基于改进乌鸦算法和ESN神经网络的短期风电功率预测
|
摘要
精确的短期风电功率预测对于提升电力系统经济稳定运行十分重要。为了克服传统的神经网络在参数选取中容易受主观因素影响和陷入局部最优的不足,提出一种基于改进乌鸦算法(ICSA)优化回声状态神经网络(ESN)参数的短期风电功率组合预测方法。在算法寻优初期引入Lévy飞行机制增强搜索效率,而在迭代后期加入高斯函数,对进化后的全部轨迹进行相应的调整,保证算法的全局寻优和逐次逼近能力;通过改进的CSA算法对ESN神经网络输出层连接权值矩阵进行优化以提高网络的训练效率。最后利用两组实验数据对预测模型进行了有效性验证,结果表明,所提算法能有效应对风电功率时序的随机性和不确定性特征,具有更高的建模精度和更快的收敛速度。
Accurate short-term wind power forecasting is important for improving the economic and stable operation of power system. Since it is easy to be affected by subjective factor and fall into local optimum in parameters selecting compared with traditional Neural Network, a novel combination forecasting approach based on Improved Crow Search Algorithm(ICSA) to optimize the parameters of Echo State Network(ESN) neural network is proposed to overcome above inadequacies. The Lévy flight is introduced to increase the searching efficiency at initial stages, and during the later stage of iteration, the Gauss function is added aiming at making an appropriate adjustments for the whole trajectory points after evolution, which can guarantee the ability of global optimization and successive approximation; it chooses optimal the weight values of the hidden layer to enhance the efficiency of neural network training by ICSA algorithm. Finally, effectiveness of the proposed forecasting model is tested on two groups of experimental data, the results show that proposed algorithm can effectively cope with the variability and intermittency of wind power time series, having higher modeling precision and faster convergence speed.
Accurate short-term wind power forecasting is important for improving the economic and stable operation of power system. Since it is easy to be affected by subjective factor and fall into local optimum in parameters selecting compared with traditional Neural Network, a novel combination forecasting approach based on Improved Crow Search Algorithm(ICSA) to optimize the parameters of Echo State Network(ESN) neural network is proposed to overcome above inadequacies. The Lévy flight is introduced to increase the searching efficiency at initial stages, and during the later stage of iteration, the Gauss function is added aiming at making an appropriate adjustments for the whole trajectory points after evolution, which can guarantee the ability of global optimization and successive approximation; it chooses optimal the weight values of the hidden layer to enhance the efficiency of neural network training by ICSA algorithm. Finally, effectiveness of the proposed forecasting model is tested on two groups of experimental data, the results show that proposed algorithm can effectively cope with the variability and intermittency of wind power time series, having higher modeling precision and faster convergence speed.
引文
[1]刘波,贺志佳,金昊.风力发电现状与发展趋势[J].东北电力大学学报,2016,36(2):7-13.LIU Bo,HE Zhijia,JIN Hao.A review of chaos theory in power system load prediction[J].Journal of Northeast Dianli University,2016,36(2):7-13.
[2]CATALAO J,POUSINHO H,MENDES V.Hybrid intelligent approach for short-term wind power forecasting in Portugal[J].IET Renewable Power Generation,2011,5(3):251-257.
[3]JIANG Yu,CHEN Xingying,YU Kun,et al.Short-term wind power forecasting using hybrid method based on enhanced boosting algorithm[J].Journal of Modern Power System and Clean Energy,2017,5(1):126-133.
[4]陈昊,万秋兰,王玉荣.基于厚尾均值广义自回归条件异方差族模型的短期风电功率预测[J].电工技术学报,2016,31(5):91-98.CHEN Hao,WAN Qiulan,WANG Yurong.Short-term wind power forecast based on fat-tailed generalized autoregressive conditional heteroscedasticity in mean type model[J].Transactions of China Electrotechnical Society,2016,31(5):91-98.
[5]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率超短期预测[J].电力系统保护与控制,2015,43(2):90-95.LIU Aiguo,XUE Yuntao,HU Jianglu,et al.Ultra-shortterm wind power forecasting based on SVM optimized by GA[J].Power System Protection and Control,2015,43(2):90-95.
[6]张宜阳,卢继平,孟洋洋,等.基于经验模式分解和混沌相空间重构的风电功率短期预测[J].电力系统自动化,2012,36(5):24-28.ZHANG Yihang,LU Jiping,MENG Yangyang,et al.Wind power short-term forecasting based on empirial mode decomposition and chaotic phase space reconstruction[J].Automation of Electric Power Systems,2012,36(5):24-28.
[7]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI:10.1186/s41601-016-0016-y.
[8]师彪,李郁侠,于新花,等.基于改进粒子群-模糊神经网络的短期电力负荷预测[J].系统工程理论与实践,2010,30(1):158-166.SHI Biao,LI Yuxia,YU Xinhua,et al.Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model[J].Systems Engineering Theory and Practice,2010,30(1):158-166.
