基于模糊信息粒化和长短期记忆网络的短期风速预测
|
摘要
针对风速点预测无法对预测结果进行风险评估、区间预测难以满足电网精细化要求,以及现有静态预测方法难以描述风速序列长期相关性的现象,提出一种基于模糊信息粒化(Fuzzy Information Granulation,FIG)和长短期记忆(Long Short-Term Memory,LSTM)网络的动态预测模型。该方法先对风速序列进行模糊信息粒化,提取出粒化后数据的最大值(区间上界)、最小值(区间下界)和平均值。其次采用ADAM算法优化的LSTM网络对各粒化数据进行动态建模,得到能描述风速波动性的区间预测结果和点预测结果。算列表明,所提动态模型的预测效果比其它基本模型的预测效果更好。
In view of the fact that the deterministic wind speed forecasting cannot assess the risk of the prediction results and the long-term correlation of wind speed sequences cannot be described by the existing static prediction methods,a dynamic prediction model based on fuzzy information granulation( FIG) and long short-term memory( LSTM) network is proposed in this paper. In this method,the wind speed sequence is firstly granulated by fuzzy information,and the maximum value( interval upper bound),average value and the minimum value( interval lower bound) of the data after granulation are extracted. Secondly,the granulated data are respectively dynamically modeled through the LSTM optimized by ADAM algorithm to obtain interval forecasting results and point forecasting results which can describe the wind speed volatility. Calculations show that the proposed dynamic model prediction is better than other basic models.
In view of the fact that the deterministic wind speed forecasting cannot assess the risk of the prediction results and the long-term correlation of wind speed sequences cannot be described by the existing static prediction methods,a dynamic prediction model based on fuzzy information granulation( FIG) and long short-term memory( LSTM) network is proposed in this paper. In this method,the wind speed sequence is firstly granulated by fuzzy information,and the maximum value( interval upper bound),average value and the minimum value( interval lower bound) of the data after granulation are extracted. Secondly,the granulated data are respectively dynamically modeled through the LSTM optimized by ADAM algorithm to obtain interval forecasting results and point forecasting results which can describe the wind speed volatility. Calculations show that the proposed dynamic model prediction is better than other basic models.
引文
[1]张国荣,陈夏冉.能源互联网未来发展综述[J/OL].电力自动化设备,2017,37(1):1-7.
[2]李丹,刘俊勇,刘友波,等.考虑风储参与的电力市场联动博弈分析[J].电网技术,2015,39(4):1001-1007.Li Dan,Liu Junyong,Liu Youbo,et al. Analysis on electricity market linkage game considering participation of wind power and energy storage[J]. Power System Technology,2015,39(4):1001-1007.
[3]陈盼,陈皓勇,叶荣,等.基于小波包和支持向量回归的风速预测[J].电网技术,2011,35(5):177-182.Chen Pan,Chen Haoyong,Ye Rong,et al. Wind speed forecasting based on combination of wavelet packet analysis with support vector regression[J]. Power System Technology,2011,35(5):177-182.
[4] Kavasseri RG,Seetharaman K. Day-ahead wind speed forecasting using-ARIMA models[J]. Renewable Energy, 2009, 34(5):1388-1393.
[5]孙国强,卫志农,翟玮星.基于RVM与ARMA误差校正的短期风速预测[J].电工技术学报,2012,27(8):187-193.Sun Guoqiang,Wei Zhinong,Zhai Weixing. Short term wind speed forecasting based on RVM and ARMA error correcting[J]. Transactions of China Electrotechnical Society,2012,27(8):187-193.
[6]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41.Yang Xiyun,Sun Baojun,Zhang Xinfang,et al. Short-term wind speed forecasting based on support vector machine with similar data[J]. Proceedings of the CSEE,2012,32(4):35-41.
[7]王晓兰,王明伟.基于小波分解和最小二乘支持向量机的短期风速预测[J].电网技术,2010,(1):179-184.Wang Xiaolan,Wang Mingwei. Short-term wind speed forecasting based on wavelet decomposition and least square support vector machine[J].Power System Technology,2010,34(1):179-184.
