An international conference connecting people
in CAD research, education and business
Bookmark and Share
Copyright (C) CAD Solutions, LLC. All rights reserved.
Proceedings of CAD'14, 2014, 67-69
A Hybrid Approach of Dynamic Programming and Genetic Algorithm for Multi-criteria Optimization on Sustainable Architecture Design

Mei-Chih Chang, Shen-Guan Shih, National Taiwan University of Science and Technology

Abstract. Sustainable building design is a growing global issue. One of its most important goals is energy efficiency over the entire life cycle of buildings. Design decisions for sustainable buildings are often concerned with a large set of decision variables and multiple criteria so complex that can hardly be resolved at once. Genetic Algorithms have been demonstrated to solve multi-objective optimization problems and consistently get close to the best. However, GA requires tens of thousands of simulations to converge to the global optimal, yet multi-criteria GA will take more. And it is widely acclaimed that the most important design decisions concerning building sustainability have to be made in the early design stages by the architect or building designer. In this stage, an architect also has to consider other architecture aspects, such as regulations, views, construction cost, and so on. Therefore, an architect has to comprise all diverse decisions to find the possible optimal solution. However, most of the researches for sustainable architecture design only concern related issues. Chen Kain Wee proposed a design method for multi-criteria optimization of low energy architecture by using GA in the early design stage. His research focuses on the exploration of holistic low exergy design on passive and active system with only energy related issue.

Keywords. Dynamic programming, genetic algorithm, sustainable architecture design

DOI: 10.14733/cadconfP.2014.67-69