基于奇异谱分析的短期电价预测
|
摘要
针对电价序列具有非线性和非平稳性的特点,提出了一种基于奇异谱分析(SSA)和改进布谷鸟算法(ICS)优化极限学习机(ELM)的短期电价预测模型。采用奇异谱分析提取电价序列中的趋势成分和振荡成分,进行准周期信号分量重建,并对重建序列进行ELM建模预测。针对ELM预测模型中的参数易陷入局部最优的问题,为了提高预测精度,提出改进布谷鸟算法优化预测模型的参数。最后将所有预测序列进行叠加,得到最终的电价预测值。以澳大利亚某电力市场电价数据为例进行分析,通过与其他几种预测模型相比,表明SSA-ICS-ELM模型能有效提高电价预测的精度和稳定性。
In view of the nonlinear and non-stationary characteristics of electricity price time series, the novel model for electricity price forecasting in this paper is proposed by the combination of Singular Spectrum Analysis(SSA) and Extreme Learning Machine(ELM) optimized by the Improved Cuckoo Search algorithm(ICS). SSA is used to extract the trend components and oscillation components of the original data and reconstruct all the components, and the ELM model is used to predict the reconstruction sequences. Against the parameters that in the ELM prediction model tend to fall into the local optimum, the ICS algorithm is introduced to optimize the model parameters to further improve the predictive value. Finally, all the predicted sequences are summed up to get the final forecast of electricity price. The empirical results demonstrate that the SSA-ICS-ELM model can improve the prediction accuracy and stability of electricity price forecasting considerably in comparison with other methods by analyzing the price data in Australia electricity market.
In view of the nonlinear and non-stationary characteristics of electricity price time series, the novel model for electricity price forecasting in this paper is proposed by the combination of Singular Spectrum Analysis(SSA) and Extreme Learning Machine(ELM) optimized by the Improved Cuckoo Search algorithm(ICS). SSA is used to extract the trend components and oscillation components of the original data and reconstruct all the components, and the ELM model is used to predict the reconstruction sequences. Against the parameters that in the ELM prediction model tend to fall into the local optimum, the ICS algorithm is introduced to optimize the model parameters to further improve the predictive value. Finally, all the predicted sequences are summed up to get the final forecast of electricity price. The empirical results demonstrate that the SSA-ICS-ELM model can improve the prediction accuracy and stability of electricity price forecasting considerably in comparison with other methods by analyzing the price data in Australia electricity market.
引文
[1]白杨,李昂,夏清.新形势下电力市场营销模式与新型电价体系[J].电力系统保护与控制,2016,44(5):10-16.BAI Yang,LI Ang,XIA Qing.Electricity business marketing modes in the new environment and new electricity pricing systems[J].Power System Protection and Control,2016,44(5):10-16.
[2]熊尚飞,邹小燕.电力市场价格风险价值与波动预测研究综述[J].电力系统保护与控制,2014,42(2):146-153.XIONG Shangfei,ZOU Xiaoyan.Value at risk and price volatility forecasting in electricity market:a literature review[J].Power System Protection and Control,2014,42(2):146-153.
[3]张显,王锡凡.分时段短期电价预测[J].中国电机工程学报,2005,25(15):1-6.ZHANG Xian,WANG Yifan.Review of the short-term electricity price[J].Proceedings of the CSEE,2005,25(15):1-6.
[4]HE K,YU L,TANG L.Electricity price forecasting with a BED(Bivariate EMD Denoising)methodology[J].Energy,2015,91:601-609.
[5]刘丽燕,邹小燕.GARCH族模型在电力市场电价预测中的比较研究[J].电力系统保护与控制,2016,44(4):57-63.LIU Liyan,ZOU Xiaoyan.Comparison of GARCHmodels in electricity price forecasting[J].Power System Protection and Control,2016,44(4):57-63.
[6]陈思杰,周浩.电力市场电价预测方法综述[J].电力系统保护与控制,2006,34(11):54-60.CHEN Sijie,ZHOU Hao.Electricity price forecast method of electricity market[J].Power System Protection and Control,2006,34(11):54-60.
[7]张肖波,李婧娇,罗欣.基于灰色关联分析与人工神经网络算法的节假日负荷预测研究[J].广东电力,2012,25(7):38-42.ZHANG Xiaobo,LI Jingjiao,LUO Xin.Research on load forecast on holidays based on grey relational analysis and artificial neural network algorithm[J].Guangdong Electric Power,2012,25(7):38-42.
