频域分解和深度学习算法在短期负荷及光伏功率预测中的应用
|
摘要
由于光伏发电和负荷的时变特性,光伏发电功率的消纳存在动态的过程,提升精细化的光伏及负荷预测技术对配电网的实时调度运行至关重要。该文在负荷和光伏发电精确预测的基础上,对光伏消纳能力进行分析。首先提出一种基于频域分解的短期负荷预测方法;其次,应用基于孤立森林和长短期记忆神经网络,预测短期光伏发电功率;然后,分析负荷特性及光伏发电特性;最后,结合消纳指标对安徽省某地级市国庆期间进行消纳能力分析。实验结果表明,所提出的短期负荷及光伏预测方法可达到理想的预测效果,消纳分析结果为该地区配电网火电机组调配提供参考意义。
Due to the time-varying characteristics of photovoltaic power generation and load, the photovoltaic power consumption is a dynamic process. The improvement and refinement of the photovoltaic and the load forecasting technology is critical to the distribution networks real-time dispatching. Based on the accurate prediction of load and photovoltaic power generation, this paper analyzed the photovoltaic consumption capacity. Firstly, a method of the short-term load forecasting was proposed, based on frequency domain decomposition. Secondly, the short-term photovoltaic power generation forecasting was applied via the isolation forest and the long short-term memory neural network algorithms. Then the load and photovoltaic power generation characteristics were analyzed. Finally, indicators of distributed PV capacity were proposed and calculated. The consumption capacity of a city in Anhui Province during the National Day was analyzed. Experimental results verify that the short-term load and photovoltaic forecasting methods can achieve the desired forecasting effect. The results of the consumption analysis provide a reference for the deployment of thermal power units in the distribution network.
Due to the time-varying characteristics of photovoltaic power generation and load, the photovoltaic power consumption is a dynamic process. The improvement and refinement of the photovoltaic and the load forecasting technology is critical to the distribution networks real-time dispatching. Based on the accurate prediction of load and photovoltaic power generation, this paper analyzed the photovoltaic consumption capacity. Firstly, a method of the short-term load forecasting was proposed, based on frequency domain decomposition. Secondly, the short-term photovoltaic power generation forecasting was applied via the isolation forest and the long short-term memory neural network algorithms. Then the load and photovoltaic power generation characteristics were analyzed. Finally, indicators of distributed PV capacity were proposed and calculated. The consumption capacity of a city in Anhui Province during the National Day was analyzed. Experimental results verify that the short-term load and photovoltaic forecasting methods can achieve the desired forecasting effect. The results of the consumption analysis provide a reference for the deployment of thermal power units in the distribution network.
引文
[1]丁明,王伟胜,王秀丽,等.大规模光伏发电对电力系统影响综述[J].中国电机工程学报,2014,34(1):1-14.Ding Ming,Wang Weisheng,Wang Xiuli,et al.A review on the effect of large-scale pv generation on power systems[J].Proceedings of the CSEE,2014,34(1):1-14(in Chinese).
[2]Mokhtari G,Ghosh A,Nourbakhsh G,et al.Smart robust resources control in lv network to deal with voltage rise issue[J].IEEE Transactions on Sustainable Energy,2013,4(4):1043-1050.
[3]Dubey A,Santoso S.On estimation and sensitivity analysis of distribution circuit’s photovoltaic hosting capacity[J].IEEE Transactions on Power Systems,2017,32(4):2779-2789.
[4]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.Ye Lin,Liu Peng.Combined model based on EMD-SVMfor short-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108(in Chinese).
[5]Ren Ye,Suganthan P N,Srikanth N.A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods[J].IEEE Transactions on Sustainable Energy,2015,6(1):236-244.
[6]曲正伟,张坤,王云静,等.基于PSO-OMP优化的WD-ASD超短期负荷预测[J].电工电能新技术,2017,36(12):39-45.Qu Zhengwei,Zhang Kun,Wang Yunjing,et al.Shortterm load forecasting based on WD-ASD optimized by PSO-OMP[J].Advanced Technology of Electrical Engineering and Energy,2017,36(12):39-45(in Chinese).
[7]邹红波,伏春林,喻圣.基于Akima-LMD和GRNN的短期负荷预测[J].电工电能新技术,2018,37(1):51-56.Zou Hongbo,Fu Chunlin,Yu Sheng.Short-term load forecasting based on Akima-LMD and GRNN[J].Advanced Technology of Electrical Engineering and Energy,2018,37(1):51-56(in Chinese).
[8]穆钢,侯凯元,杨右虹,等.负荷预报中负荷规律性评价方法的研究[J].中国电机工程学报,2001,21(10):96-101.Mu Gang,Hou Kaiyuan,Yang Youhong,et al.Studies on load regularity evaluating method for load forecasting[J].Proceedings of the CSEE,2001,21(10):96-101(in Chinese).
