基于空间化粒子群的建筑空间利用率优化算法

Design of optimization algorithm for building space utilization based on spatialized particle swarm

针对传统建筑空间配置模型无法满足建筑空间特征优化的问题,文中提出了基于空间化粒子群的建筑空间利用率优化算法,以解决空间优化配置问题。首先针对空间优化配置问题,根据建筑空间特征进行粒子群算法的空间化改进,并采用符号编码方法进行空间单元的空间化编码;其次使用最大标准化法进行数据处理,归纳影响空间利用率的因素,并从经济效益、社会效益及生态效益三个方面给出建筑空间优化配置的目标函数;最终通过分析主从并行模型与点对点并行模型的优缺点,提出了链式并行结构。通过数据仿真测试实验,验证了链式并行模型具有较高适应度、收敛速度与较短的运行时间,性能要优于另外两种,表明文中所提出的优化算法具有良好的性能。

Aiming at the problem that the traditional model of building space allocation can not meet the optimization of building space characteristics,this paper proposes an optimization algorithm of building space utilization based on spatial particle swarm optimization to solve the problem of space optimal allocation.First of all,aiming at the problem of space optimization,according to the characteristics of building space,the particle swarm optimization algorithm is improved spatially,and the symbol coding method is used to encode the space unit spatially.Secondly,the maximum standardization method is used to process the data,and the factors affecting the space utilization rate are summarized,and the construction is given from three aspects of economic benefit,social benefit and ecological benefit.Finally,by analyzing the advantages and disadvantages of master⁃slave parallel model and point⁃to⁃point parallel model,a chain parallel structure is proposed.Through the data simulation test,it is verified that the chain parallel model has higher convergence speed and shorter running time,and the performance is better than the other two,which shows that the optimization algorithm proposed in this paper has good performance.