基于状态参量的智能电表误差状态预测方法
|
摘要
在智能电表挂网运行的过程中,其计量性能会逐渐发生变化,可能影响电能计量的准确性和电力交易的公平性,因此,对其误差状态的管控具有重大意义。在运智能电表数量巨大,一般采用定期随机抽检的方法来获得部分表计的误差情况,但随机抽检覆盖面较小,存在抽检间隔,无法全面、及时地获取在运表计的计量误差,存在已超差表计仍长期挂网的风险。对此,提出了一种基于状态参量与计量性能退化的智能电表误差状态预测方法,基于智能电表的计量原理,研究了影响表计计量性能的关键因素,进而建立了一个计及温度、湿度、负荷、检定结果、时间累积影响的预测模型,借助BP神经网络算法,实现了历史数据下的网络训练和实时数据下的误差预测。最后,建立在线监测试点,开展实例应用,验证了该方法的有效性。
When smart meters are functioning in the power system, their measuring performances will gradually change, which will affect the accuracy of power measuring and the fairness of power trading. Thus, the control over error states of smart meters is of great significance. Since the quantity of smart meter is very large, the traditional method of casual inspection is adopted to acquire their error states. However, the small coverage and the interval of casual inspection make it impossible to know overall error states. Thus, there exists a risk that smart meters exceeding the error limit still serve for the power system. In this paper, a method for forecasting smart meters' error states is proposed based on state parameters and performance degeneration. Firstly, key factors in affecting measuring performances of smart meters are identified. Then, a forecasting model comprising temperature, humidity, load, verification results, time accumulative influence is established and the error forecasting is achieved with the method of nerve net algorithm. Finally, an application is conducted to verify the effeteness of the proposed method.
When smart meters are functioning in the power system, their measuring performances will gradually change, which will affect the accuracy of power measuring and the fairness of power trading. Thus, the control over error states of smart meters is of great significance. Since the quantity of smart meter is very large, the traditional method of casual inspection is adopted to acquire their error states. However, the small coverage and the interval of casual inspection make it impossible to know overall error states. Thus, there exists a risk that smart meters exceeding the error limit still serve for the power system. In this paper, a method for forecasting smart meters' error states is proposed based on state parameters and performance degeneration. Firstly, key factors in affecting measuring performances of smart meters are identified. Then, a forecasting model comprising temperature, humidity, load, verification results, time accumulative influence is established and the error forecasting is achieved with the method of nerve net algorithm. Finally, an application is conducted to verify the effeteness of the proposed method.
引文
[1] 陈信华,姜丽娟.电能计量装置分类及计量方式[J].电测与仪表,2004,41(1): 4-6.
[2] 刘慧敏,张慧贤.电能计量标准量值传递体系及传递精度控制的研究[J].电测与仪表,2010,47(9): 31-34.
[3] 胡青禾.我国电能表的现状、趋势与质量监督[J].电力设备,2005,6(7): 102-103.
[4] 陈树勇,宋书芳,李兰欣,等.智能电网技术综述[J].电网技术,2009,33(8):1-6
[5] 余贻鑫,栾文鹏.智能电网述评[J].中国电机工程学报,2009,29(34):1-7.
[6] 王思彤,周晖,袁瑞铭,等.智能电表的概念及应用[J].电网技术,2010,34(3):17-23.
[7] BORGES FAS, FERNANDES RAS, SILVA IN, et al. Feature extraction and power quality disturbances classification using smart meters signals[J]. IEEE Transactions on Industrial Informatics, 2017, 12(2):824-833.
[8] JAMALI S, BAHMANYAR A, BOMPARD E. Fault location method for distribution networks using smart meters[J]. Measurement, 2017(102):150-157.
[9] HSIAO YH. Household electricity demand forecast based on context information and user daily schedule analysis from meter data[J]. IEEE Transactions on Industrial Informatics,2017,11(1):33-43.
[10] LUAN W, PENG J, MARAS M, et al. Smart meter data analytics for distribution network connectivity verification[J]. IEEE Transactions on Smart Grid,2015,6(4):1964-1971.
