基于相似日和CAPSO-SNN的光伏发电功率预测
|
摘要
针对光伏发电功率预测精度不高的问题,提出一种基于相似日和云自适应粒子群优化(CAPSO)算法优化Spiking神经网络(SNN)的发电功率预测模型。考虑到季节类型、天气类型和气象等主要影响因素,提出以综合相似度指标进行相似日选取;以SNN强大的计算能力和其善于处理时间序列问题的特点为基础,结合CAPSO算法搜索的随机性和稳定性优化SNN的多突触连接权值,减少对权值的约束,提高算法的收敛精度。根据某光伏电站的实测功率数据对所提模型进行测试和评估,结果表明,该模型比传统预测模型具有更高的预测精度和更好的适用性。
Since the forecasting accuracy of PV(Photo Voltaic) power generation is not high,a forecasting model based on the similar day and SNN(Spiking Neural Network) optimized by CAPSO(Cloud Adaptive Particle Swarm Optimization) algorithm is proposed. The comprehensive similarity index considering the main influencing factors,e.g. season,weather,meteorology,etc.,is adopted for selecting the similar day. Based on the powerful computation ability and efficiency in dealing with the time series problem of SNN,its multiple synaptic connection weights are optimized by the randomness and stability of CAPSO algorithm to loosen the constraint of weight and improve the convergence accuracy of algorithm. The proposed model is tested and evaluated based on the measured power data of a PV station and results show that,it has higher forecasting accuracy and better applicability than traditional forecasting models.
Since the forecasting accuracy of PV(Photo Voltaic) power generation is not high,a forecasting model based on the similar day and SNN(Spiking Neural Network) optimized by CAPSO(Cloud Adaptive Particle Swarm Optimization) algorithm is proposed. The comprehensive similarity index considering the main influencing factors,e.g. season,weather,meteorology,etc.,is adopted for selecting the similar day. Based on the powerful computation ability and efficiency in dealing with the time series problem of SNN,its multiple synaptic connection weights are optimized by the randomness and stability of CAPSO algorithm to loosen the constraint of weight and improve the convergence accuracy of algorithm. The proposed model is tested and evaluated based on the measured power data of a PV station and results show that,it has higher forecasting accuracy and better applicability than traditional forecasting models.
引文
[1]陈炜,艾欣,吴涛,等.光伏并网发电系统对电网的影响研究综述[J].电力自动化设备,2013,33(2):26-32.CHEN Wei,AI Xin,WU Tao,et al.Influence of grid-connected photovoltaic system on power network[J].Electric Power Automation Equipment,2013,33(2):26-32.
[2]李斌,袁越.光伏并网发电对保护及重合闸的影响与对策[J].电力自动化设备,2013,33(4):12-17.LI Bin,YUAN Yue.Impact of grid-connected photovoltaic power generation on protection and reclose,and its countermeasures[J].Electric Power Automation Equipment,2013,33(4):12-17.
[3]ALMONACID F,P譩REZ-HIGUERAS P J,FERN魣NDEZ E F,et al.A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator[J].Energy Conversion and Management,2014(85):389-398.
[4]丁明,徐宁舟.基于马尔可夫链的光伏发电系统输出功率短期预测方法[J].电网技术,2011,35(1):152-157.DING Ming,XU Ningzhou.A method to forecast short-term output power of photovoltaic generation system based on Markov chain[J].Power System Technology,2011,35(1):152-157.
[5]郭旭阳,谢开贵,胡博,等.计入光伏发电的电力系统分时段随机生产模拟[J].电网技术,2013,37(6):1499-1505.GUO Xuyang,XIE Kaigui,HU Bo,et al.A time-interval based probabilistic production simulation of power system with gridconnected photovoitaic generation[J].Power System Technology,2013,37(6):1499-1505.
[6]王守相,张娜.基于灰色神经网络组合模型的光伏短期出力预测[J].电力系统自动化,2012,36(19):37-41.WANG Shouxiang,ZHANG Na.Short-term output power forecast of pho tovoltaic based on a grey and neural network hybrid model[J].Automation of Electric Power Systems,2012,36(19):37-41.
