基于改进随机森林的电力线通信优化算法研究
|
摘要
针对传统信道估计技术会占用频谱资源的缺陷,提出了一种基于改进随机森林的解映射优化算法。首先针对信源数据固有的不平衡性引入了改进SMOTE算法进行预处理,基于电力线信道特性确定了少数类数据的合成规则,并以解映射模块的子区间误码率作为评价指标进行性能分析。搭建了宽带电力线通信系统模型,以实际电表数据作为信源数据,在500 m的18径电力线信道模型下进行了仿真测试。实验结果表明,所提算法可以很好地弥补电表数据固有的不平衡性对随机森林性能的影响,极大地降低了子区间误码率的波动性。在各种信噪比环境下,引入改进随机森林算法均可以很好地优化解映射模块性能,提高宽带电力线通信质量,降低误码率。
Aiming at the defect that traditional channel estimation technology will occupy spectrum resources, an improved algorithm based on improved random forest is proposed. Firstly, the improved SMOTE algorithm is preprocessed according to the inherent imbalance of the source data. Based on the characteristics of the power line channel, the synthetic rules of the minority data are determined, and the performance of the subinterval error rate of the mapped module is analyzed as the evaluation index. A broadband power line communication system model is built, and the actual meter data is used as the source data to carry out the simulation test under 500 m 18 path power line channel model. The experimental results show that the algorithm can make up for the influence of the inherent imbalance of the meter data on the performance of the random forest, and greatly reduce the fluctuation of the bit error rate. In all kinds of signal to noise environment, the improved random forest algorithm can well optimize the performance of the module, improve the quality of broadband power line communication and reduce the bit error rate.
Aiming at the defect that traditional channel estimation technology will occupy spectrum resources, an improved algorithm based on improved random forest is proposed. Firstly, the improved SMOTE algorithm is preprocessed according to the inherent imbalance of the source data. Based on the characteristics of the power line channel, the synthetic rules of the minority data are determined, and the performance of the subinterval error rate of the mapped module is analyzed as the evaluation index. A broadband power line communication system model is built, and the actual meter data is used as the source data to carry out the simulation test under 500 m 18 path power line channel model. The experimental results show that the algorithm can make up for the influence of the inherent imbalance of the meter data on the performance of the random forest, and greatly reduce the fluctuation of the bit error rate. In all kinds of signal to noise environment, the improved random forest algorithm can well optimize the performance of the module, improve the quality of broadband power line communication and reduce the bit error rate.
引文
[1]何玉钧,刘毅,周生平.基于物元可拓模型的电力通信网风险评估[J].电力系统保护与控制,2017,45(14):64-69.HE Yujun,LIU Yi,ZHOU Shengping.Risk evaluation for electric power communication network based on matterelement extensible model[J].Power System Protection and Control,2017,45(14):64-69.
[2]田洪迅,王宏刚,万涛,等.基于BP神经网络的配电网可靠性关联因素灵敏度计算方法[J].电力系统保护与控制,2017,45(19):71-77.TIAN Hongxun,WANG Honggang,WAN Tao,et al.Amethodology of computing sensitivity of distribution system reliability with respect to driving factors based on a BP neural network[J].Power System Protection and Control,2017,45(19):71-77.
[3]彭显刚,李壮茂,邓小康,等.智能电网框架下的高级量测体系研究述评[J].广东电力,2017,30(12):7-14.PENG Xiangang,LI Zhuangmao,DENG Xiaokang,et al.Research on advanced metering infrastructure under smart grid framework[J].Guangdong Electric Power,2017,30(12):7-14.
[4]陈可,胡晓光.基于低压电力线正交频分复用系统虚载波改进信道估计算法[J].电力自动化设备,2013,33(4):135-141.CHEN Ke,HU Xiaoguang.Improved channel estimation algorithm based on virtual carriers of low-voltage power line OFDM system[J].Electric Power Automation Equipment,2013,33(4):135-141.
[5]唐英杰,董月军,任宏亮,等.基于时频域卡尔曼滤波的CO-OFDM系统相位噪声补偿算法[J].光学学报,2017,37(9):47-58.TANG Yingjie,DONG Yuejun,REN Hongliang,et al.Phase noise compensation algorithm based on Kalman filtering in time and frequency domains for CO-OFDMsystem[J].Acta Optica Sinica,2017,37(9):47-58.
[6]谷双春,张润生.一种基于改进Lloyd-Max的信道估计算法[J].无线电通信技术,2017,43(3):56-59.GU Shuangchun,ZHANG Runsheng.A new channel estimation method based on improved Lloyd-Max[J].Radio Communications Technology,2017,43(3):56-59.
[7]刘剑飞,石慧敏,曾祥烨,等.基于小波降噪和改进ISFA的CO-OFDM信道估计方法[J].中国激光,2015,42(12):145-151.LIU Jianfei,SHI Huimin,ZENG Xiangye,et al.Channel estimation method based on wavelet and improved ISFAfor CO-OFDM system[J].Chinese Journal of Lasers,2015,42(12):145-151.