[9]李燕青,袁燕舞,郭通.基于AMD-ICSA-SVM的超短期风电功率组合预测[J].电力系统保护与控制,2017,45(14):113-120.LI Yanqing,YUAN Yanwu,GUO Tong.Combination ultra-short-term prediction of wind power based on AMD-ICSA-SVM[J].Power System Protection and Control,2017,45(14):113-120.
[10]尹东阳,盛义发,蒋明结,等.基于粗糙集理论-主成分分析的Elam神经网络的短期风速预测[J].电力系统保护与控制,2014,42(11):46-50.YIN Dongyang,SHENG Yifa,JIANG Mingjie,et al.Short-term wind speed forecasting using Elman neural network based on rough set theory and principal components analysis[J].Power System Protection and Control,2014,42(11):46-50.
[11]张颖超,王雅晨,邓华,等.基于IAFSA-BPNN的短期风电功率预测[J].电力系统保护与控制,2017,45(7):58-63.ZHANG Yingchao,WANG Yachen,DENG Hua,et al.IAFSA-BPNN for wind power probabilistic forecasting[J].Power System Protection and Control,2017,45(7):58-63.
[12]李松,刘力军,解永乐.遗传算法优化BP神经网络的短时交通流混沌预测[J].决策与控制,2011,26(10):1581-1585.LI Song,LIU Lijun,XIE Yongle.Chaotic prediction for short-term traffic flow of optimized BP neural network based on genetic algorithm[J].Control and Decision,2011,26(10):1581-1585.
[13]叶小岭,顾荣,邓华,等.基于WRF模式和PSO-LSSVM的风电场短期风速订正[J].电力系统保护与控制,2017,45(22):48-54.YE Xiaoling,GU Rong,DENG Hua,et al.Modification technology research of short-term wind speed in wind farm based on WRF model and PSO-LSSVM method[J].Power System Protection and Control,2017,45(22):48-54.
[14]ALMOATAZ Y,ABDELAZIZ A,AHMED F.A novel approach based on crow search algorithm for optimal selection of conductor size in radial distribution networks[J].Engineering Science and Technology,2017,20:391-402.
[15]BABINEC S,POSPICHAL J.Modular echo state neural networks in time series prediction[J].Computing and Informatics,2011,30:321-334.
[16]SAYED G,HASSANIEN A,AZAR A.Feature selection via a novel chaotic crow search algorithm[J].Neural Computing and Applications,2017(1):1-18.
[17]VISWANATHAN G M,AFANSYEV V,BULDYREV S,et al.Lévy flights search patterns of wandering albatrosses[J].Nature,1996,381:13-15.
[18]费腾,张立毅,陈雷.混合Levy变异与混沌变异的改进人工鱼群算法[J].计算机工程,2016,42(7):146-15.FEI Teng,ZHANG Liyi,CHEN Lei.Improved artificial fish swarm algorithm mixing Levy mutation and chaotic mutation[J].Computer Engineering,2016,42(7):146-152.
[19]张迅,王平,邢建春,等.基于高斯函数递减惯性权重的粒子群优化算法[J].计算机应用研究,2012,29(10):3710-3712.ZHANG Xun,WANG Ping,XING Jianchu,et al.Particle swarm optimization algorithms with decreasing inertia weight based on Gaussian function[J].Application Research of Computers,2012,29(10):3710-3712.
[20]温润,谭丽.结合HS算法与ESN算法的光伏发电短期出力预测[J].计算机科学,2017,44(6):226-231.WEN Run,TAN Li.Short-term power forecasting for photovoltaic generation based on HS-ESN[J].Computer Science,2017,44(6):226-231.
[21]乔俊飞,李瑞祥,柴伟,等.基于PSO-ESN神经网络的污水BOD预测[J].控制工程,2016,23(4):463-467.QIAO Junfei,LI Ruixiang,CHAI Wei,et al.Prediction of BOD based on PSO-ESN neutral network[J].Control Engineering of China,2016,23(4):463-467.
[2]CATALAO J,POUSINHO H,MENDES V.Hybrid intelligent approach for short-term wind power forecasting in Portugal[J].IET Renewable Power Generation,2011,5(3):251-257.
[3]JIANG Yu,CHEN Xingying,YU Kun,et al.Short-term wind power forecasting using hybrid method based on enhanced boosting algorithm[J].Journal of Modern Power System and Clean Energy,2017,5(1):126-133.
[4]陈昊,万秋兰,王玉荣.基于厚尾均值广义自回归条件异方差族模型的短期风电功率预测[J].电工技术学报,2016,31(5):91-98.CHEN Hao,WAN Qiulan,WANG Yurong.Short-term wind power forecast based on fat-tailed generalized autoregressive conditional heteroscedasticity in mean type model[J].Transactions of China Electrotechnical Society,2016,31(5):91-98.
