An evolutionary strategy enhanced with a local search technique for the space allocation problem in architecture, Part 1: Methodology

Abstract

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights • A new hybrid evolutionary computation methodology and mathematical model are presented. • The algorithm is tested in its validation and performance. • The proposed technique generates floor plans to be used in the early architectural design stage.

User-driven automation for optimal thermal-zone layout during space programming phases

“…The automation of architectural layout has been rekindled by the development in mathematical representation techniques of various space-creating constraints such as wall thickness, window locations, and so on (Rodrigues, Gaspar, and Gomes 2013). However, it should be noted that constraint-focused layout formulations may discourage practitioners in that it is unlikely to arrive optimized within a limited time frame, as high-quality results require a hard sets of constraints.…”

Automated approach for design generation and thermal assessment of alternative floor plans

“…The floor plans are generated by a hybrid evolutionary technique, which couples an ES and a SHC in a two-stage procedure [12]. The technique has been validated in several tests; among which one was the replication of an architect floor plan design [13].…”

“…It uses a hybrid evolutionary technique that couples an evolutionary strategy (ES) with a stochastic hill climbing (SHC) technique, named Evolutionary Program for the Space Allocation Problem (EPSAP) [12][13][14][15][16]. Due to the fact that alternative space arrangements limit the envelope design, it is important for the architect to be able to compare different floor plans from the early stages of design.…”

How reliable are geometry-based building indices as thermal performance indicators?

“…This is a trial-and-error iterative process, where alternative solutions are tested and compared. To assist the architects during this phase, the hybrid evolutionary algorithm EPSAP was developed [23][24][25]28], which couples an Evolutionary Strategy and a local search technique in a two-stage procedure. As the space allocation problem is a difficult and very computational intensive task, adaptive transformation operators were used to increase the efficiency of the algorithm and reduce computational time.…”

“…To test the effectiveness of these indices in the current buildings' performance requirements, large sets of floor plan designs were automatically generated using a hybrid evolutionary algorithm specifically developed to create alternative solutions, according to the user's preferences and requirements, named the Evolutionary Program for the Space Allocation Problem (EPSAP) [23][24][25]. The 3D simulation model is built with another algorithm, named Floor plan Performance Optimization Program (FPOP) [26,27], which performs the thermal assessment of each solution using a dynamic simulation program (EnergyPlus).…”