[9]温锦斌,王昕,李立学,等.基于频域分解的短期风电负荷预测[J].电工技术学报,2013,28(5):67-72.Wen Jinbin,Wang Xin,Li Lixue,et al.Short-term wind power load forecasting based on frequency domain decomposition[J].Transactions of China Electrotechnical Society,2013,28(5):67-72(in Chinese).
[10]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社,2007.Kang Chongqing,Xia Qing,Liu Mei.Power system load forecasting[M].Beijing:China Electric Power Press,2017(in Chinese).
[11]代倩,段善旭,蔡涛,等.基于天气类型聚类识别的光伏系统短期无辐照度发电预测模型研究[J].中国电机工程学报,2011,31(34):28-35.Dai Qian,Duan Shanxu,Cai Tao,et al.Short-term pv generation system forecasting model without irradiation based on weather type clustering[J].Proceedings of the CSEE,2011,31(34):28-35(in Chinese).
[12]阳霜,罗滇生,何洪英,等.基于EMD-LSSVM的光伏发电系统功率预测方法研究[J].太阳能学报,2016,37(6):1387-1395.Yang Shuang,Luo Diansheng,He Hongying,et al.Output power forecast of pv power system based on EMD-LSSVM model[J].Acta Energiae Solaris Sinica,2016,37(6):1387-1395(in Chinese).
[13]王继东,冉冉,宋智林.基于改进深度受限玻尔兹曼机算法的光伏发电短期功率概率预测[J].电力自动化设备,2018,38(5):43-49.Wang Jidong,Ran Ran,Song Zhilin.Probability forecast of short-term photovoltaic power generation based on improved depth restricted Boltzmann machine algorithm[J].Electric Power Automation Equipment,2018,38(5):43-49(in Chinese).
[14]赵波,肖传亮,徐琛,等.基于渗透率的区域配电网分布式光伏并网消纳能力分析[J].电力系统自动化,2017,41(21):105-111.Zhao Bo,Xiao Chuanliang,Xu Chen,et al.Penetration based accommodation capacity analysis on distributed photovoltaic connection in regional distribution network[J].Automation of Electric Power Systems,2017,41(20):105-111(in Chinese).
[15]温正.精通MATLAB智能算法[M].北京:清华大学出版社,2015.Wen Zheng.Proficient in MATLAB intelligent algorithm[M].Beijing:Tsinghua University Press,2015(in Chinese).
[16]Puggini L,Mc Loone S.An enhanced variable selection and Isolation Forest based methodology for anomaly detection with OES data[J].Engineering Applications of Artificial Intelligence,2016,67:126-135.
[17]吴潇雨,和敬涵,张沛,等.基于灰色投影改进随机森林算法的电力系统短期负荷预测[J].电力系统自动化,2015,39(12):50-55.Wu Xiaoyu,He Jinghan,Zhang Pei,et al.Power system short-term load forecasting based on improved random forest with grey relation projection[J].Automation of Electric Power Systems,2015,39(12):50-55(in Chinese).
[18]李光珍,刘文颖,云会周,等.母线负荷预测中样本数据预处理的新方法[J].电网技术,2010,34(2):149-154.Li Guangzhen,Liu Wenyin,Yun Huizhou,et al.A new data preprocessing method for bus load forecasting[J].Power System Technology,2010,34(2):149-154(in Chinese).
[19]Ugurlu U,Oksuz I,Ta?O.Electricity price forecasting using recurrent neural networks[J].Energies,2018,11(5):1255.
[20]贡晓旭,金强,王基,等.典型功能区分布式光伏接入对配电网建设改造的影响[J].中国电力,2016,49(3):166-171.Gong Xiaoxu,Jin Qiang,Wang Ji,et al.Effects of distributed pv connected to grid on distribution network constructions in typical functional zones[J].Electric Power,2016,49(3):166-171(in Chinese).
[21]Zhao Bo,Xu Zhicheng,Xu Chen,et al.Network partition-based zonal voltage control for distribution networks with distributed pv systems[J].IEEETransactions on Smart Grid,2018,9(5):4087-4098.
[2]Mokhtari G,Ghosh A,Nourbakhsh G,et al.Smart robust resources control in lv network to deal with voltage rise issue[J].IEEE Transactions on Sustainable Energy,2013,4(4):1043-1050.
[3]Dubey A,Santoso S.On estimation and sensitivity analysis of distribution circuit’s photovoltaic hosting capacity[J].IEEE Transactions on Power Systems,2017,32(4):2779-2789.
[4]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.Ye Lin,Liu Peng.Combined model based on EMD-SVMfor short-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108(in Chinese).
[5]Ren Ye,Suganthan P N,Srikanth N.A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods[J].IEEE Transactions on Sustainable Energy,2015,6(1):236-244.
[6]曲正伟,张坤,王云静,等.基于PSO-OMP优化的WD-ASD超短期负荷预测[J].电工电能新技术,2017,36(12):39-45.Qu Zhengwei,Zhang Kun,Wang Yunjing,et al.Shortterm load forecasting based on WD-ASD optimized by PSO-OMP[J].Advanced Technology of Electrical Engineering and Energy,2017,36(12):39-45(in Chinese).
