基于多元分析的优化模糊神经网络太阳能辐射量短期预测
|
摘要
为准确预测太阳能辐射量,提出一种基于多元分析的优化模糊神经网络预测辐射量的方法。首先结合曲线拟合和拉依达准则对数据做粗大误差的剔除,然后运用主成分分析法提取影响太阳能辐射量的主要因素,最后结合定性分析和定量分析建立优化的模糊神经网络预测模型,并设计数据采集装置采集短期气象数据,以提高预测的实时性和准确性。通过与不同的预测模型对比,验证本文所提算法和模型的正确性,结果表明该模型有效提高了短期太阳能数据预测的精准度。
In order to predict the solar energy radiation accurately, a method for forecasting solar radiation based on optimized fuzzy neural network with multivariate analysis is proposed. Firstly, the gross error of data is eliminated by combining the curve fitting and Pauta criterion, then the principal component analysis method is used to extract the main affecting factors of solar energy radiation, and finally, the optimized fuzzy neural network prediction model is established by combining qualitative and quantitative analyses. A data acquisition device is designed to collect short-term meteorological data in order to improve the real-time and accuracy of prediction. The comparison with the results of other prediction models verifies the correctness of proposed algorithm and model. The prediction results show that the proposed model can effectively improve the accuracy of short-term solar energy prediction.
In order to predict the solar energy radiation accurately, a method for forecasting solar radiation based on optimized fuzzy neural network with multivariate analysis is proposed. Firstly, the gross error of data is eliminated by combining the curve fitting and Pauta criterion, then the principal component analysis method is used to extract the main affecting factors of solar energy radiation, and finally, the optimized fuzzy neural network prediction model is established by combining qualitative and quantitative analyses. A data acquisition device is designed to collect short-term meteorological data in order to improve the real-time and accuracy of prediction. The comparison with the results of other prediction models verifies the correctness of proposed algorithm and model. The prediction results show that the proposed model can effectively improve the accuracy of short-term solar energy prediction.
引文
[1]李志恒,孙冉,张建立,等.基于改进BP神经网络的中长期电力负荷预测算法设计[J].自动化与仪器仪表,2017(10):23-25,28.
[2]陈亚.人工鱼群神经网络在短期电力负荷预测中的研究与应用[D].银川:宁夏大学,2017.
[3]陈亚,李萍.基于神经网络的短期电力负荷预测仿真研究[J].电气技术,2017(1):26-29.
[4]李文.基于Elman神经网络算法的电力负荷预测模型研究[J].赤峰学院学报:自然科学版,2017,33(21):38-40.
[5]黄俊梅.基于神经网络的风电机组变桨距恒功率控制系统的研究[J].电子产品世界,2017,24(5):76-79.
[6]付光杰,胡明哲.基于改进型学习率自适应BP神经网络的风力发电变桨距控制技术[J].自动化与仪器仪表,2016(6):8-10.
[7]袁铁江,晁勤,李义岩,等.大规模风电并网电力系统经济调度中风电场出力的短期预测模型[J].中国电机工程学报,2010,30(13):23-27.
[8]范高枫,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[9]鲍安平.光伏发电中太阳辐照度短期优化预测仿真[J].计算机仿真,2017,34(10):69-72.
[10]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):226-231,265.
[11]陈昌松,段善旭,殷进军.基于神经网路的光伏阵列发电预测模型的设计[J].电工技术学报,2009,24(9):153-158.
[12]于秋玲,许长清,李珊,等.基于模糊聚类和支持向量机的短期光伏功率预测[J].电力系统及其自动化学报,2016,28(12):115-118,129.
[13] YONAHA A, SENJYU T, FUNABASHI T. Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system[C]//IEEE Power Engineering Society General Meeting,2007.
[14] MOHANDES M, REHMAN S, HALAWANI T O. Estimation of global solar radiation using artificial neural networks[J]. Renewable Energy,1998,14(1-4):179-184.
[15] DORVLO A S S, JERVASE J A, Al-LAWATI A. Solar radiation assessment using artificial neural networks[J]. Applied Energy,2002,71(4):307-319.
[16] ELMINIR H K, AREED F F, ELSAYED T S. Estimation of solar radiation components incident on Helwan site using neural networks[J]. Solar Energy,2005,79(3):270-279.
[17] TYMVIOS F S, JACOVIDES C P, MICHAELIDES S C, et al. Comparative study ofngstrm's and artificial neural networks methodologies in estimating global solar radiation[J]. Solar Energy,2005,78(6):752-762.
[2]陈亚.人工鱼群神经网络在短期电力负荷预测中的研究与应用[D].银川:宁夏大学,2017.
[3]陈亚,李萍.基于神经网络的短期电力负荷预测仿真研究[J].电气技术,2017(1):26-29.
[4]李文.基于Elman神经网络算法的电力负荷预测模型研究[J].赤峰学院学报:自然科学版,2017,33(21):38-40.
[5]黄俊梅.基于神经网络的风电机组变桨距恒功率控制系统的研究[J].电子产品世界,2017,24(5):76-79.
[6]付光杰,胡明哲.基于改进型学习率自适应BP神经网络的风力发电变桨距控制技术[J].自动化与仪器仪表,2016(6):8-10.
[7]袁铁江,晁勤,李义岩,等.大规模风电并网电力系统经济调度中风电场出力的短期预测模型[J].中国电机工程学报,2010,30(13):23-27.
[8]范高枫,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[9]鲍安平.光伏发电中太阳辐照度短期优化预测仿真[J].计算机仿真,2017,34(10):69-72.
[10]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):226-231,265.
[11]陈昌松,段善旭,殷进军.基于神经网路的光伏阵列发电预测模型的设计[J].电工技术学报,2009,24(9):153-158.
[12]于秋玲,许长清,李珊,等.基于模糊聚类和支持向量机的短期光伏功率预测[J].电力系统及其自动化学报,2016,28(12):115-118,129.
[13] YONAHA A, SENJYU T, FUNABASHI T. Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system[C]//IEEE Power Engineering Society General Meeting,2007.
[14] MOHANDES M, REHMAN S, HALAWANI T O. Estimation of global solar radiation using artificial neural networks[J]. Renewable Energy,1998,14(1-4):179-184.
[15] DORVLO A S S, JERVASE J A, Al-LAWATI A. Solar radiation assessment using artificial neural networks[J]. Applied Energy,2002,71(4):307-319.
[16] ELMINIR H K, AREED F F, ELSAYED T S. Estimation of solar radiation components incident on Helwan site using neural networks[J]. Solar Energy,2005,79(3):270-279.
[17] TYMVIOS F S, JACOVIDES C P, MICHAELIDES S C, et al. Comparative study ofngstrm's and artificial neural networks methodologies in estimating global solar radiation[J]. Solar Energy,2005,78(6):752-762.