预测径流式水电站发量。针对径流式水电站发电量变化的随机性及水力发电系统的复杂非线性，提出一种基于相空间重构小波神经网络的径流式水电站发电量预测模型，并借助具有全局搜索能力的改进粒子群优化算法对小波神经网络特征参数进行优化，提高模型的精度和泛化能力。结果表明: 相空间重构小波神经网络模型的预测平均相对误差约为 8．7%，相关系数达到 0．81，误差分析指标优于传统神经网络预测模型，在多步预测情形下模型的收敛性和稳定性得到较为明显增强，能够准确进行发电量预测。
Abstract
According to the random and complex nonlinear characteristics of the power generation of runoff hydropower station, the paper presents a new model of runoff-hydro station based on phase-space reconstruction wavelet neural network model. In order to enhance the global search ability of the model, parameters of the wavelet neural network are optimized by using the improved particle swarm optimization algorithm to overcome the randomness of the model parameters selection. Results show that the relative error of the improved particle swarm optimization wavelet neural network model is about 8.7%, the correlation coefficient is 0.81, and the other error analysis indexes are better than the traditional BP neural network forecasting model. The model proposes in this paper have a more obvious accuracy, convergence and stability enhancements in multi-step predictions, which can accurately forecast the generating capacity.
基金
国家科技支撑计划项目( 2012BAD10B02) ; 中央高校基本科研业务费专项资金( 22050205) ; 陕西省水利科技项目( SLKJ-2013-14)
{{custom_fund}}
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李树山,廖胜利,李刚,等.大规模小水电群一体化发电计划编制方法[J].中国电机工程学报,2012,(13):29-35+188.
[2] 吴德会,虞耀君.基于LS-SVM的小水电站年发电量智能预测模型[J].中国农村水利水电,2007,(02):93-95+98.
[3] Monteiro C, Ramirez-Rosado I J, Fernandez-Jimenez L A. Short-term forecasting model for aggregated regional hydropower generation[J].Energy Conversion and Management,2014,(88):231-238.
[4] Moreno J. Hydraulic plant generation forecasting in Colombian power market using ANFIS [J].Energy Economics, 2009,(31): 450-455.
[5] 王保国,刘淑艳,钱耕,等.一种小波神经网络与遗传算法结合的优化方法[J].航空动力学报,2008,(11):1953-1960.
[6] Kreinovich V, Sirisaengtaksin O, Cabrera S. Wavelet neural networks are asymptotically optimal approximators for functions of one variable [C]//Neural Networks, 1994.IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on. IEEE, 1994, 01: 299-304.
[7] 何自立,王云霏,马孝义,杨建国.基于改进PSO-WNN模型的管网余氯预测研究[J].中国农村水利水电,2015,(02):86-88+92.
[8] 高大启.有教师的线性基本函数前向三层神经网络结构研究[J].计算机学报,1998,01:80-86.
PDF(334 KB)
鄂公网安备 42010602001274号 鄂ICP备14015464号-1