Applications in CityLearn Gym Environment for Multi-Objective Control Benchmarking in Grid-Interactive Buildings and Districts

TL;DR

This paper introduces CityLearn, an open-source Gym environment designed for benchmarking multi-objective control algorithms in district-scale energy management, facilitating comparison of simple and advanced control strategies across diverse building scenarios.

Contribution

The paper presents CityLearn as a novel benchmarking platform that models district-level energy control with multi-agent capabilities and supports evaluation of various control algorithms.

Findings

CityLearn effectively models 17 diverse building control problems.

It enables benchmarking of rule-based and advanced control algorithms.

The platform assesses control resiliency and district-level objectives.

Abstract

It is challenging to coordinate multiple distributed energy resources in a single or multiple buildings to ensure efficient and flexible operation. Advanced control algorithms such as model predictive control and reinforcement learning control provide solutions to this problem by effectively managing a distribution of distributed energy resource control tasks while adapting to unique building characteristics, and cooperating towards improving multi-objective key performance indicator. Yet, a research gap for advanced control adoption is the ability to benchmark algorithm performance. CityLearn addresses this gap an open-source Gym environment for the easy implementation and benchmarking of simple rule-based control and advanced algorithms that has an advantage of modeling simplicity, multi-agent control, district-level objectives, and control resiliency assessment. Here we demonstrate the functionalities of CityLearn using 17 different building control problems that have varying complexity with respect to the number of controllable distributed energy resources in buildings, the simplicity of the control algorithm, the control objective, and district size.