李冬辉;尹海燕;郑博文;

• 1:天津大学电气自动化与信息工程学院

摘要(Abstract)：

精确的年电力负荷预测为电力建设和电网运行提供可靠的指导。受多种因素的影响,年电力负荷曲线呈现出非线性特性,因此年电力负荷预测问题的解决需要建立在非线性模型的基础之上。广义回归神经网络(GRNN)已被证明在处理非线性问题上是非常有效的。该网络只有一个扩展参数,如何确定适当的扩展参数是使用GRNN进行预测的关键点。提出了一种将多种群的果蝇优化算法(MFOA)和GRNN相结合的混合年电力负荷预测模型,用以解决上述问题。其中,MFOA用作为GRNN电力负荷预测模型选择适当的扩展参数。最后通过模拟实验数据分析,MFOA-GRNN模型的年电力负荷预测平均绝对百分比误差为0.510%,均方误差为0.281。并且将其结果与差分进化的支持向量机模型(DE-SVM)、粒子群优化的GRNN模型(PSO-GRNN)、以及果蝇优化的GRNN模型(FOA-GRNN)的预测结果进行了比较。最终得出,文中所提出的MFOA-GRNN模型在年电力负荷预测中的预测性能优于上述3种模型。

关键词(KeyWords)： 年电力负荷预测;广义回归神经网络;参数优化;多种群;果蝇优化算法;相对误差

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 李冬辉;尹海燕;郑博文;

Email:

DOI: 10.13335/j.1000-3673.pst.2017.1403

参考文献(References)：

• [1]Rui H,Wen S P,Zeng Z J,et al.A short-term power load forecasting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm[J].Neurocomputing,2017(221):24-31.
• [2]Kavousi-Fard A,Samet H,Marzbani F.A new hybrid modified firefly algorithm and support vector regression model foraccurate short term load forecasting[J].Expert Systems with Applications,2014,41(13):6047-6056.
• [3]肖白,周潮,穆港.空间电力负荷预测方法综述与展望[J].中国电机工程学报,2013,33(25):78-92.Xiao Bai,Zhou Chao,Mu Gang.Review and prospect of the spatial load forecasting methods[J].Proceedings of the CSEE,2013,33(25):78-92(in Chinese).
• [4]于海燕,张凤玲.基于模糊神经网络的电力负荷短期预测[J].电网技术,2007,31(3):68-72.Yu Haiyan,Zhang Fengling.Short-term load forecasting based on fuzzy neural network[J].Power System Technology,2007,31(3):68-72(in Chinese).
• [5]Pappas S S,Ekonomou L,Karampelas P,et al.Electricity demand load forecasting of the Hellenic power system using an ARMA model[J].Electric Power Systems Research,2010,80(3):256-264.
• [6]Sorjamaa A,Jin Hao,Reyhani N,et al.Methodology for long-term prediction of time series[J].Neurocomputer,2007,70(16-18):861-869.
• [7]Chen J F,Wang W M,Huang C M.Analysis of an adaptive time-series auto regressive moving-average(ARMA)model for shortterm load forecasting[J].Electric Power Systems Research,1995,34:187-96.
• [8]Wang B,Tai N L,Zhai H Q,et al.A new ARMAX model based on evolutionary algorithm and particle swarm optimization for shortterm load forecasting[J].Electric Power Systems Research,2008,78(10):1679-85.
• [9]Hsu C C,Chen C Y.Regional load forecasting in Taiwan-applications of artificial neural networks[J].Energy Conversion and Management,2003,44(12):1941-1949.
• [10]Beccali M,Cellura M,Lo Brano V,et al.Forecasting daily urban electric load profiles using artificial neural networks[J].Energy Conversion and Management,2008,45(18-19):2879-2900.
• [11]傅军栋,刘晶,喻勇.基于果蝇优化灰色神经网络的年电力负荷预测[J].华东交通大学学报,2015,32(1):98-104.Fu Jundong,Liu Jing,Yu Yong.An annual load forecasting model based on gray neural network with multi-swarm fruit fly optimization algorithm[J].Journal of East China Jiaotong University,2015,32(1):98-104(in Chinese).
• [12]Specht D F.A general regression neural network[J].IEEE Transactions on Neural Networks,1991,2(11):568-576.
• [13]刘磊,杨鹏,刘作军.基于多源信息和广义回归神经网络的下肢运动模式识别[J].机器人,2015,37(3):310-317.Liu Lei,Yang Peng,Liu Zuojun.Lower limb locomotion modes recognition based on multiple-source information and general regression neural network[J].Robot,2015,37(3):310-317(in Chinese).
• [14]Shahlaei M,Sabet R,Ziari M B,et al.QSAR study of anthranilic acid sulfonamides as inhibitors of methionine aminopeptidase-2 using LS-SVM and GRNN based on principal components[J].European Journal of Medicinal Chemistry,2010,45(10):4499-4508.
• [15]Zhen H G,Jie W,Lu H Y,et al.A case study on a hybrid wind speed forecasting method using BP neural network[J].Knowledge-Based Systems,2011,24(7):1048-1056.
• [16]Panda B N,Raju B M V A,Biswal B B.Optimization of resistance spot welding parameters using differential evolution algorithm and GRNN[C]//8 th IEEE International Conference on Intelligent Systems and Control(ISCO).Coimbatore,INDIA,2014:50-55.
• [17]Zhao H,Guo S.Annual energy consumption forecasting based on PSOCA-GRNN model[J].Advances in Mechatronics and Control Engineering,2014(1):1-11.
• [18]Pan W C.A new fruit fly optimization algorithm:taking the financial distress model as an example[J].Knowledge-Based Systems,2012,26(3):69-74.
• [19]Li H,Guo Z,Li S,et al.A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm[J].Knowledge-Based Systems,2013,37(2):378-387.
• [20]Yuan X F,Dai X S,Zhao J Y.On a novel multi-swarm fruit fly optimization algorithm and its application[J].Applied Mathematics and Computation,2014,233(2):260-271.
• [21]Wang J J,Li L,Niu D X.An annual load forecasting model based on support vector regression with differential evolution algorithm[J].Applied Energy,2012,94(6):65-70.
• [22]Niu D X,Wang Y G,Desheng Dash Wu.Power load forecasting using support vector machine and ant colony optimization[J].Expert Systems with Applications,2010,37(3):2531-2539.