[8]陈金楷,夏季,谭鹏,等.结合相空间重构和ELM的磨煤机振动软测量[J].热力发电,2015,44(3):42-47.CHEN Jinkai,XIA Ji,TAN Peng,et al.Phase spase reconstruction and ELM based soft measurement for vibration of a mill with multiple parameters and coal types[J].Thermal Power Generation,2015,44(3):42-47.
[9]熊军华,牛珂,张春歌,等.基于小波变异果蝇优化支持向量机短期负荷预测方法研究[J].电力系统保护与控制,2017,45(13):71-77.XIONG Junhua,NIU Ke,ZHANG Chunge,et al.LSSVMin short-term load forecasting based on wavelet transform and mutant fruit fly optimization algorithm[J].Power System Protection and Control,2017,45(13):71-77.
[10]周俊,陈璟华,刘国祥,等.粒子群优化算法中惯性权重综述[J].广东电力,2013,26(7):6-12.ZHOU Jun,CHEN Jinghua,LIU Guoxiang,et a1.Summary on inertia weight in particle swarm optimization algorithm[J].Guangdong Electric Power,2013,26(7):6-12.
[11]董福贵,张世英,谭忠富,等.基于遗传算法的小波神经网络在电价预测中的应用[J].计算机工程,2005,31(4):32-33.DONG Fugui,ZHANG Shiying,TAN Zhongfu,et a1.Application for electricity price forecasting using wavelet neural networks based on GA[J].Computer Engineering,2005,31(4):32-33.
[12]薛浩然,张珂珩,李斌,等.基于布谷鸟算法和支持向量机的变压器故障诊断[J].电力系统保护与控制,2015,43(8):8-13.XUE Haoran,ZHANG Keheng,LI Bin,et a1.Fault diagnosis of transformer based on the cuckoo search and support vector machine[J].Power System Protection and Control,2015,43(8):8-13.
[13]ZHANG X,WANG J,ZHANG K.Short-term electric load forecasting based on singular spectrum analysis and support vector machine optimized by Cuckoo search algorithm[J].Electric Power Systems Research,2017,146:270-285.
[14]罗勇,匡翠林,卢辰龙,等.基于SSA的GPS坐标序列去噪及季节信号提取[J].大地测量与地球动力学,2015,35(3):391-395.LUO Yong,KUANG Cuilin,LU Chenlong,et a1.GPScoordinate series denoising and seasonal signal extraction based on SSA[J].Journal of Geodesy and Geodynamics,2015,35(3):391-395.
[15]ABDOLLAHZADE M,MIRANIAN A,HASSANI H,et al.A new hybrid enhanced local linear neuro-fuzzy model based on the optimized singular spectrum analysis and its application for nonlinear and chaotic time series forecasting[J].Information Sciences,2015,295:107-125.
[16]XIAO L,WANG J,HOU R,et al.A combined model based on data pre-analysis and weight coefficients optimization for electrical load forecasting[J].Energy,2015,82:524-549.
[17]LI Z,YE L,ZHAO Y,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.
[18]YANG X S,DEB S.Engineering optimization by cuckoo search[J].International Journal of Mathematical Modeling&Numerical Optimization,2010,1(4):330-343.
[19]LIU H,CHEN C,TIAN H Q,et al.A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks[J].Renewable Energy,2012,48(6):545-556.
[20]HASSANI H.Singular spectrum analysis:methodology and comparison[J].Journal of Data Science,2007,5(2):239-257.
[2]熊尚飞,邹小燕.电力市场价格风险价值与波动预测研究综述[J].电力系统保护与控制,2014,42(2):146-153.XIONG Shangfei,ZOU Xiaoyan.Value at risk and price volatility forecasting in electricity market:a literature review[J].Power System Protection and Control,2014,42(2):146-153.
[3]张显,王锡凡.分时段短期电价预测[J].中国电机工程学报,2005,25(15):1-6.ZHANG Xian,WANG Yifan.Review of the short-term electricity price[J].Proceedings of the CSEE,2005,25(15):1-6.
[4]HE K,YU L,TANG L.Electricity price forecasting with a BED(Bivariate EMD Denoising)methodology[J].Energy,2015,91:601-609.
