Use of Support Vector Regression to Improve Computational Efficiency of Stochastic Time-Cost Trade-Off

Abstract

Stochastic time-cost trade-off has been a popular object of investigation in past decades because there are uncertain factors that can be considered when determining the appropriate trade-off between project completion time and cost. Previous studies, however, have implemented a double loop procedure, which performs optimization in the outer loop and simulation in the inner loop. The double loop procedure is ponderous because it requires an unacceptably long computation time (taking hours or days), even for a small to medium project. The present study proposes an integrated system that converts the double loop to single loops,thereby dramatically reducing computation time. This is done by incorporating a support vector regression model to obtain a decision function, which will be used to replace the time-consuming Monte Carlo simulation to evaluate the objective function values for individual solutions. With the objective function values, a multiobjective particle swarm optimization algorithm is developed to search for the Pareto front composed of nondominated solutions. It has been empirically shown that the proposed system significantly outperforms the conventional double loop procedure because the former can consistently generate a better Pareto front (with a larger hyperarea ratio) hundreds of times faster by using much less computation time. The Student’s