带扩展记忆的粒子群优化最小二乘支持向量机在中长期电力负荷预测中的应用

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z6): 41-43.

带扩展记忆的粒子群优化最小二乘支持向量机在中长期电力负荷预测中的应用

段其昌,周华鑫,曾勇,张广峰

重庆大学自动化学院重庆400044;重庆大学自动化学院重庆400044;重庆大学自动化学院重庆400044;重庆大学自动化学院重庆400044

出版日期:2018-11-16 发布日期:2018-11-16

Application of PSOEM-LSSVM in Medium and Long Term Power Load Forecasting

DUAN Qi-chang,ZHOU Hua-xin,ZENG Yong and ZHANG Guang-feng

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 针对中长期电力负荷预测,考虑了影响中长期电力负荷的各种因素,提出了一种带扩展记忆的粒子群优化算法(PSOEM)与最小二乘支持向量机(LSSVM)相结合的中长期负荷预测方法。PSOEM比传统PS0收敛速度更快,精度更高,具有更强的寻优能力,因此利用PSOEM算法对LSSVM参数进行优化选择,获得了较优的PSOEM-LSSVM预测模型。通过实例仿真表明,该方法与其他几种方法相比具有更高的预测精度和速度。

关键词: 中长期负荷预测,带扩展记忆粒子群,最小二乘支持向量机

Abstract: For medium and long term power load forecasting,considering the factors affecting medium and long-term power load,a method based on the particle swarm optimization with Extended Memory(PSOEM) and Least squares support vector machines(LSSVM) was proposed for medium and long -term load forecasting．PSOEM has more extensive capability of global optimization than PSO owing to higher accuracy and convergence rate,so it is used to optimize the parameters of the LSSVM,and obtains an optimum PSOEM-LSSVM model to forecast the load．An example simulation shows that this method can offer a higher precision and speed of forcasting than several other methods.

Key words: Medium and long term load forecasting,PSOEM,LSSVM

段其昌,周华鑫,曾勇,张广峰. 带扩展记忆的粒子群优化最小二乘支持向量机在中长期电力负荷预测中的应用[J]. 计算机科学, 2013, 40(Z6): 41-43. https://doi.org/

DUAN Qi-chang,ZHOU Hua-xin,ZENG Yong and ZHANG Guang-feng. Application of PSOEM-LSSVM in Medium and Long Term Power Load Forecasting[J]. Computer Science, 2013, 40(Z6): 41-43. https://doi.org/

参考文献

[1] 牛东晓,曹树华,等．电力负荷预测技术及其应用[M]．北京:中国电力出版社,1998
[2] 卜虎正,姚建刚,李文杰,等.中长期电力负荷预测的改进免疫粒子群算法[J].电力系统及其自动化学报,2011,3(3):139-144
[3] 王成山,杨军,张崇见.灰色系统理论在城市年用电量预测中的应用:不同预测方法的分析比较[J].电网技术,1999,3(2):15-18
[4] 王翠茹,孙辰军,杨静,等.改进残差灰色预测模型在负荷预测中的应用[J].电力系统及其自动化学报,2006,8(1):86-89
[5] 胡越黎,计惠杰．短期电力负荷预测的模糊神经网络方法[J]．应用科学学报,2009,27(1):79-83
[6] 高海龙,张国立.改进遗传神经网络及其在负荷预测中的应用[J].华北电力大学学报,2009,6(5):37-40
[7] 赵登福,王蒙,张讲社,等.基于支撑向量机方法的短期负荷预测[J].中国电机工程学报,2002,2(4):26-30
[8] 李元诚,方廷健,于尔铿.短期负荷预测的支持向量机方法研究[J].中国电机工程学报,2003,3(6):55-59
[9] 章健.电力系统复合模型与辨识[M].北京:中国电力出版社,2007
[10] Zhang Ming-guang.Short-term load forecasting based on sup-port vector machines regression[C]∥Proceedings of 2005International Conference on Machine Learning and Cybernetics．Lanzhou,China,2005,7:4310-4314
[11] Chen Bo-juen,Chang Ming-wei,Lin Chih-Jen.Load forecasting using support vector machines:a study on EUNITE competition 2001[J].IEEE Transactions on Power Systems,2004,9(4):1821-1830
[12] 孙翠娟.基于K型核函数的支持向量机[J].淮海工学院学报:自然科学版,2006,5(4):4-7
[13] Vapnik N.The Nature of Statistical Learning Theory[M].Newyork:Springer-Verlag,1995
[14] Suykens J A K,Vanddewalle J.Least squares support vectormachines classifiers[J].Neural Network Letters,1999,9(3):293-300
[15] Kennedy J,Eberhart R．Particle swarm optimization [C]∥IEEE International Conference on Neural Networks．Perth,Australia,1995,4:1942-1948

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed