基于GOA-SVM的短期负荷预测
|
摘要
支持向量机是借助于凸优化技术的统计学习方法,与传统神经网络相比,泛化错误率低并且结果易于解释。将支持向量机用于负荷预测时,参数选择不准确会导致预测性能较差。提出一种基于蚱蜢优化算法的支持向量机短期负荷预测方法,以某地区负荷、天气等历史数据对SVM进行训练,并通过GOA优化选取支持向量机参数,然后以得到的最优参数建立GOA-SVM负荷预测模型。算例分析表明,GOA-SVM预测模型比GA-SVM和PSO-SVM模型有更好的收敛性能,且预测精度更高。
Support vector machine( SVM) is a statistical learning method based on convex optimization technique,compared with traditional neural network,the generalization error rate is low and the result is easy to explain. When SVM is applied to load forecasting,the inaccurate selection of parameters will result in poor prediction performance. A short-term load forecasting method of support vector machine based on grasshopper optimization algorithm is proposed in this paper.SVM is trained with historical data such as load and weather in a certain area. The parameters of support vector machine are selected by GOA,and then the GOA-SVM load forecasting model is established with the obtained optimal parameters.The example analysis shows that the GOA-SVM model has better convergence performance and higher prediction accuracy than GA-SVM and PSO-SVM models.
Support vector machine( SVM) is a statistical learning method based on convex optimization technique,compared with traditional neural network,the generalization error rate is low and the result is easy to explain. When SVM is applied to load forecasting,the inaccurate selection of parameters will result in poor prediction performance. A short-term load forecasting method of support vector machine based on grasshopper optimization algorithm is proposed in this paper.SVM is trained with historical data such as load and weather in a certain area. The parameters of support vector machine are selected by GOA,and then the GOA-SVM load forecasting model is established with the obtained optimal parameters.The example analysis shows that the GOA-SVM model has better convergence performance and higher prediction accuracy than GA-SVM and PSO-SVM models.
引文
[1]康重庆,等.电力系统负荷预测[M].中国电力出版社,2017.
[2]赵希正.中国电力负荷特性分析与预测[M].中国电力出版社,2002.
[3]李明干,孙建利,刘沛.基于卡尔曼滤波的电力系统短期负荷预测[J].继电器,2004,32(4):9-12.Li Minggan,Sun Jianli,Liu Pei. Short-term load forecast of power system based on Kalman filter[J]. Relay,2004,32(4):9-12.
[4]马静波,杨洪耕.自适应卡尔曼滤波在电力系统短期负荷预测中的应用[J].电网技术,2005,29(1):75-79.Ma Jingbo,Yang Honggeng. Application of adaptive Kalman filter in power system short-term load forecasting[J]. Power System Technology,2005,29(1):75-79.
[5]赵登福,吴娟,刘昱,等.基于事例推理的短期负荷预测[J].西安交通大学学报,2003,37(6):608-611.Zhao Dengfu,Wu Juan,Liu Yu,et al. Case-based reasoning for short term load forecasting[J]. Journal of Xi’an Jiao Tong University,2003,37(6):608-611.
[6]徐进东,丁晓群,邓勇.基于相似日的线性外推短期负荷预测[J],继电器,2005,33(7):37-40.Xu Jindong,Ding Xiaoqun,Deng Yong. Short-term load forecast using linear extrapolation based on similar historical day data[J]. Relay,2005,33(7):37-40.
[7]方鸽飞,胡长洪,郑奕辉,等.考虑夏季气象因素的短期负荷预测方法研究[J].电力系统保护与控制,2010,38(22):100-104.Fang Gefei,Hu Changhong,Zheng Yihui,et al. Studu on the method of short-term load forecasting considering summer weather factors[J].Power System Protection and Control,2010,38(22):100-104.
