|
| 基于IFOA-GRNN的电力系统短期负荷预测 |
| Short-term load forecasting of the power system based on the improved fruit fly optimization algorithm-generalized regression neural network (IFOA-GRNN) |
| 投稿时间：2016-12-06 |
| DOI：10.13259/j.cnki.eri.2020.03.006 |
| 中文关键词: 电力系统 短期负荷预测 果蝇优化算法 广义回归神经网络 |
| 英文关键词:power system short-term load forecasting fruit fly optimization algorithm generalized regression neural network |
| 基金项目:甘肃省自然科学基金资助项目（1506RJZA006）；甘肃省干旱生境作物学重点实验室资助项目（GSCS201215） |
|
| 摘要点击次数: 2382 |
| 全文下载次数: 2049 |
| 中文摘要: |
| 考虑到电网负荷与诸多因素有关，设计了一种带有温度、气象、日期类型的广义回归神经网络（GRNN）负荷预测模型。为了提高该模型的预测精度，提出了一种改进果蝇优化算法优化广义回归神经网络（IFOA-GRNN）的方法，即在利用果蝇优化算法（FOA）进入迭代寻优时，通过改进搜索距离优化该算法的性能和稳定性。利用改进的FOA优化GRNN的光滑参数，然后利用训练好的预测模型对甘肃省某地区进行了短期负荷预测，并与FOA-GRNN和误差反向传播神经网络(BPNN)模型结果进行了误差比较。结果表明， IFOA-GRNN具有较高的预测精度，能够满足电力系统短期负荷预测的要求。 |
| 英文摘要: |
| Considering that the load of power grid was related to many factors, a load forecasting model based on generalized regression neural network (GRNN) including temperature, weather and date type was developed. To improve the accuracy of prediction, an improved fruit fly optimization algorithm-generalized regression neural network (IFOA-GRNN) was proposed. The performance and stability of the algorithm were optimized by improving the search distance when FOA was used in the iterative optimization. The method used IFOA to optimize the smooth parameters of GRNN. A short-term load forecasting of a certain area in Gansu Province was carried out with the trained model. Its errors were compared with those of FOA-GRNN and BPNN. The results showed that IFOA-GRNN had high prediction accuracy and could meet the requirements of power system short-term load forecasting. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
