Join the Conversation
30 September 2020
The CityLearn Challenge — Multi-agent reinforcement learning for community-scale energy management
Periods of high demand for electricity raise electricity prices and the overall cost of electric power provision. Flattening, smoothing, and reducing electrical demand reduces operational and capital costs of electricity generation, transmission, and distribution. Demand response is the coordination of electricity consuming agents (i.e. buildings) in order to reshape electrical demand to achieve grid benefits.
Reinforcement learning (RL) has gained popularity in the research community as a model-free and adaptive control paradigm for the built environment. RL has the potential to enable inexpensive plug-and-play building controllers that can be easily implemented without necessitating potentially expensive control models (unlike model predictive control), and to coordinate multiple buildings for demand response and load shaping. Despite its potential, there are still many open questions regarding its plug-and-play capabilities, performance characteristics and limitations, safety of operation, and learning speed.
The aim of this Special Issue is to explore how reinforcement learning algorithms for adaptive control can be used in a portfolio of buildings to coordinate their building energy system behavior to achieve multiple objectives, e.g., peak shaving or load shifting, in pursuit of grid-interactive and efficient building operation.
Topics of interest
This topical issue on “The CityLearn Challenge — Multi-agent reinforcement learning for community-scale energy management” addresses the following areas:
- Application of the CityLearn OpenAI Gym environment (citylearn.net) to study multi-agent coordination, in particular submissions to the 2019 CityLearn Challenge
- Modeling and simulation of building energy systems to integrate with CityLearn (distributed energy sources, district scale storage and generation, etc)
- Novel reinforcement learning-based control algorithms, with emphasis on applications suitable for the built environment (both residential and commercial)
- Computational and simulation frameworks to study RL in the built environment
- Adaptive and coordinated building control applications at the community scale
- Uncertainty and sensitivity analysis
Other related topics are welcome, authors should generally consider the aims and scope of JBPS which can be found here: https://www.tandfonline.com/action/journalInformation?show=aimsScope&journalCode=tbps20
Looking to Publish your Research?
We aim to make publishing with Taylor & Francis a rewarding experience for all our authors. Please visit our Author Services website for more information and guidance, and do contact us if there is anything we can help with!
Abstract (500 words): August 15th, 2020
Submission deadline of full papers: September 30th, 2020
Completion of first-round review: November 30th, 2020
Submission deadline of revised papers: January 15th, 2021
Final notification: February 15th, 2021
Issue published: March 15th, 2021
Only original manuscripts can be submitted, according to the ‘Guide for Authors’ published on the JBPS website https://mc.manuscriptcentral.com/tbps. As regards the online submission system of JBPS, the authors are invited to follow the link “Submit your Paper”, located in the main page of the Journal website.
Please mention the name of the Special Issue in your cover letter. All manuscripts will be peer-reviewed in accordance with the established policies and procedures of the journal. The final papers will be selected for publication depending on the results of the peer review process and the reviews of the Guest Editors.
View the latest tweets from tandfstem