基于EMD-KELM-EKF与参数优选的用户侧微电网短期负荷预测方法

发布时间：2018-06-27 05:14

本文选题：微电网 + 短期负荷预测　；参考：《电网技术》2014年10期

【摘要】：短期负荷预测是微电网经济调度的重要组成部分,预测误差将直接影响运行经济性。相对于大电网环境,在用户侧微电网实施短期负荷预测的难度更高。提出了一种基于经验模态分解、扩展卡尔曼滤波及核函数极限学习机的组合短期负荷预测模型,通过经验模态分解对随机性强的微电网负荷时间序列逐级分解为多组固有模态函数分量,采用扩展卡尔曼滤波及核函数极限学习机2种存在典型差异的预测模型对不同性质的固有模态函数分量进行预测,并采用粒子群算法实现模型参数的优选。针对用户侧微电网的环境约束,提出了离线参数寻优、周期参数更新与在线预测相结合的实现模式。通过多种类型、容量的用户侧微电网算例分析,验证了模型预测精度、周期更新稳定性与计算效率。
[Abstract]:Short-term load forecasting is an important part of microgrid economic dispatch, and the forecasting error will directly affect the operation economy. Compared with the large power grid environment, it is more difficult to implement short-term load forecasting in the user side microgrid. A combined short-term load forecasting model based on empirical mode decomposition, extended Kalman filter and kernel function limit learning machine is proposed. Through empirical mode decomposition (EMD), the load time series with strong randomness are decomposed into multiple inherent modal function components. Extended Kalman filter and kernel function limit learning machine are used to predict the intrinsic modal function components with different properties, and particle swarm optimization (PSO) algorithm is used to optimize the parameters of the model. In view of the environmental constraints of the user-side microgrid, an off-line parameter optimization, periodic parameter updating and on-line prediction are proposed. The model prediction accuracy, periodic renewal stability and computational efficiency are verified by the numerical examples of various types of user-side microgrid.
【作者单位】：新能源电力系统国家重点实验室(华北电力大学);国家电网公司华北电力调控分中心;南方电网科学研究院;
【基金】：国家863高技术基金项目(2014AA052001)~~
【分类号】：TM715

【参考文献】