基于减法聚类模糊推理系统的短期负荷预测

采用减法聚类辅助模糊推理系统进行电力系统短期负荷预测。首先用减法聚类建立T-S模糊模型,然后通过调整聚类半径优选模糊规则数,以取得具有良好泛化性能的模型,最后利用梯度下降混合最小二乘算法精调参数。利用某局网负荷数据对ANFIS网络模型进行训练和检测,然后用于负荷预测,所得结果表明该算法鲁棒性好,抗干扰能力强,并且预测时间较ANFIS大大减少。

Short-term Load Forecasting Based on ANFIS with Subtractive Clustering

The application of Subtractive Clustering Fuzzy Inference System model to forecast short-term load is presented. Firstly, Subtractive clustering is used to generate a T-S fuzzy model. Secondly, the radius of a cluster center is adjusted to select optimal fuzzy rules, to acquire a fuzzy model with perfect generalization capability. Finally the parameters is fine-tuned by means of a hybrid gradient descent (GD) and least-squares estimation (LSE). This paper gives a certain network data to train and check the Adaptive Neuro-Fuzzy Interference System (ANFIS) with Subtractive Clustering neural network, then give the simulation example of modeling to forecast short-term load, and the results ware indicates that this strategy has good robust and anti-disturb ability, and it uses less training time than ANFIS.