[8]彭显刚,胡松峰,吕大勇.基于RBF神经网络的短期负荷预测方法综述[J].电力系统保护与控制,2011,39(17):144-148.Peng Xiangang,Hu Songfeng,Lv Dayong. Review on grid short-term load forecasting methods based on RBF neural network[J]. Power System Protection and Control,2011,39(17):144-148.
[9]刘荣,方鸽飞.改进Elman神经网络的综合气象短期负荷预测[J].电力系统保护与控制,2012,40(22):113-117.Liu Rong,Fang Gefei. Short-term load forecasting with comprehensive weather factors based on improved Elman neural nerwork[J]. Power System Protection and Control,2012,40(22):113-117.
[10]周英,尹邦德,任铃,等.基于BP神经网络的电网短期负荷预测模型研究[J].电测与仪表,2011,48(42):68-71.Zhou Ying,Yin Bangde,Ren Ling,et al. Study on electricity shortterm load forecast based on BP neural network[J]. Electrical Measurement&Instrumentation,2011,48(542):68-71.
[11]潘峰,程浩忠,杨镜非,等.基于支持向量机的电力系统短期负荷预测[J].电网技术,2004,28(21):39-42.Pan Feng,Cheng Haozhong,Yang Jingfei,et al. Power system shortterm load forecasting based on support vector machine[J]. Power System Technology,2004,28(21):39-42.
[12]王小君,毕圣,徐云鹍,等.基于数据挖掘技术和支持向量机的短期负荷预测[J].电测与仪表,2016,53(10):62-67.Wang Xiaojun,Bi Sheng,Xu Yunkun,et al. Short-term load forecasting based on support vector machine and data mining technology[J].Electrical Measurement&Instrumentation,2016,53(10):62-67.
[13]刘宝英,杨仁刚.基于主成分分析的最小二乘支持向量机短期负荷预测模型[J].电力自动化设备,2008,28(11):13-17.Liu Baoying,Yang Rengang. Short-term load forecasting model based on LS-SVM with PCA[J]. Electric Power Automation Equipment,2008,28(11):13-17.
[14]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.Wu Jinglong,Yang Shuxia,Liu Chengshui. Parameter selection for support vector machines based on genetic alrorithms to short-term power load forecasting[J]. Journal of Central South University(Science and Technology),2009,40(1):180-184.
[15]Wenchuan Wang,Dongmei Xu,Kwokwing Chau,et al. Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD[J]. Journal of Hydroinformatics,2013,15(4):1377-1390.
[16]嵇灵,牛东晓,吴焕苗.基于贝叶斯框架和回声状态网络的日最大负荷预测研究[J].电网技术,2012,36(11):82-86.Ji Ling,Niu Dongxiao,Wu Huanmiao. Daily peak load forecasting based on bayesian framework and echo state network[J]. Power System Technology,2012,36(11):82-86.
[17]刘晓娟,方建安.基于双修正因子的模糊时间序列日最大负荷预测[J].中国电力,2013,46(10):115-118.Liu Xiaojuan,Fang Jian'an. Maximum load foaecasting based on a bifactor revised fuzzy time series model[J]. Electric Power,2013,46(10):115-118.
[2]赵希正.中国电力负荷特性分析与预测[M].中国电力出版社,2002.
[3]李明干,孙建利,刘沛.基于卡尔曼滤波的电力系统短期负荷预测[J].继电器,2004,32(4):9-12.Li Minggan,Sun Jianli,Liu Pei. Short-term load forecast of power system based on Kalman filter[J]. Relay,2004,32(4):9-12.
[4]马静波,杨洪耕.自适应卡尔曼滤波在电力系统短期负荷预测中的应用[J].电网技术,2005,29(1):75-79.Ma Jingbo,Yang Honggeng. Application of adaptive Kalman filter in power system short-term load forecasting[J]. Power System Technology,2005,29(1):75-79.
[5]赵登福,吴娟,刘昱,等.基于事例推理的短期负荷预测[J].西安交通大学学报,2003,37(6):608-611.Zhao Dengfu,Wu Juan,Liu Yu,et al. Case-based reasoning for short term load forecasting[J]. Journal of Xi’an Jiao Tong University,2003,37(6):608-611.
