Cloud-based design analysis and optimization framework

Integration of analysis into early design phases in support of improved building performance has become increasingly important. It is considered a required response to demands on contemporary building design to meet environmental concerns. The goal is to assist designers in their decision making throughout the design of a building but with growing focus on the earlier phases in design during which design changes consume less effort than similar changes would in later design phases or during construction and occupation.Multi-disciplinary optimization has the potential of providing design teams with information about the potential trade-offs between various goals, some of which may be in conflict with each other. A commonly used class of optimization algorithms is the class of genetic algorithms which mimic the evolutionary process. For effective parallelization of the cascading processes occurring in the application of genetic algorithms in multi-disciplinary optimization we propose a cloud implementation and describe its architecture designed to handle the cascading tasks as efficiently as possible.Integration of analysis into early design phases in support of improved building performance has become increasingly important. It is considered a required response to demands on contemporary building design to meet environmental concerns. The goal is to assist designers in their decision making throughout the design of a building but with growing focus on the earlier phases in design during which design changes consume less effort than similar changes would in later design phases or during construction and occupation.Multi-disciplinary optimization has the potential of providing design teams with information about the potential trade-offs between various goals, some of which may be in conflict with each other. A commonly used class of optimization algorithms is the class of genetic algorithms which mimic the evolutionary process. For effective parallelization of the cascading processes occurring in the application of genetic algorithms in multi-disciplinary optimization we propose a cloud implementation and describe its architecture designed to handle the cascading tasks as efficiently as possible.P