[8]王为国,窦震海,等.基于模糊理论和逆推算法改进均值生成函数的短期风速预测研究[J].电测与仪表,2018,55(13):19-24.Wang Weiguo,Dou Zhenhai,et al. Research on short-term wind speed prediction based on improved mean generating function with fuzzy theory and back-stepping algorithm[J]. Electrical Measurement&Instrumentation,2018,55(13):19-24.
[9] Yin H,Dong Z,Chen Y,et al. An effective secondarydecompsition approach for wind power forecasting using extreme learning machine trained by crisscross optimization[J]. Energy Conversion&Management,2017,150:108-121.
[10]朱乔木,李弘毅,等.基于长短期记忆网络的风电场发电功率超短期预测[J].电网技术,2017,(12):3797-3802.Zhu Qiaomu,Li Hongyi,et al. Short-Term Wind Power Forecasting Based on LSTM[J]. Power System Technology, 2017,(12):3797-3802.
[11]Xu S,Niu R. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area,China[J]. Computers&Geosciences,2018,111:87-96.
[12]Jain L C,Medsker L R. Recurrent Neural Networks:Design and Applications[C] Int. Joint Conference on Neural Networks. 1999:1537-1541.
[13]Pascanu R,Mikolov T,Bengio Y. On the difficulty of training Recurrent Neural Networks[J]. 2012,52(3):III-1310.
[14]Tian Y,Pan L. Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network[C]//IEEE International Conference on Smart City/socialcom/sustaincom. IEEE,2015:153-158.
[15]Li X,Peng L,Yao X,et al. Long short-term memory neural network for air pollutant concentration predictions:Method development and evaluation[J]. Environmental Pollution,2017,231(Pt 1):997-1004.
[16]Xu S,Niu R. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area,China[J]. Computers&Geosciences,2018,111:87-96.
[17]方必武,刘涤尘,王波,等.基于小波变换和改进萤火虫算法优化LSSVM的短期风速预测[J].电力系统保护与控制,2016,44(8):37-43.Fang Biwu,Liu Dichen,Wang Bo,et al. Short-term wind speed forecasting based on WD-CFA-LSSVM model[J]. Power System Protection and Control,2016,44(8):37-43.
[18]王晓兰,王明伟.基于小波分解和最小二乘支持向量机的短期风速预测[J].电网技术,2010,34(1):179-184.Wang Xiaolan,Wang Mingwei. Short-term wind speed forecasting based on wavelet decomposition and least square support vector machine[J].Power System Technology,2010,34(1):179-184.
[19]张亚超,刘开培,等.基于聚类经验模态分解样本熵和优化极限学习机的风电功率多步区间预测[J].电网技术,2016,40(7):2045-2051.Zhang Yachao,Liu Kaipei,et al. Wind Power Multi-Step Interval Prediction Based on Ensemble Empirical Mode Decomposition Sample Entropy and Optimized Extreme Learning Machine[J]. Power System Technology,2016,40(7):2045-2051.
[20]陈杰,沈艳霞,陆欣,等.一种风电功率概率区间多目标智能优化预测方法[J].电网技术,2016,40(8):2281-2287.Chen Jie,Shen Yanxia,Lu Xin,et al. An intelligent multi-objective optimized method for wind power prediction intervals[J]. Power System Technology,2016,40(10):2758-2765.
[21]范磊,卫志农,等.基于变分模态分解和蝙蝠算法-相关向量机的短期风速区间预测[J].电力自动化设备,2017,37(1):93-100.Fan Lei,Wei Zhinong,et al. Short-term wind speed interval prediction based on VMD and BA-RVM algorithm[J]. Electric Power Automation Equipment,2017,37(1):93-100.
[22]王贺,胡志坚,仉梦林.基于模糊信息粒化和最小二乘支持向量机的风电功率波动范围组合预测模型[J].电工技术学报,2014,29(12):218-224.Wang He,Hu Zhijian,Zhang Menglin. A combined forecasting model for range of wind power fluctuation based on fuzzy information granulation and least squares support vector machine[J]. Transactions of China Electrotechnical Society,2014,29(12):218-224.