[11] 陈会,孙洁,吴婷.分析外界环境对电能计量装置精准度的影响[J].通讯世界,2016(3):187-188.
[12] 殷鑫,陆以彪,宫游,等.温度影响下的智能电能表误差模型[J].电测与仪表,2017,54(8):85-88.
[13] 李黎,张登,谢龙君,等.采用关联规则综合分析和变权重系数的电力变压器状态评估方法[J].中国电机工程学报,2013,33(24):152-159.
[14] 廖瑞金,张镱议,黄飞龙,等.基于可拓分析法的电力变压器本体绝缘状态评估[J].高电压技术,2012,38(2):521-526.
[15] 郝建,廖瑞金,杨丽君,等.应用频域介电谱法的变压器油纸绝缘老化状态评估[J].电网技术,2011,35(7):187-193.
[16] 国连玉,李可军,梁永亮,等.基于灰色模糊综合评判的高压断路器状态评估[J].电力自动化设备,2014,34(11):161-167.
[17] 静恩波. 智能电网AMI中的智能电表系统设计[J].电测与仪表,2010,47(s2):36-39.
[18] 黄丽.BP神经网络学习算法的研究[D].重庆:重庆师范大学,2008.
[19] MIRCHANDANI G,CAO W. On hidden nodes for neural nets[J]. IEEE Transactions on Circuits & Systems,2002,3(5):661-664.
[2] 刘慧敏,张慧贤.电能计量标准量值传递体系及传递精度控制的研究[J].电测与仪表,2010,47(9): 31-34.
[3] 胡青禾.我国电能表的现状、趋势与质量监督[J].电力设备,2005,6(7): 102-103.
[4] 陈树勇,宋书芳,李兰欣,等.智能电网技术综述[J].电网技术,2009,33(8):1-6
[5] 余贻鑫,栾文鹏.智能电网述评[J].中国电机工程学报,2009,29(34):1-7.
[6] 王思彤,周晖,袁瑞铭,等.智能电表的概念及应用[J].电网技术,2010,34(3):17-23.
[7] BORGES FAS, FERNANDES RAS, SILVA IN, et al. Feature extraction and power quality disturbances classification using smart meters signals[J]. IEEE Transactions on Industrial Informatics, 2017, 12(2):824-833.
[8] JAMALI S, BAHMANYAR A, BOMPARD E. Fault location method for distribution networks using smart meters[J]. Measurement, 2017(102):150-157.
[9] HSIAO YH. Household electricity demand forecast based on context information and user daily schedule analysis from meter data[J]. IEEE Transactions on Industrial Informatics,2017,11(1):33-43.
[10] LUAN W, PENG J, MARAS M, et al. Smart meter data analytics for distribution network connectivity verification[J]. IEEE Transactions on Smart Grid,2015,6(4):1964-1971.
[11] 陈会,孙洁,吴婷.分析外界环境对电能计量装置精准度的影响[J].通讯世界,2016(3):187-188.
[12] 殷鑫,陆以彪,宫游,等.温度影响下的智能电能表误差模型[J].电测与仪表,2017,54(8):85-88.
[13] 李黎,张登,谢龙君,等.采用关联规则综合分析和变权重系数的电力变压器状态评估方法[J].中国电机工程学报,2013,33(24):152-159.
[14] 廖瑞金,张镱议,黄飞龙,等.基于可拓分析法的电力变压器本体绝缘状态评估[J].高电压技术,2012,38(2):521-526.
[15] 郝建,廖瑞金,杨丽君,等.应用频域介电谱法的变压器油纸绝缘老化状态评估[J].电网技术,2011,35(7):187-193.
[16] 国连玉,李可军,梁永亮,等.基于灰色模糊综合评判的高压断路器状态评估[J].电力自动化设备,2014,34(11):161-167.
[17] 静恩波. 智能电网AMI中的智能电表系统设计[J].电测与仪表,2010,47(s2):36-39.
[18] 黄丽.BP神经网络学习算法的研究[D].重庆:重庆师范大学,2008.
[19] MIRCHANDANI G,CAO W. On hidden nodes for neural nets[J]. IEEE Transactions on Circuits & Systems,2002,3(5):661-664.