[5]刘丽燕,邹小燕.GARCH族模型在电力市场电价预测中的比较研究[J].电力系统保护与控制,2016,44(4):57-63.LIU Liyan,ZOU Xiaoyan.Comparison of GARCHmodels in electricity price forecasting[J].Power System Protection and Control,2016,44(4):57-63.
[6]陈思杰,周浩.电力市场电价预测方法综述[J].电力系统保护与控制,2006,34(11):54-60.CHEN Sijie,ZHOU Hao.Electricity price forecast method of electricity market[J].Power System Protection and Control,2006,34(11):54-60.
[7]张肖波,李婧娇,罗欣.基于灰色关联分析与人工神经网络算法的节假日负荷预测研究[J].广东电力,2012,25(7):38-42.ZHANG Xiaobo,LI Jingjiao,LUO Xin.Research on load forecast on holidays based on grey relational analysis and artificial neural network algorithm[J].Guangdong Electric Power,2012,25(7):38-42.
[8]陈金楷,夏季,谭鹏,等.结合相空间重构和ELM的磨煤机振动软测量[J].热力发电,2015,44(3):42-47.CHEN Jinkai,XIA Ji,TAN Peng,et al.Phase spase reconstruction and ELM based soft measurement for vibration of a mill with multiple parameters and coal types[J].Thermal Power Generation,2015,44(3):42-47.
[9]熊军华,牛珂,张春歌,等.基于小波变异果蝇优化支持向量机短期负荷预测方法研究[J].电力系统保护与控制,2017,45(13):71-77.XIONG Junhua,NIU Ke,ZHANG Chunge,et al.LSSVMin short-term load forecasting based on wavelet transform and mutant fruit fly optimization algorithm[J].Power System Protection and Control,2017,45(13):71-77.
[10]周俊,陈璟华,刘国祥,等.粒子群优化算法中惯性权重综述[J].广东电力,2013,26(7):6-12.ZHOU Jun,CHEN Jinghua,LIU Guoxiang,et a1.Summary on inertia weight in particle swarm optimization algorithm[J].Guangdong Electric Power,2013,26(7):6-12.
[11]董福贵,张世英,谭忠富,等.基于遗传算法的小波神经网络在电价预测中的应用[J].计算机工程,2005,31(4):32-33.DONG Fugui,ZHANG Shiying,TAN Zhongfu,et a1.Application for electricity price forecasting using wavelet neural networks based on GA[J].Computer Engineering,2005,31(4):32-33.
[12]薛浩然,张珂珩,李斌,等.基于布谷鸟算法和支持向量机的变压器故障诊断[J].电力系统保护与控制,2015,43(8):8-13.XUE Haoran,ZHANG Keheng,LI Bin,et a1.Fault diagnosis of transformer based on the cuckoo search and support vector machine[J].Power System Protection and Control,2015,43(8):8-13.
[13]ZHANG X,WANG J,ZHANG K.Short-term electric load forecasting based on singular spectrum analysis and support vector machine optimized by Cuckoo search algorithm[J].Electric Power Systems Research,2017,146:270-285.
[14]罗勇,匡翠林,卢辰龙,等.基于SSA的GPS坐标序列去噪及季节信号提取[J].大地测量与地球动力学,2015,35(3):391-395.LUO Yong,KUANG Cuilin,LU Chenlong,et a1.GPScoordinate series denoising and seasonal signal extraction based on SSA[J].Journal of Geodesy and Geodynamics,2015,35(3):391-395.
[15]ABDOLLAHZADE M,MIRANIAN A,HASSANI H,et al.A new hybrid enhanced local linear neuro-fuzzy model based on the optimized singular spectrum analysis and its application for nonlinear and chaotic time series forecasting[J].Information Sciences,2015,295:107-125.
[16]XIAO L,WANG J,HOU R,et al.A combined model based on data pre-analysis and weight coefficients optimization for electrical load forecasting[J].Energy,2015,82:524-549.
[17]LI Z,YE L,ZHAO Y,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.
[18]YANG X S,DEB S.Engineering optimization by cuckoo search[J].International Journal of Mathematical Modeling&Numerical Optimization,2010,1(4):330-343.
[19]LIU H,CHEN C,TIAN H Q,et al.A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks[J].Renewable Energy,2012,48(6):545-556.
[20]HASSANI H.Singular spectrum analysis:methodology and comparison[J].Journal of Data Science,2007,5(2):239-257.