[23]Kingma D P,Ba J. Adam:A Method for Stochastic Optimization[J].Computer Science,2014.
[24]Lu W,Pedrycz W,Liu X,et al. The modeling of time series based on fuzzy information granules[J]. Expert Systems with Applications,2014,41(8):3799-3808.
[25]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015,43(2):26-32.Wang Kai,Guan Shaoqing,Wang Lingxiang,et al. A combined forecasting model for wind power prediction based on fuzzy information granulation and least squares support vector machine[J]. Power System Protection and Control,2015,43(2):26-32.
[26]Ma X,Tao Z,Wang Y,et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J].Transportation Research Part C Emerging Technologies,2015,54:187-197.
[27]Bengio Y,Simard P,Frasconi P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks,1994,5(2):157.
[28][Bottou L. Large-Scale Machine Learning with Stochastic Gradient Descent[J]. 2010:177-186.
[29]Zeiler M D. ADADELTA:An Adaptive Learning Rate Method[J].Computer Science,2012.
[2]李丹,刘俊勇,刘友波,等.考虑风储参与的电力市场联动博弈分析[J].电网技术,2015,39(4):1001-1007.Li Dan,Liu Junyong,Liu Youbo,et al. Analysis on electricity market linkage game considering participation of wind power and energy storage[J]. Power System Technology,2015,39(4):1001-1007.
[3]陈盼,陈皓勇,叶荣,等.基于小波包和支持向量回归的风速预测[J].电网技术,2011,35(5):177-182.Chen Pan,Chen Haoyong,Ye Rong,et al. Wind speed forecasting based on combination of wavelet packet analysis with support vector regression[J]. Power System Technology,2011,35(5):177-182.
[4] Kavasseri RG,Seetharaman K. Day-ahead wind speed forecasting using-ARIMA models[J]. Renewable Energy, 2009, 34(5):1388-1393.
[5]孙国强,卫志农,翟玮星.基于RVM与ARMA误差校正的短期风速预测[J].电工技术学报,2012,27(8):187-193.Sun Guoqiang,Wei Zhinong,Zhai Weixing. Short term wind speed forecasting based on RVM and ARMA error correcting[J]. Transactions of China Electrotechnical Society,2012,27(8):187-193.
[6]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41.Yang Xiyun,Sun Baojun,Zhang Xinfang,et al. Short-term wind speed forecasting based on support vector machine with similar data[J]. Proceedings of the CSEE,2012,32(4):35-41.
[7]王晓兰,王明伟.基于小波分解和最小二乘支持向量机的短期风速预测[J].电网技术,2010,(1):179-184.Wang Xiaolan,Wang Mingwei. Short-term wind speed forecasting based on wavelet decomposition and least square support vector machine[J].Power System Technology,2010,34(1):179-184.
[8]王为国,窦震海,等.基于模糊理论和逆推算法改进均值生成函数的短期风速预测研究[J].电测与仪表,2018,55(13):19-24.Wang Weiguo,Dou Zhenhai,et al. Research on short-term wind speed prediction based on improved mean generating function with fuzzy theory and back-stepping algorithm[J]. Electrical Measurement&Instrumentation,2018,55(13):19-24.
[9] Yin H,Dong Z,Chen Y,et al. An effective secondarydecompsition approach for wind power forecasting using extreme learning machine trained by crisscross optimization[J]. Energy Conversion&Management,2017,150:108-121.
[10]朱乔木,李弘毅,等.基于长短期记忆网络的风电场发电功率超短期预测[J].电网技术,2017,(12):3797-3802.Zhu Qiaomu,Li Hongyi,et al. Short-Term Wind Power Forecasting Based on LSTM[J]. Power System Technology, 2017,(12):3797-3802.
[11]Xu S,Niu R. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area,China[J]. Computers&Geosciences,2018,111:87-96.