[8]王守相,周凯,苏运.基于随机森林算法的台区合理线损率估计方法[J].电力自动化设备,2017,37(11):39-45.WANG Shouxiang,ZHOU Kai,SU Yun.Line loss rate estimation method of transformer district based on random forest algorithm[J].Electric Power Automation Equipment,2017,37(11):39-45.
[9]黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HUANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[10]曹正凤.随机森林算法优化研究[D].北京:首都经济贸易大学,2014.CAO Zhengfeng.Study on optimization of random forests algorithm[D].Beijing:Capital University of Economics and Business,2014.
[11]李军锋,王钦若,李敏.结合深度学习和随机森林的电力设备图像识别[J].高电压技术,2017,43(11):3705-3711.LI Junfeng,WANG Qinruo,LI Min.Electric equipment image recognition based on deep learning and random forest[J].High Voltage Engineering,2017,43(11):3705-3711.
[12]刘达,孙堃,黄晗.基于EEMD和随机森林的月度负荷预测[J].智慧电力,2018,46(6):12-18.LIU Da,SUN Kun,HUANG Han.Monthly load forecasting based on EEMD and random forest[J].Smart Power,2018,46(6):12-18.
[13]索超男,张慧,赵雄文.小波基在低压电力线信道有色背景噪声建模中的应用研究[J].电力系统保护与控制,2017,45(4):121-125.SUO Chaonan,ZHANG Hui,ZHAO Xiongwen.Research on the application of wavelet basis functions on modeling of colored background noise for low-voltage power line channels[J].Power System Protection and Control,2017,45(4):121-125.
[14]李松浓,胡晓锐,郑可,等.低压电力线载波通信信道衰减特性测量与分析[J].电力系统保护与控制,2018,46(4):99-106.LI Songnong,HU Xiaorui,ZHENG Ke,et al.Measure and research on attenuation characteristics of voltage power line communication channel[J].Power System Protection and Control,2018,46(4):99-106.
[15]曹旺斌,尹成群,谢志远,等.多输入多输出宽带电力线载波通信信道模型研究[J].中国电机工程学报,2017,37(4):1136-1142.CAO Wangbin,YIN Chengqun,XIE Zhiyuan,et al.Research on broadband MIMO power line communications model[J].Proceedings of the CSEE,2017,37(4):1136-1142.
[16]易琳,秦晓科,王刚,等.基于改进蚁群算法的电力巡检路径规划[J].广东电力,2018,31(3):115-119.YI Lin,QIN Xiaoke,WANG Gang,et al.Path planning for electric power patrol based on improved ant colony algorithms[J].Guangdong Electric Power,2018,31(3):115-119.
[17]张旭辉,张礼勇,梁宵.基于改进粒子群优化算法的电力线通信多径传输模型参数辨识[J].电网技术,2009,33(1):75-79.ZHANG Xuhui,ZHANG Liyong,LIANG Xiao.Parameter identification of multi-path transmission model for power line communication based on improved particle swarm optimization[J].Power System Technology,2009,33(1):75-79.
[18]WEISS G M.Mining with rarity:a unifying framework[J].SIGKDD Explorations,2004,6(1):7-19.
[19]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[20]黄建明,李晓明,瞿合祚,等.考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J].中国电机工程学报,2017,37(11):3099-3107,3365.HUANG Jianming,LI Xiaoming,QU Hezuo,et al.Method for fault type identification of transmission line considering wavelet singular information and unbalanced dataset[J].Proceedings of the CSEE,2017,37(11):3099-3107,3365.
[21]QUINLAN J R.Induction on decision tree[J].Machine Learning,1986,1(1):81-106.
[22]王宇恒.推荐系统中随机森林算法的优化与应用[D].杭州:浙江大学,2016.WANG Yuheng.Improvement and application of random forest algorithm in recommender systems[D].Hangzhou:Zhejiang University,2016.
[2]田洪迅,王宏刚,万涛,等.基于BP神经网络的配电网可靠性关联因素灵敏度计算方法[J].电力系统保护与控制,2017,45(19):71-77.TIAN Hongxun,WANG Honggang,WAN Tao,et al.Amethodology of computing sensitivity of distribution system reliability with respect to driving factors based on a BP neural network[J].Power System Protection and Control,2017,45(19):71-77.
[3]彭显刚,李壮茂,邓小康,等.智能电网框架下的高级量测体系研究述评[J].广东电力,2017,30(12):7-14.PENG Xiangang,LI Zhuangmao,DENG Xiaokang,et al.Research on advanced metering infrastructure under smart grid framework[J].Guangdong Electric Power,2017,30(12):7-14.
[4]陈可,胡晓光.基于低压电力线正交频分复用系统虚载波改进信道估计算法[J].电力自动化设备,2013,33(4):135-141.CHEN Ke,HU Xiaoguang.Improved channel estimation algorithm based on virtual carriers of low-voltage power line OFDM system[J].Electric Power Automation Equipment,2013,33(4):135-141.