[7]王晓兰,葛鹏江.基于相似日和径向基函数神经网络的光伏阵列输出功率预测[J].电力自动化设备,2013,33(1):100-103.WANG Xiaolan,GE Pengjiang.PV array output power forecasting based on similar day and RBFNN[J].Electric Power Automation Equipment,2013,33(1):100-103.
[8]KULKARNI S,SIMON S P,SUNDARESWARAN K.A Spiking Neural Network(SNN)forecast engine for short-term electrical load forecasting[J].Applied Soft Computing,2013,13(8):3628-3635.
[9]MAASS W.Networks of spiking neurons:the third generation of neural network models[J].Neural Networks,1997,10(9):1659-1671.
[10]GERSTNER W,KISTLER W M.Spiking neuron models:single neuron,populations,plasticity[M].Cambridge,UK:Cambridge University Press,2002:1-29.
[11]NATSCHLA咬ER T,RUF B.Spatial and temporal pattern analysis via spiking neurons[J].Network,1998,9(3):319-332.
[12]BOHTE S M,POUTRE H L,KOK J N.Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer spike neural network[J].IEEE Transactions on Neural Networks,2002,13(2):426-435.
[13]杨锡运,刘欢,张彬,等.组合权重相似日选取方法及光伏输出功率预测[J].电力自动化设备,2014,34(9):118-122.YANG Xiyun,LIU Huan,ZHANG Bin,et al.Similar day selection based on combined weight and photovoltaic power output forecasting[J].Electric Power Automation Equipment,2014,34(9):118-122.
[14]BOHTE S M,POUTRE J A L,KOK J N.Error-backpropagation in temporally encoded networks of spiking neurons[J].Neurocomputing,2002,48(1):17-37.
[15]吴杰康,熊焰.风水气互补发电优化的云模型自适应粒子群优化算法[J].中国电机工程学报,2014,34(增刊1):17-24.WU Jiekang,XIONG Yan.Based adaptive particle swarm optimization algorithm for complementary power generation optimization of wind-energy,hydro-energy and natural gas[J].Proceedings of the CSEE,2014,34(Supplement 1):17-24.
[16]徐茹枝,王宇飞.粒子群优化的支持向量回归机计算配电网理论线损方法[J].电力自动化设备,2012,32(5):86-89,93.XU Ruzhi,WANG Yufei.Theoretical line loss calculation based on SVR and PSO for distribution system[J].Electric Power Automation Equipment,2012,32(5):86-89,93.
[17]李德毅,刘常昱,杜鹢,等.不确定性人工智能[J].软件学报,2004,15(11):1583-1594.LI Deyi,LIU Changyu,DU Yi,et al.Artificial intelligence with uncertainty[J].Journal of Software,2004,15(11):1583-1594.
[18]李德毅,孟海军,史雪梅.隶属云和隶属云发生器[J].计算机研究与发展,1995,32(6):15-20.LI Deyi,MENG Haijun,SHI Xuemei.Membership clouds and membership cloud generators[J].Journal of Computer Research and Development,1995,32(6):15-20.
[19]易丹辉.数据分析与Eviews应用[M].北京:中国人民大学出版社,2008:47.
[2]李斌,袁越.光伏并网发电对保护及重合闸的影响与对策[J].电力自动化设备,2013,33(4):12-17.LI Bin,YUAN Yue.Impact of grid-connected photovoltaic power generation on protection and reclose,and its countermeasures[J].Electric Power Automation Equipment,2013,33(4):12-17.
[3]ALMONACID F,P譩REZ-HIGUERAS P J,FERN魣NDEZ E F,et al.A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator[J].Energy Conversion and Management,2014(85):389-398.
[4]丁明,徐宁舟.基于马尔可夫链的光伏发电系统输出功率短期预测方法[J].电网技术,2011,35(1):152-157.DING Ming,XU Ningzhou.A method to forecast short-term output power of photovoltaic generation system based on Markov chain[J].Power System Technology,2011,35(1):152-157.