[12]Jain L C,Medsker L R. Recurrent Neural Networks:Design and Applications[C] Int. Joint Conference on Neural Networks. 1999:1537-1541.
[13]Pascanu R,Mikolov T,Bengio Y. On the difficulty of training Recurrent Neural Networks[J]. 2012,52(3):III-1310.
[14]Tian Y,Pan L. Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network[C]//IEEE International Conference on Smart City/socialcom/sustaincom. IEEE,2015:153-158.
[15]Li X,Peng L,Yao X,et al. Long short-term memory neural network for air pollutant concentration predictions:Method development and evaluation[J]. Environmental Pollution,2017,231(Pt 1):997-1004.
[16]Xu S,Niu R. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area,China[J]. Computers&Geosciences,2018,111:87-96.
[17]方必武,刘涤尘,王波,等.基于小波变换和改进萤火虫算法优化LSSVM的短期风速预测[J].电力系统保护与控制,2016,44(8):37-43.Fang Biwu,Liu Dichen,Wang Bo,et al. Short-term wind speed forecasting based on WD-CFA-LSSVM model[J]. Power System Protection and Control,2016,44(8):37-43.
[18]王晓兰,王明伟.基于小波分解和最小二乘支持向量机的短期风速预测[J].电网技术,2010,34(1):179-184.Wang Xiaolan,Wang Mingwei. Short-term wind speed forecasting based on wavelet decomposition and least square support vector machine[J].Power System Technology,2010,34(1):179-184.
[19]张亚超,刘开培,等.基于聚类经验模态分解样本熵和优化极限学习机的风电功率多步区间预测[J].电网技术,2016,40(7):2045-2051.Zhang Yachao,Liu Kaipei,et al. Wind Power Multi-Step Interval Prediction Based on Ensemble Empirical Mode Decomposition Sample Entropy and Optimized Extreme Learning Machine[J]. Power System Technology,2016,40(7):2045-2051.
[20]陈杰,沈艳霞,陆欣,等.一种风电功率概率区间多目标智能优化预测方法[J].电网技术,2016,40(8):2281-2287.Chen Jie,Shen Yanxia,Lu Xin,et al. An intelligent multi-objective optimized method for wind power prediction intervals[J]. Power System Technology,2016,40(10):2758-2765.
[21]范磊,卫志农,等.基于变分模态分解和蝙蝠算法-相关向量机的短期风速区间预测[J].电力自动化设备,2017,37(1):93-100.Fan Lei,Wei Zhinong,et al. Short-term wind speed interval prediction based on VMD and BA-RVM algorithm[J]. Electric Power Automation Equipment,2017,37(1):93-100.
[22]王贺,胡志坚,仉梦林.基于模糊信息粒化和最小二乘支持向量机的风电功率波动范围组合预测模型[J].电工技术学报,2014,29(12):218-224.Wang He,Hu Zhijian,Zhang Menglin. A combined forecasting model for range of wind power fluctuation based on fuzzy information granulation and least squares support vector machine[J]. Transactions of China Electrotechnical Society,2014,29(12):218-224.
[23]Kingma D P,Ba J. Adam:A Method for Stochastic Optimization[J].Computer Science,2014.
[24]Lu W,Pedrycz W,Liu X,et al. The modeling of time series based on fuzzy information granules[J]. Expert Systems with Applications,2014,41(8):3799-3808.
[25]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015,43(2):26-32.Wang Kai,Guan Shaoqing,Wang Lingxiang,et al. A combined forecasting model for wind power prediction based on fuzzy information granulation and least squares support vector machine[J]. Power System Protection and Control,2015,43(2):26-32.
[26]Ma X,Tao Z,Wang Y,et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J].Transportation Research Part C Emerging Technologies,2015,54:187-197.
[27]Bengio Y,Simard P,Frasconi P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks,1994,5(2):157.
[28][Bottou L. Large-Scale Machine Learning with Stochastic Gradient Descent[J]. 2010:177-186.
[29]Zeiler M D. ADADELTA:An Adaptive Learning Rate Method[J].Computer Science,2012.