[6]徐进东,丁晓群,邓勇.基于相似日的线性外推短期负荷预测[J],继电器,2005,33(7):37-40.Xu Jindong,Ding Xiaoqun,Deng Yong. Short-term load forecast using linear extrapolation based on similar historical day data[J]. Relay,2005,33(7):37-40.
[7]方鸽飞,胡长洪,郑奕辉,等.考虑夏季气象因素的短期负荷预测方法研究[J].电力系统保护与控制,2010,38(22):100-104.Fang Gefei,Hu Changhong,Zheng Yihui,et al. Studu on the method of short-term load forecasting considering summer weather factors[J].Power System Protection and Control,2010,38(22):100-104.
[8]彭显刚,胡松峰,吕大勇.基于RBF神经网络的短期负荷预测方法综述[J].电力系统保护与控制,2011,39(17):144-148.Peng Xiangang,Hu Songfeng,Lv Dayong. Review on grid short-term load forecasting methods based on RBF neural network[J]. Power System Protection and Control,2011,39(17):144-148.
[9]刘荣,方鸽飞.改进Elman神经网络的综合气象短期负荷预测[J].电力系统保护与控制,2012,40(22):113-117.Liu Rong,Fang Gefei. Short-term load forecasting with comprehensive weather factors based on improved Elman neural nerwork[J]. Power System Protection and Control,2012,40(22):113-117.
[10]周英,尹邦德,任铃,等.基于BP神经网络的电网短期负荷预测模型研究[J].电测与仪表,2011,48(42):68-71.Zhou Ying,Yin Bangde,Ren Ling,et al. Study on electricity shortterm load forecast based on BP neural network[J]. Electrical Measurement&Instrumentation,2011,48(542):68-71.
[11]潘峰,程浩忠,杨镜非,等.基于支持向量机的电力系统短期负荷预测[J].电网技术,2004,28(21):39-42.Pan Feng,Cheng Haozhong,Yang Jingfei,et al. Power system shortterm load forecasting based on support vector machine[J]. Power System Technology,2004,28(21):39-42.
[12]王小君,毕圣,徐云鹍,等.基于数据挖掘技术和支持向量机的短期负荷预测[J].电测与仪表,2016,53(10):62-67.Wang Xiaojun,Bi Sheng,Xu Yunkun,et al. Short-term load forecasting based on support vector machine and data mining technology[J].Electrical Measurement&Instrumentation,2016,53(10):62-67.
[13]刘宝英,杨仁刚.基于主成分分析的最小二乘支持向量机短期负荷预测模型[J].电力自动化设备,2008,28(11):13-17.Liu Baoying,Yang Rengang. Short-term load forecasting model based on LS-SVM with PCA[J]. Electric Power Automation Equipment,2008,28(11):13-17.
[14]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.Wu Jinglong,Yang Shuxia,Liu Chengshui. Parameter selection for support vector machines based on genetic alrorithms to short-term power load forecasting[J]. Journal of Central South University(Science and Technology),2009,40(1):180-184.
[15]Wenchuan Wang,Dongmei Xu,Kwokwing Chau,et al. Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD[J]. Journal of Hydroinformatics,2013,15(4):1377-1390.
[16]嵇灵,牛东晓,吴焕苗.基于贝叶斯框架和回声状态网络的日最大负荷预测研究[J].电网技术,2012,36(11):82-86.Ji Ling,Niu Dongxiao,Wu Huanmiao. Daily peak load forecasting based on bayesian framework and echo state network[J]. Power System Technology,2012,36(11):82-86.
[17]刘晓娟,方建安.基于双修正因子的模糊时间序列日最大负荷预测[J].中国电力,2013,46(10):115-118.Liu Xiaojuan,Fang Jian'an. Maximum load foaecasting based on a bifactor revised fuzzy time series model[J]. Electric Power,2013,46(10):115-118.