoption. CityLearn provides an environment for benchmarking simple and advanced distributed energy resource control algorithms including rule-based, model-predictive, and reinforcement learning control. CityLearn v2 presented here extends CityLearn v1 by providing a simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create virtual grid-interactive communities for resilient, multi-agent distributed energy resources and objective control with dynamic occupant feedback. This work details the v2 environment design and provides application examples that utilize reinforcement learning to manage battery energy storage system charging/discharging cycles, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

Figures (12)

• Figure 1: CityLearn building model including electricity sources that power controllable including electric devices and , used to satisfy thermal and electrical loads as well as provide the grid with energy flexibility. A distinction is made between environment and control aspects of a building to show the transfer of actions from the control agent and reception of measurable observations by the control agent that quantifies the building's states.
• Figure 2: Framework for designing virtual grid-interactive communities in CityLearn from the eulp for the United States Building Stock dataset (adapted from bs2023_1404).
• Figure 3: Control summary in CityLearn.
• Figure 4: Integration of rbc, mpc, and rlc with CityLearn.
• Figure 5: Cost ($) and emissions (kgCO2e) results in simbuild2024_2283 from either or of , - system or both when the control objective is to reduce cost or emission. The dashed red line shows the cost for a baseline scenario and the dotted blue line shows the cost for a baseline scenario but with solar generation to augment electricity from the grid.