引用本文: | 谢文旺,孙云莲,黄雅鑫.基于改进随机森林的电力线通信优化算法研究[J].电力系统保护与控制,2019,47(11):22-29.[点击复制] |
XIE Wenwang,SUN Yunlian,HUANG Yaxin.Research on power line communication optimization algorithm based on improved random forest[J].Power System Protection and Control,2019,47(11):22-29[点击复制] |
|
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。 |
关键词: 电力线通信 OFDM 不平衡数据集 改进SMOTE算法 随机森林 |
DOI:10.7667/PSPC20191104 |
投稿时间:2018-07-05修订日期:2018-10-13 |
基金项目:南方电网公司科技项目资助(035300KK52150007) |
|
Research on power line communication optimization algorithm based on improved random forest |
XIE Wenwang,SUN Yunlian,HUANG Yaxin |
(School of Electric Engineering and Automation, Wuhan University, Wuhan 430072, China) |
Abstract: |
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. This work is supported by Science and Technology Project of China Southern Power Grid (No. 035300KK52150007). |
Key words: power line communication OFDM imbalanced dataset improved SMOTE algorithm random forest |