基于量子粒子群优化最小二乘支持向量机的变电站全寿命周期成本预测研究

变电站的规划设计与建设是电力工程建设的重点内容,快速的对变电站全寿命周期成本进行准确预测对变电站的建设具有指导意义.本文建立基于量子粒子群优化最小二乘支持向量机的变电站全寿命周期成本预测模型,将变电站全寿命周期内相关特征指标作为模型的输入,输出为变电站全寿命周期成本.通过仿真算例对比了QPSO优化LS-SVM,PSO优化LS-SVM,传统LS-SVM,BP神经网络4种预测模型的预测结果与相关性能指标.仿真结果表明,QPSO优化LS-SVM模型具有更好的预测精度,在变电站设计建设时能够快速准确的对全寿命周期成本进行预测评估,提高变电站建设的经济性.

Life Cycle Cost Prediction of Substation Based on QPPO and Least Squares Support Vector Machine

The planning, design and construction of substation is the key content of power engineering construction. The rapid prediction of the full life cycle cost of substation has guiding significance for the construction of substation. In this paper, a substation full life cycle cost prediction model based on quantum particle swarm optimization least squares support vector machine is established. The relevant characteristic index of the substation life cycle is used as the input of the model, and the output is the substation full life cycle cost. The simulation results are compared with the prediction results of QPSO optimized LS-SVM, PSO optimized LS-SVM, traditional LS-SVM, BP neural network four prediction models and related performance indicators. The simulation results show that the QPSO optimized LS-SVM model has better prediction accuracy, and can predict and evaluate the life cycle cost quickly and accurately during substation design and construction, and improve the economics of substation construction.