[5]郭旭阳,谢开贵,胡博,等.计入光伏发电的电力系统分时段随机生产模拟[J].电网技术,2013,37(6):1499-1505.GUO Xuyang,XIE Kaigui,HU Bo,et al.A time-interval based probabilistic production simulation of power system with gridconnected photovoitaic generation[J].Power System Technology,2013,37(6):1499-1505.
[6]王守相,张娜.基于灰色神经网络组合模型的光伏短期出力预测[J].电力系统自动化,2012,36(19):37-41.WANG Shouxiang,ZHANG Na.Short-term output power forecast of pho tovoltaic based on a grey and neural network hybrid model[J].Automation of Electric Power Systems,2012,36(19):37-41.
[7]王晓兰,葛鹏江.基于相似日和径向基函数神经网络的光伏阵列输出功率预测[J].电力自动化设备,2013,33(1):100-103.WANG Xiaolan,GE Pengjiang.PV array output power forecasting based on similar day and RBFNN[J].Electric Power Automation Equipment,2013,33(1):100-103.
[8]KULKARNI S,SIMON S P,SUNDARESWARAN K.A Spiking Neural Network(SNN)forecast engine for short-term electrical load forecasting[J].Applied Soft Computing,2013,13(8):3628-3635.
[9]MAASS W.Networks of spiking neurons:the third generation of neural network models[J].Neural Networks,1997,10(9):1659-1671.
[10]GERSTNER W,KISTLER W M.Spiking neuron models:single neuron,populations,plasticity[M].Cambridge,UK:Cambridge University Press,2002:1-29.
[11]NATSCHLA咬ER T,RUF B.Spatial and temporal pattern analysis via spiking neurons[J].Network,1998,9(3):319-332.
[12]BOHTE S M,POUTRE H L,KOK J N.Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer spike neural network[J].IEEE Transactions on Neural Networks,2002,13(2):426-435.
[13]杨锡运,刘欢,张彬,等.组合权重相似日选取方法及光伏输出功率预测[J].电力自动化设备,2014,34(9):118-122.YANG Xiyun,LIU Huan,ZHANG Bin,et al.Similar day selection based on combined weight and photovoltaic power output forecasting[J].Electric Power Automation Equipment,2014,34(9):118-122.
[14]BOHTE S M,POUTRE J A L,KOK J N.Error-backpropagation in temporally encoded networks of spiking neurons[J].Neurocomputing,2002,48(1):17-37.
[15]吴杰康,熊焰.风水气互补发电优化的云模型自适应粒子群优化算法[J].中国电机工程学报,2014,34(增刊1):17-24.WU Jiekang,XIONG Yan.Based adaptive particle swarm optimization algorithm for complementary power generation optimization of wind-energy,hydro-energy and natural gas[J].Proceedings of the CSEE,2014,34(Supplement 1):17-24.
[16]徐茹枝,王宇飞.粒子群优化的支持向量回归机计算配电网理论线损方法[J].电力自动化设备,2012,32(5):86-89,93.XU Ruzhi,WANG Yufei.Theoretical line loss calculation based on SVR and PSO for distribution system[J].Electric Power Automation Equipment,2012,32(5):86-89,93.
[17]李德毅,刘常昱,杜鹢,等.不确定性人工智能[J].软件学报,2004,15(11):1583-1594.LI Deyi,LIU Changyu,DU Yi,et al.Artificial intelligence with uncertainty[J].Journal of Software,2004,15(11):1583-1594.
[18]李德毅,孟海军,史雪梅.隶属云和隶属云发生器[J].计算机研究与发展,1995,32(6):15-20.LI Deyi,MENG Haijun,SHI Xuemei.Membership clouds and membership cloud generators[J].Journal of Computer Research and Development,1995,32(6):15-20.
[19]易丹辉.数据分析与Eviews应用[M].北京:中国人民大学出版社,2008:47.