基于大数据降维及优化神经网络的负荷预测研究  

Research on load forecasting based on big data dimensionality reduction and optimized neural network

在线阅读下载全文

作  者:孔庆泽 张添洋 高迪 张士然[1] 陈婧 KONG Qingze;ZHANG Tianyang;GAO Di;ZHANG Shiran;CHEN Jing(State Grid Jibei Electric Power Supply Co.,Ltd.,Chengde Power Supply Company,Chengde 067000,Hebei China;Hebei Minzu Normal University,Chengde 067000,Hebei China;State Grid Jibei Electric Power Company Limited,Beijing 100039,China;State Grid Info-Telecom Great Power Science and Technology Co.,Ltd.,Fuzhou 350003,Fujian China)

机构地区:[1]国网冀北电力有限公司承德供电公司,河北承德067000 [2]河北民族师范学院,河北承德067000 [3]国网冀北电力有限公司,北京100053 [4]国网信通亿力科技有限责任公司,福建福州350003

出  处:《粘接》2025年第5期182-185,共4页Adhesion

摘  要:为了提高电力负荷预测能力,设计出一套电力负荷数据智能监控系统,其硬件结构包括信息处理终端、网络通信和监控模型等,系统能够显著提高整个输电线路的运行能力。该研究设计以主控芯片为TMS320DM8168的嵌入式监控系统,通过改进BP神经网络模型,提高数据计算能力;通过基于XGboost融合模型,实现异常数据信息监控;通过在35 kV电力负荷数据路进行实验,发现设计监控线路运行数量为36条,监控清晰度为1 080 ppi,算法识别精度为97.3%,大大提高了监控能力。In order to improve the power load prediction ability,a set of power load data intelligent monitoring system was designed,and its hardware structure included information processing terminal,network communication and monitoring model,etc.,and the system could significantly improve the operation capacity of the entire transmission line.In this study,an embedded monitoring system with the main control chip as the TMS320DM8168 was designed,and the data computing capability was improved by improving the BP neural network model.Based on the XGboost fusion model,abnormal data information monitoring was realized.Through experiments on the 35 kV power load data path,it was found that the number of designed monitoring lines was 36,the monitoring clarity was 1080 ppi,and the algorithm recognition accuracy was 97.3%,which greatly improves the monitoring ability.

关 键 词:电力负荷 输电线路 嵌入式监控 BP神经网络模型 XGboost融合模型 

分 类 号:TP391.92[自动化与计算机技术—计算机应用技术] TM711[自动化与计算机技术—计算机科学与技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象