摘要
智能电网的一个重要特征是通过高精度的用电量预测进行电能智能调配,用电量信息的精确预测是电网智能化的关键指标。针对用电量数据非线性的特点,提出了一种基于粒子群优化的PSO-CV-SVR模型。该模型基于支持向量回归机原理,以粒子群算法和交叉验证的思想优化模型参数。将该模型应用于江苏省全社会用电量的预测分析,结果表明该模型优于BP-神经网络方法,提高了预测的精度。
An important feature of smart grid is the intelligent power distribution function based on electricity consump- tion forecasting with high accuracy. Accurate prediction of electricity consumption is the key indicator of power intelli- gence. The SVR model with Particle Swarm Optimization and Cross Validation is proposed according to the characteristics of the nonlinear electricity consumption data. In this model, PSO - CV method is used to the parameter determination. Then PSO - CV - SVR model is applied to the electricity consumption prediction of Jiangsn province. The result shows that the model is better than the ANNs method and improves the accuracy of the prediction.
出处
《科技管理研究》
CSSCI
北大核心
2013年第11期235-238,共4页
Science and Technology Management Research
基金
国家自然科学基金项目"不确定信息环境下基于大规模数据的趋势预测与智能决策方法研究"(71101041)
国家863智能电网重大项目"智能配用电信息及通信支持技术研究与开发"(2011AA05A116)
关键词
预测
支持向量回归
粒子群算法
交叉验证
prediction
Support vector regression （SVR）
Particle Swarm Optimization （PSO）
cross validation
