基于S变换和SVM分类器的电能质量分析的研究
|
摘要
在电能质量评价中,需要结合大数据分析方法进行电能质量的特征分析和数据挖掘,采用自适应融合方法进行电能质量大数据评价,提高电能评价的信息管理能力,提出一种基于S变换和SVM分类器的电能质量分析方法。采用信息传感器进行电能质量评价数据模糊采集,对采集的电能质量信息数据进行相似性特征提取,采用S变换进行电能质量数据信息流的时频分解,提取反映电能质量的关联信息特征量,对提取的特征量采用SVM分类器进行信息分类融合,在模糊聚类中心中实现电能质量信息大数据挖掘结合优化评价预测。仿真结果表明,采用该方法进行电能质量分析的评价准确性较高,收敛控制性能较好。
In power quality evaluation,it is necessary to combine big data's analysis method with power quality feature analysis and data mining,and adopt adaptive fusion method to evaluate power quality big data,so as to improve the ability of information management of power quality evaluation. This paper presents a power quality analysis method based on S transform and SVM classifier. The fuzzy acquisition of power quality evaluation data is carried out by using information sensor,and the similarity feature is extracted from the collected power quality information data. The S-transform is used to decompose the power quality data information stream in time and frequency,and the associated information characteristic quantity is extracted,and the feature quantity is classified and fused by SVM classifier. Big data mining of power quality information is realized in fuzzy clustering center and optimized evaluation and prediction is realized. The simulation results show that the evaluation accuracy and convergence control performance of power quality analysis based on this method are high.
In power quality evaluation,it is necessary to combine big data's analysis method with power quality feature analysis and data mining,and adopt adaptive fusion method to evaluate power quality big data,so as to improve the ability of information management of power quality evaluation. This paper presents a power quality analysis method based on S transform and SVM classifier. The fuzzy acquisition of power quality evaluation data is carried out by using information sensor,and the similarity feature is extracted from the collected power quality information data. The S-transform is used to decompose the power quality data information stream in time and frequency,and the associated information characteristic quantity is extracted,and the feature quantity is classified and fused by SVM classifier. Big data mining of power quality information is realized in fuzzy clustering center and optimized evaluation and prediction is realized. The simulation results show that the evaluation accuracy and convergence control performance of power quality analysis based on this method are high.
引文
[1]顾彬,郑关胜,王建东.增量和减量式标准支持向量机的分析[J].软件学报,2013,1:1-13.
[2]朱彦松,窦桂琴.一种基于多维度信任的WSN安全数据融合方法[J].武汉大学学报(理学版),2013,59(2):193-197.
[3] Joachims T,Finley T,Yu CNJ. Cutting-Plane training of structural SVMs[J]. Machine Learning,2009,77(1):27?59.
[4]叶林,任成,李智,等.风电场有功功率多目标分层递阶预测控制策略[J].中国电机工程学报,2016,36(23):6327-6336.
[5]张伯明,吴文传,郑太一,等.消纳大规模风电的多时间尺度协调的有功调度系统设计[J].电力系统自动化,2011,35(1):1-6.
[6]林俐,谢永俊,朱晨宸,等.基于优先顺序法的风电场限出力有功控制策略[J].电网技术,2013,37(4):960-966.
[7]王永旭,温渤婴.高压直流输电交流滤波器与交流系统最大并联阻抗的分析与计算[J].中国电机工程学报,2015,35(11):2703-2710.
[8]于晗,钟志勇,黄杰波,等.采用拉丁超立方采样的电力系统概率潮流计算方法[J].电力系统自动化,2009,33(21):32-36.
[9] HU S,DING Z,NI Q. Beamforming optimisation in energy harvesting cooperative full-duplex networks with self-energy recycling protocol[J]. IET Communications,2016,10(7):848-853.
[10] WEN Z,LIU X,BEAULIEU N C,et al. Joint source and relay beamforming design for full-duplex MIMO AF relay SWIPT systems[J]. IEEE Communications Letters,2016,20(2):320-323.
[11] PARK J J,MOON J H,KIM D I. Time-switching based inband full duplex wireless powered two-way relay[C]. URSI Asia-Pacific Radio Science Conference(URSI AP-RASC),2016:438-441.
[12]梁双,胡学浩,张东霞,等.基于随机模型的光伏发电置信容量评估方法[J].电力系统自动化,2012,36(13):32-37.
[13]衣晓蕾,彭思龙,栾世超.基于算子和局部正交约束的信号自适应分解方法[J].电子与信息学报,2015,37(11):2613-2620.
[14] ZHANG R,HO C K. MIMO broadcasting for simultaneous wireless information and power transfer[J]. IEEE Transactions on Wireless Communications,2013,12(5):1989-2001.
[15] WANG Y,SUN R,WANG X. Transceiver design to maximize the weighted sum secrecy rate in full-duplex SWIPT systems[J]. IEEE Signal Processing Letters,2016,23(6):883-887.
[2]朱彦松,窦桂琴.一种基于多维度信任的WSN安全数据融合方法[J].武汉大学学报(理学版),2013,59(2):193-197.
[3] Joachims T,Finley T,Yu CNJ. Cutting-Plane training of structural SVMs[J]. Machine Learning,2009,77(1):27?59.
[4]叶林,任成,李智,等.风电场有功功率多目标分层递阶预测控制策略[J].中国电机工程学报,2016,36(23):6327-6336.
[5]张伯明,吴文传,郑太一,等.消纳大规模风电的多时间尺度协调的有功调度系统设计[J].电力系统自动化,2011,35(1):1-6.
[6]林俐,谢永俊,朱晨宸,等.基于优先顺序法的风电场限出力有功控制策略[J].电网技术,2013,37(4):960-966.
[7]王永旭,温渤婴.高压直流输电交流滤波器与交流系统最大并联阻抗的分析与计算[J].中国电机工程学报,2015,35(11):2703-2710.
[8]于晗,钟志勇,黄杰波,等.采用拉丁超立方采样的电力系统概率潮流计算方法[J].电力系统自动化,2009,33(21):32-36.
[9] HU S,DING Z,NI Q. Beamforming optimisation in energy harvesting cooperative full-duplex networks with self-energy recycling protocol[J]. IET Communications,2016,10(7):848-853.
[10] WEN Z,LIU X,BEAULIEU N C,et al. Joint source and relay beamforming design for full-duplex MIMO AF relay SWIPT systems[J]. IEEE Communications Letters,2016,20(2):320-323.
[11] PARK J J,MOON J H,KIM D I. Time-switching based inband full duplex wireless powered two-way relay[C]. URSI Asia-Pacific Radio Science Conference(URSI AP-RASC),2016:438-441.
[12]梁双,胡学浩,张东霞,等.基于随机模型的光伏发电置信容量评估方法[J].电力系统自动化,2012,36(13):32-37.
[13]衣晓蕾,彭思龙,栾世超.基于算子和局部正交约束的信号自适应分解方法[J].电子与信息学报,2015,37(11):2613-2620.
[14] ZHANG R,HO C K. MIMO broadcasting for simultaneous wireless information and power transfer[J]. IEEE Transactions on Wireless Communications,2013,12(5):1989-2001.
[15] WANG Y,SUN R,WANG X. Transceiver design to maximize the weighted sum secrecy rate in full-duplex SWIPT systems[J]. IEEE Signal Processing Letters,2016,23(6):883-887.