[7]邹红波,伏春林,喻圣.基于Akima-LMD和GRNN的短期负荷预测[J].电工电能新技术,2018,37(1):51-56.Zou Hongbo,Fu Chunlin,Yu Sheng.Short-term load forecasting based on Akima-LMD and GRNN[J].Advanced Technology of Electrical Engineering and Energy,2018,37(1):51-56(in Chinese).
[8]穆钢,侯凯元,杨右虹,等.负荷预报中负荷规律性评价方法的研究[J].中国电机工程学报,2001,21(10):96-101.Mu Gang,Hou Kaiyuan,Yang Youhong,et al.Studies on load regularity evaluating method for load forecasting[J].Proceedings of the CSEE,2001,21(10):96-101(in Chinese).
[9]温锦斌,王昕,李立学,等.基于频域分解的短期风电负荷预测[J].电工技术学报,2013,28(5):67-72.Wen Jinbin,Wang Xin,Li Lixue,et al.Short-term wind power load forecasting based on frequency domain decomposition[J].Transactions of China Electrotechnical Society,2013,28(5):67-72(in Chinese).
[10]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社,2007.Kang Chongqing,Xia Qing,Liu Mei.Power system load forecasting[M].Beijing:China Electric Power Press,2017(in Chinese).
[11]代倩,段善旭,蔡涛,等.基于天气类型聚类识别的光伏系统短期无辐照度发电预测模型研究[J].中国电机工程学报,2011,31(34):28-35.Dai Qian,Duan Shanxu,Cai Tao,et al.Short-term pv generation system forecasting model without irradiation based on weather type clustering[J].Proceedings of the CSEE,2011,31(34):28-35(in Chinese).
[12]阳霜,罗滇生,何洪英,等.基于EMD-LSSVM的光伏发电系统功率预测方法研究[J].太阳能学报,2016,37(6):1387-1395.Yang Shuang,Luo Diansheng,He Hongying,et al.Output power forecast of pv power system based on EMD-LSSVM model[J].Acta Energiae Solaris Sinica,2016,37(6):1387-1395(in Chinese).
[13]王继东,冉冉,宋智林.基于改进深度受限玻尔兹曼机算法的光伏发电短期功率概率预测[J].电力自动化设备,2018,38(5):43-49.Wang Jidong,Ran Ran,Song Zhilin.Probability forecast of short-term photovoltaic power generation based on improved depth restricted Boltzmann machine algorithm[J].Electric Power Automation Equipment,2018,38(5):43-49(in Chinese).
[14]赵波,肖传亮,徐琛,等.基于渗透率的区域配电网分布式光伏并网消纳能力分析[J].电力系统自动化,2017,41(21):105-111.Zhao Bo,Xiao Chuanliang,Xu Chen,et al.Penetration based accommodation capacity analysis on distributed photovoltaic connection in regional distribution network[J].Automation of Electric Power Systems,2017,41(20):105-111(in Chinese).
[15]温正.精通MATLAB智能算法[M].北京:清华大学出版社,2015.Wen Zheng.Proficient in MATLAB intelligent algorithm[M].Beijing:Tsinghua University Press,2015(in Chinese).
[16]Puggini L,Mc Loone S.An enhanced variable selection and Isolation Forest based methodology for anomaly detection with OES data[J].Engineering Applications of Artificial Intelligence,2016,67:126-135.
[17]吴潇雨,和敬涵,张沛,等.基于灰色投影改进随机森林算法的电力系统短期负荷预测[J].电力系统自动化,2015,39(12):50-55.Wu Xiaoyu,He Jinghan,Zhang Pei,et al.Power system short-term load forecasting based on improved random forest with grey relation projection[J].Automation of Electric Power Systems,2015,39(12):50-55(in Chinese).
[18]李光珍,刘文颖,云会周,等.母线负荷预测中样本数据预处理的新方法[J].电网技术,2010,34(2):149-154.Li Guangzhen,Liu Wenyin,Yun Huizhou,et al.A new data preprocessing method for bus load forecasting[J].Power System Technology,2010,34(2):149-154(in Chinese).
[19]Ugurlu U,Oksuz I,Ta?O.Electricity price forecasting using recurrent neural networks[J].Energies,2018,11(5):1255.
[20]贡晓旭,金强,王基,等.典型功能区分布式光伏接入对配电网建设改造的影响[J].中国电力,2016,49(3):166-171.Gong Xiaoxu,Jin Qiang,Wang Ji,et al.Effects of distributed pv connected to grid on distribution network constructions in typical functional zones[J].Electric Power,2016,49(3):166-171(in Chinese).
[21]Zhao Bo,Xu Zhicheng,Xu Chen,et al.Network partition-based zonal voltage control for distribution networks with distributed pv systems[J].IEEETransactions on Smart Grid,2018,9(5):4087-4098.