Simulation of Urban Building Space Planning Optimization under Spatiotemporal Big Data
At present,urban building space planning involves multiple conflicting optimization objectives,such as building utilization rate,traffic congestion,and green coverage rate.However,due to mutual constraints and contradic-tions between these objectives,it is difficult to achieve better convergence speed and accuracy.Therefore,this paper researched an optimization algorithm for urban building space planning based on spatiotemporal big data.Firstly,this method constructed objective functions for various elements,such as urban building space planning cost,spatial com-pactness,suitability as well as environmental compatibility,and then integrated these elements to obtain an urban building space planning model.With the support of spatiotemporal big data,the method used a multi-objective opti-mization algorithm to optimize the model and the objective function of corresponding elements,thus obtaining more i-deal planning results.The following conclusions can be drawn from experimental results.The proposed algorithm has fast convergence and high accuracy of convergence.Meanwhile,the urban building space planning result obtained by the proposed algorithm has small deviations from the ideal result.
Spatio-temporal big dataUrban architectureSpatial planningOptimization algorithmPlanning model
NETL
NSTL
万方数据
