论文部分内容阅读
以基于参数优化的支持向量机为建模手段来建立电力负荷模型,该算法可自动调整经验风险和VC维之间比重,并由此提高模型的泛化能力。参数优化时采用了结合网格搜索和模式搜索的组合寻优策略优化支持向量机负荷模型的3个参数,并且引入更加客观高效的交叉验证技术参与模型的训练和评价。算例中利用实测数据进行负荷动态建模,结果表明可得到精度和泛化能力都较高的负荷模型,在电力负荷建模方面具有广泛的应用价值。
The power load model is established by using the SVM based on parameter optimization as a modeling tool. The algorithm can automatically adjust the proportion between empirical risk and VC dimension, and thus improve the generalization ability of the model. The parameter optimization uses a combination of grid search and pattern search combinatorial optimization strategy to optimize the three parameters of support vector machine load model, and introduce more objective and efficient cross-validation technology to participate in the training and evaluation of the model. In the example, the load data are dynamically modeled by the measured data. The results show that the load model with high accuracy and generalization ability can be obtained, which has a wide range of application value in power load modeling.