Multi-Objective Optimization for Zero-Energy Urban Design in China: A Benchmark

Thomas Wortmann, Jonathan Natanian

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Environmental simulation supports the design of more sustainable, zero-energy neighborhoods, especially when leveraged with multi-objective optimization. This study explores the tradeoff between urban density and energy balance---specifically, monthly load match between energy usage and generation---in terms of courtyard, slab, and tower typologies for a hypothetical neighborhood in Shanghai. Using this problem as a multi-objective optimization benchmark, the study compares the evolutionary algorithms HypE and NSGA-II with RBFMOpt, a novel, machine learning-related algorithm. The study concludes that RBFMOpt finds slightly better Pareto fronts and is much more robust, and that courtyard typologies are the most efficient for both low- and high-density neighborhoods.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 11th Annual Symposium on Simulation for Architecture and Urban Design
Number of pages8
StatePublished - 2020
Externally publishedYes

Publication series

NameSimAUD '20
PublisherSociety for Computer Simulation International


  • model-based optimization
  • monthly load match
  • multi-objective optimization benchmark
  • zero-energy urban design

Cite this