[5]唐英杰,董月军,任宏亮,等.基于时频域卡尔曼滤波的CO-OFDM系统相位噪声补偿算法[J].光学学报,2017,37(9):47-58.TANG Yingjie,DONG Yuejun,REN Hongliang,et al.Phase noise compensation algorithm based on Kalman filtering in time and frequency domains for CO-OFDMsystem[J].Acta Optica Sinica,2017,37(9):47-58.
[6]谷双春,张润生.一种基于改进Lloyd-Max的信道估计算法[J].无线电通信技术,2017,43(3):56-59.GU Shuangchun,ZHANG Runsheng.A new channel estimation method based on improved Lloyd-Max[J].Radio Communications Technology,2017,43(3):56-59.
[7]刘剑飞,石慧敏,曾祥烨,等.基于小波降噪和改进ISFA的CO-OFDM信道估计方法[J].中国激光,2015,42(12):145-151.LIU Jianfei,SHI Huimin,ZENG Xiangye,et al.Channel estimation method based on wavelet and improved ISFAfor CO-OFDM system[J].Chinese Journal of Lasers,2015,42(12):145-151.
[8]王守相,周凯,苏运.基于随机森林算法的台区合理线损率估计方法[J].电力自动化设备,2017,37(11):39-45.WANG Shouxiang,ZHOU Kai,SU Yun.Line loss rate estimation method of transformer district based on random forest algorithm[J].Electric Power Automation Equipment,2017,37(11):39-45.
[9]黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HUANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[10]曹正凤.随机森林算法优化研究[D].北京:首都经济贸易大学,2014.CAO Zhengfeng.Study on optimization of random forests algorithm[D].Beijing:Capital University of Economics and Business,2014.
[11]李军锋,王钦若,李敏.结合深度学习和随机森林的电力设备图像识别[J].高电压技术,2017,43(11):3705-3711.LI Junfeng,WANG Qinruo,LI Min.Electric equipment image recognition based on deep learning and random forest[J].High Voltage Engineering,2017,43(11):3705-3711.
[12]刘达,孙堃,黄晗.基于EEMD和随机森林的月度负荷预测[J].智慧电力,2018,46(6):12-18.LIU Da,SUN Kun,HUANG Han.Monthly load forecasting based on EEMD and random forest[J].Smart Power,2018,46(6):12-18.
[13]索超男,张慧,赵雄文.小波基在低压电力线信道有色背景噪声建模中的应用研究[J].电力系统保护与控制,2017,45(4):121-125.SUO Chaonan,ZHANG Hui,ZHAO Xiongwen.Research on the application of wavelet basis functions on modeling of colored background noise for low-voltage power line channels[J].Power System Protection and Control,2017,45(4):121-125.
[14]李松浓,胡晓锐,郑可,等.低压电力线载波通信信道衰减特性测量与分析[J].电力系统保护与控制,2018,46(4):99-106.LI Songnong,HU Xiaorui,ZHENG Ke,et al.Measure and research on attenuation characteristics of voltage power line communication channel[J].Power System Protection and Control,2018,46(4):99-106.
[15]曹旺斌,尹成群,谢志远,等.多输入多输出宽带电力线载波通信信道模型研究[J].中国电机工程学报,2017,37(4):1136-1142.CAO Wangbin,YIN Chengqun,XIE Zhiyuan,et al.Research on broadband MIMO power line communications model[J].Proceedings of the CSEE,2017,37(4):1136-1142.
[16]易琳,秦晓科,王刚,等.基于改进蚁群算法的电力巡检路径规划[J].广东电力,2018,31(3):115-119.YI Lin,QIN Xiaoke,WANG Gang,et al.Path planning for electric power patrol based on improved ant colony algorithms[J].Guangdong Electric Power,2018,31(3):115-119.
[17]张旭辉,张礼勇,梁宵.基于改进粒子群优化算法的电力线通信多径传输模型参数辨识[J].电网技术,2009,33(1):75-79.ZHANG Xuhui,ZHANG Liyong,LIANG Xiao.Parameter identification of multi-path transmission model for power line communication based on improved particle swarm optimization[J].Power System Technology,2009,33(1):75-79.
[18]WEISS G M.Mining with rarity:a unifying framework[J].SIGKDD Explorations,2004,6(1):7-19.
[19]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[20]黄建明,李晓明,瞿合祚,等.考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J].中国电机工程学报,2017,37(11):3099-3107,3365.HUANG Jianming,LI Xiaoming,QU Hezuo,et al.Method for fault type identification of transmission line considering wavelet singular information and unbalanced dataset[J].Proceedings of the CSEE,2017,37(11):3099-3107,3365.
[21]QUINLAN J R.Induction on decision tree[J].Machine Learning,1986,1(1):81-106.
[22]王宇恒.推荐系统中随机森林算法的优化与应用[D].杭州:浙江大学,2016.WANG Yuheng.Improvement and application of random forest algorithm in recommender systems[D].Hangzhou:Zhejiang University,2016.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |