基于BFA-Elman的电力负荷可靠性预测系统设计

Design of power load reliability forecast system based on BFA-Elman

针对现有负荷预测系统耗时长且精度较差等问题,文中设计了一种基于BFA-Elman的电力负荷可靠性的预测系统。利用细菌觅食算法(BFA)优化Elman网络模型的结构参数获得最佳的权值和阈值,同时避免Elman网络陷入局部最优。通过结合BFA和Elman网络构建BFA-Elman电力负荷预测模型,以实现可靠的预测。利用历史电力负荷对所提系统进行实验论证。结果表明,计算量对所提系统的性能影响较小,预测耗时不超过20 s且预测误差均值为0.41%,低于对比方法,从而能够有效提高发电设备的利用率与调度的经济性。

Aiming at the problems of long time consuming and poor accuracy of existing load forecasting system,a power load reliability forecasting system based on BFA-Elman is designed. Bacterial Foraging Algorithm(BFA) is used to optimize the structural parameters of Elman network model to obtain the optimal weight and threshold,and to avoid Elman network falling into local optimum. The BFA-Elman power load forecasting model is constructed by combining BFA and Elman network to realize reliable forecasting. The historical power load is used to demonstrate the performance of the proposed system. The results show that the amount of calculation has little effect on the performance of the proposed system,the prediction time is less than 20 s,and the average prediction error is 0.41%,which is lower than the comparison method,and can effectively improve the utilization rate of power generation equipment and the economy of dispatching.