[5]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率超短期预测[J].电力系统保护与控制,2015,43(2):90-95.LIU Aiguo,XUE Yuntao,HU Jianglu,et al.Ultra-shortterm wind power forecasting based on SVM optimized by GA[J].Power System Protection and Control,2015,43(2):90-95.
[6]张宜阳,卢继平,孟洋洋,等.基于经验模式分解和混沌相空间重构的风电功率短期预测[J].电力系统自动化,2012,36(5):24-28.ZHANG Yihang,LU Jiping,MENG Yangyang,et al.Wind power short-term forecasting based on empirial mode decomposition and chaotic phase space reconstruction[J].Automation of Electric Power Systems,2012,36(5):24-28.
[7]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI:10.1186/s41601-016-0016-y.
[8]师彪,李郁侠,于新花,等.基于改进粒子群-模糊神经网络的短期电力负荷预测[J].系统工程理论与实践,2010,30(1):158-166.SHI Biao,LI Yuxia,YU Xinhua,et al.Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model[J].Systems Engineering Theory and Practice,2010,30(1):158-166.
[9]李燕青,袁燕舞,郭通.基于AMD-ICSA-SVM的超短期风电功率组合预测[J].电力系统保护与控制,2017,45(14):113-120.LI Yanqing,YUAN Yanwu,GUO Tong.Combination ultra-short-term prediction of wind power based on AMD-ICSA-SVM[J].Power System Protection and Control,2017,45(14):113-120.
[10]尹东阳,盛义发,蒋明结,等.基于粗糙集理论-主成分分析的Elam神经网络的短期风速预测[J].电力系统保护与控制,2014,42(11):46-50.YIN Dongyang,SHENG Yifa,JIANG Mingjie,et al.Short-term wind speed forecasting using Elman neural network based on rough set theory and principal components analysis[J].Power System Protection and Control,2014,42(11):46-50.
[11]张颖超,王雅晨,邓华,等.基于IAFSA-BPNN的短期风电功率预测[J].电力系统保护与控制,2017,45(7):58-63.ZHANG Yingchao,WANG Yachen,DENG Hua,et al.IAFSA-BPNN for wind power probabilistic forecasting[J].Power System Protection and Control,2017,45(7):58-63.
[12]李松,刘力军,解永乐.遗传算法优化BP神经网络的短时交通流混沌预测[J].决策与控制,2011,26(10):1581-1585.LI Song,LIU Lijun,XIE Yongle.Chaotic prediction for short-term traffic flow of optimized BP neural network based on genetic algorithm[J].Control and Decision,2011,26(10):1581-1585.
[13]叶小岭,顾荣,邓华,等.基于WRF模式和PSO-LSSVM的风电场短期风速订正[J].电力系统保护与控制,2017,45(22):48-54.YE Xiaoling,GU Rong,DENG Hua,et al.Modification technology research of short-term wind speed in wind farm based on WRF model and PSO-LSSVM method[J].Power System Protection and Control,2017,45(22):48-54.
[14]ALMOATAZ Y,ABDELAZIZ A,AHMED F.A novel approach based on crow search algorithm for optimal selection of conductor size in radial distribution networks[J].Engineering Science and Technology,2017,20:391-402.
[15]BABINEC S,POSPICHAL J.Modular echo state neural networks in time series prediction[J].Computing and Informatics,2011,30:321-334.
[16]SAYED G,HASSANIEN A,AZAR A.Feature selection via a novel chaotic crow search algorithm[J].Neural Computing and Applications,2017(1):1-18.
[17]VISWANATHAN G M,AFANSYEV V,BULDYREV S,et al.Lévy flights search patterns of wandering albatrosses[J].Nature,1996,381:13-15.
[18]费腾,张立毅,陈雷.混合Levy变异与混沌变异的改进人工鱼群算法[J].计算机工程,2016,42(7):146-15.FEI Teng,ZHANG Liyi,CHEN Lei.Improved artificial fish swarm algorithm mixing Levy mutation and chaotic mutation[J].Computer Engineering,2016,42(7):146-152.
[19]张迅,王平,邢建春,等.基于高斯函数递减惯性权重的粒子群优化算法[J].计算机应用研究,2012,29(10):3710-3712.ZHANG Xun,WANG Ping,XING Jianchu,et al.Particle swarm optimization algorithms with decreasing inertia weight based on Gaussian function[J].Application Research of Computers,2012,29(10):3710-3712.
[20]温润,谭丽.结合HS算法与ESN算法的光伏发电短期出力预测[J].计算机科学,2017,44(6):226-231.WEN Run,TAN Li.Short-term power forecasting for photovoltaic generation based on HS-ESN[J].Computer Science,2017,44(6):226-231.
[21]乔俊飞,李瑞祥,柴伟,等.基于PSO-ESN神经网络的污水BOD预测[J].控制工程,2016,23(4):463-467.QIAO Junfei,LI Ruixiang,CHAI Wei,et al.Prediction of BOD based on PSO-ESN neutral network[J].Control Engineering of China,2016,23(4):463-467.