Distribution area line loss prediction method based on support vector machine

The invention relates to a transformer area line loss prediction method based on a support vector machine, and the method comprises the following steps: 1, determining indexes which may influence the line loss according to the existing line loss rate data, and determining a training set and a test set which are needed by the support vector machine; step 2, constructing a transformer area line loss prediction model based on the training set data obtained in the step 1, and training the transformer area line loss prediction model to obtain a trained transformer area line loss prediction model; and step 3, obtaining a transformer area line loss prediction result based on the transformer area line loss prediction model trained in the step 2. The technical problems that a traditional method is large in calculation amount and poor in generalization can be solved. 本发明涉及一种基于支持向量机的台区线损预测方法，包括以下步骤：步骤1、根据现有的线损率数据确定可能影响线损的指标，并确定支持向量机所需的训练集和测试集；步骤2、基于步骤1得到的训练集数据，构建台区线损预测模型，并对其进行训练，得到训练好的台区线损预测模型；步骤3、基于步骤2训练好的台区线损预测模型，得到台区