[1]于军琪,王佳丽,赵安军,等.基于AP相似日选取与FISOA-RBF的短期负荷预测[J].深圳大学学报理工版,2021,38(3):315-323.[doi:10.3724/SP.J.1249.2021.03315]
 YU Junqi,WANG Jiali,ZHAO Anjun,et al.Short-term load forecasting based on AP similar day and improved SOA-RBF[J].Journal of Shenzhen University Science and Engineering,2021,38(3):315-323.[doi:10.3724/SP.J.1249.2021.03315]
点击复制

基于AP相似日选取与FISOA-RBF的短期负荷预测()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第38卷
期数:
2021年第3期
页码:
315-323
栏目:
电子与信息科学
出版日期:
2021-05-14

文章信息/Info

Title:
Short-term load forecasting based on AP similar day and improved SOA-RBF
文章编号:
202103015
作者:
于军琪王佳丽赵安军解云飞冉彤赵泽华
西安建筑科技大学建筑设备科学与工程学院,陕西西安 710055
Author(s):
YU Junqi WANG Jiali ZHAO Anjun XIE Yunfei RAN Tong and ZHAO Zehua
School of Building Services Science and Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, Shaanxi Province, P.R.China
关键词:
计算机神经网络 吸引子传播 相似日选取 人群搜索算法 径向基 建筑用电 短期负荷预测
Keywords:
computer neural network affinity propagation (AP) similar day method seeker optimization algorithm radial basis function electricity consumption of buildings short-term load forecasting
分类号:
TU852
DOI:
10.3724/SP.J.1249.2021.03315
文献标志码:
A
摘要:
为提高建筑电力负荷的预测精度,在考虑天气信息、日期类型等影响因素的基础上,提出一种基于吸引子传播(affinity propagation, AP)相似日选取和改进人群搜索算法-径向基神经网络(fusion improvement seeker optimization algorithm-radial basis function, FISOA-RBF)的建筑用电短期负荷预测模型.采用AP算法对短期电力负荷进行相似日选取,以克服外界环境对建筑电力负荷预测精度的影响;以RBF神经网络的网络参数为解对象,采用人群搜索算法(seeker optimization algorithm, SOA)进行参数寻优,并引入“融合改进策略”提高传统人群算法的寻优性能,以进一步提高RBF神经网络的预测精度和学习速度;根据FISOA 算法优化后的RBF神经网络对相似日数据进行训练,建立最优参数下的建筑短期电力负荷预测模型.预测结果表明,在相同数据集和气候特征条件下,与传统RBF、PSO-RBF和SOA-RBF预测模型相比,其平均预测绝对百分比误差分别降低了93.05%、83.60%和71.13%,平均预测速度分别提高了54.34%、39.25%和23.96%,表明FISOA-RBF模型在预测精度和预测速度上的表现更好.
Abstract:
In response to the requirements of high precision power load forecasting for large public buildings, considering the influencing factors of weather information and date type, a forecasting model for the short-term load of large public buildings based on affinity propagation (AP) similar day and the fusion improved seeker optimization algorithm-radial basis neural network (FISOA-RBF) is proposed.AP clustering similar day method is used to meet the demend of external environment.The structural parameters of RBF neural network are optimized by FISOA that introducing fusion improvement theory to further improve the prediction accuracy and learning speed of RBF neural network.Finally, Similar daily load data were trained by optimized FISOA-RBF to predict the short-term electrical load of buildings.To affirm the efficacy of the proposed model, same inputs are delivered in other three alternative models, named RBF, PSO-RBF and SOA-RBF. The results indicate that the proposed model outperforms the other models , the mean absolute percentage error(MAPE) is reduced by 93.05%、83.60% and 71.13%, and the average prediction speed is increased by 54.34%、39.25% and 23.96%, which proved AP-FISOA-RBF model in prediction accuracy and speed of prediction performance better.

相似文献/References:

[1]陈玉佳,姜波.基于小波神经网络的加工番茄产量预测模型[J].深圳大学学报理工版,2015,32(5):546.[doi:10.3724/SP.J.1249.2015.05546]
 Chen Yujia and Jiang Bo.A wavelet neural network model for processing tomato yield forecasting[J].Journal of Shenzhen University Science and Engineering,2015,32(3):546.[doi:10.3724/SP.J.1249.2015.05546]
[2]杨珺,佘佳丽,刘艳珍.基于深度置信网络的时间序列预测[J].深圳大学学报理工版,2019,36(6):718.[doi:10.3724/SP.J.1249.2019.06718]
 YANG Jun,SHE Jiali,and LIU Yanzheng.Time series prediction based on deep confidence networks[J].Journal of Shenzhen University Science and Engineering,2019,36(3):718.[doi:10.3724/SP.J.1249.2019.06718]
[3]马杰,王旭娇,马鹏飞,等.融合kd tree邻域查询的深度学习点云分类网络[J].深圳大学学报理工版,2020,37(1):79.[doi:10.3724/SP.J.1249.2020.01079]
 MA Jie,WANG Xujiao,MA Pengfei,et al.Deep learning network for point cloud classification based on k-dimensional tree neighbor query[J].Journal of Shenzhen University Science and Engineering,2020,37(3):79.[doi:10.3724/SP.J.1249.2020.01079]
[4]孙文赟,宋昱,陈昌盛.基于卷积-反卷积网络的正交人脸特征学习算法[J].深圳大学学报理工版,2020,37(5):474.[doi:10.3724/SP.J.1249.2020.05474]
 SUN Wenyun,SONG Yu,and CHEN Changsheng.An orthogonal facial feature learning method based on convolutional-deconvolutional network[J].Journal of Shenzhen University Science and Engineering,2020,37(3):474.[doi:10.3724/SP.J.1249.2020.05474]

更新日期/Last Update: 2021-05-30