基于信息粒化和支持向量机的母线等效负荷波动预测方法
|
摘要
随着接入母线多源功率的不断增加,使电网更加合理安排调度计划有了较大的难度。首先,提出了构建一种母线等效负荷模型,将接入母线的不可调发电功率等效为负的负荷功率,使不可调发电功率和母线负荷功率等效为母线的等效负荷功率。然后,获取等效负荷的历史数据,作为母线等效负荷预测模型的输入。最后,基于模糊信息粒化和支持向量机进行母线等效负荷波动预测。实例验证表明,等效负荷预测值相比单独预测不可调多源功率及母线负荷之后的等效值,精确度有所提高。同时预测结果可以更加清楚地了解各母线不可调等效负荷的波动范围,有利于地调系统更好地计划可调小容量发电的出力,并为省调更合理地安排新能源消纳及全网可调发电计划提供预测基础。
The constant increase of multi-source power connected to bus causes a larger difficulty to the more rational scheduling of power grid. First,an equivalent load model of bus is constructed by making an equivalence of nonadjustable generation power to negative load power. Then,the acquired history data of equivalent load are used as input of the prediction model for the equivalent load of bus. Finally,the equivalent load fluctuation of bus is predicted based on fuzzy information granulation(FIG)and support vector machine. The results of a case study show that the accuracy of the predicted value of equivalent load is higher than that of the equivalent value after respective predictions of non adjustable multi-source power and bus load. Meanwhile,the fluctuation range of nonadjustable equivalent load of each bus can be clearly acquired from the prediction results,which is conducive to better planning the adjustable small capacity generation power for the district-level power system;furthermore,a prediction basis can be provided so that the renewable energy accommodation and network-wide adjustable generation power planningcan be more rationally scheduled for the province-level power system.
The constant increase of multi-source power connected to bus causes a larger difficulty to the more rational scheduling of power grid. First,an equivalent load model of bus is constructed by making an equivalence of nonadjustable generation power to negative load power. Then,the acquired history data of equivalent load are used as input of the prediction model for the equivalent load of bus. Finally,the equivalent load fluctuation of bus is predicted based on fuzzy information granulation(FIG)and support vector machine. The results of a case study show that the accuracy of the predicted value of equivalent load is higher than that of the equivalent value after respective predictions of non adjustable multi-source power and bus load. Meanwhile,the fluctuation range of nonadjustable equivalent load of each bus can be clearly acquired from the prediction results,which is conducive to better planning the adjustable small capacity generation power for the district-level power system;furthermore,a prediction basis can be provided so that the renewable energy accommodation and network-wide adjustable generation power planningcan be more rationally scheduled for the province-level power system.
引文
[1]孙谦,姚建刚,赵俊,等(Sun Qian,Yao Jiangang,Zhao Jun,et al).基于最优交集相似日选取的短期母线负荷综合预测(Short-term bus load integrated forecasting based on selecting optimal intersection similar days)[J].中国电机工程学报(Proceedings of the CSEE),2013,33(4):126-134.
[2]李博,门德月,严亚勤,等(Li Bo,Men Deyue,Yan Yaqin,et al).基于数值天气预报的母线负荷预测(Bus load forecasting based on numerical weather prediction)[J].电力系统自动化(Automation of Electric Power Systems),2015,39(1):137-140.
[3]韩锋(Han Feng).基于负荷分配与最小二乘的母线负荷预测研究(The Study on Bus Load Forecasting Based on load Distribution and the Least Square Model)[D].济南:山东大学电气工程学院(Jinan:College of Electrical Engineering,Shandong University),2016.
[4]董瑞(Dong Rui).基于聚类分析的母线负荷预测研究(Research of Bus Load Forecasting Based on Clustering Analysis)[D].杭州:浙江大学电气工程学院(Hangzhou:College of Electrical Engineering,Zhejiang University),2015.
[5]龙丹丽,黎静华,韦化(Long Danli,Li Jinghua,Wei Hua).粗糙集法解多环境因素影响的母线负荷预测问题(Solution of multi environmental factor-influenced bus load forecasting by rough set method)[J].电网技术(Power System Technology),2013,37(5):1335-1340.
[6]尹星露,肖先勇,孙晓璐(Yin Xinglu,Xiao Xianyong,Sun Xiaolu).母线负荷异常数据复杂不确定性检测与基于综合云的修正模型(Complex uncertainty detection and synthesized cloud correction model for abnormal bus load data)[J].电力自动化设备(Electric Power Automation Equipment),2015,35(6):117-122.
[7]杨理才,张文磊,周勇,等(Yang Licai,Zhang Wenlei,Zhou Yong,et al).间接预测法在母线负荷预测中的应用(Application of indirect forecasting method in bus load forecasting)[J].电网技术(Power System Technology),2011,35(12):177-182.
[8]颜宏文,李欣然(Yan Hongwen,Li Xinran).基于差分进化的含分布式电源母线净负荷预测(Uncertainty analysis on net load forecasting for busbar containing distributed energy sources based on differential evolution and rough sets reduction)[J].电网技术(Power System Technology),2013,37(6):1602-1606.
[9]李宇佳(Li Yujia).考虑风电并网的短期负荷预测方法研究(Research on Short-term Load Forecasting by Considering Grid-connected Wind Power)[D].北京:华北电力大学电气与电子工程学院(Beijing:School of Electrical and Electronic Engineering,North China Electric Power University),2011.
[10]朱泽磊,程鑫,杨桂钟(Zhu Zelei,Cheng Xin,Yang Guizhong).基于母线负荷预测改进的省地协同发电计划优化方法(Collaborative scheduling optimization method for provincial grid and regional grid based on refined busload forecast)[J].中国电机工程学报(Proceedings of the CSEE),2017,37(3):665-675.
[11]王贺,胡志坚,仉梦林(Wang He,Hu Zhijian,Zhang Menglin).基于模糊信息粒化和最小二乘支持向量机的风电功率波动范围组合预测模型(A combined forecasting model for range of wind power fluctuation based on fuzzy information granulation and least squares support vector machine)[J].电工技术学报(Transactions of China Electrotechnical Society),2014,29(12):218-224.
[12] Huang Wenwei,Zhao Yun,QiziHuangpeng. SOC prediction of Lithium battery based on fuzzy information granulation and support vector regression[C]//4th International Conference on Electrical and Electronic Engineering. Ankara,Turkey,2017:177-180.
[13] Yu Fusheng,Cai Ruiqiong. Optimized fuzzy information granulation of temporal data[C]//7th International Conference on FSKD. Yatai,China,2010:419-423.
[14]刘爱国,薛云涛,胡江鹭,等(Liu Aiguo,XueYuntao,Hu Jianglu,et al).基于GA优化SVM的风电功率的超短期预测(Ultra-short-term wind power forecasting based on SVM optimized by GA)[J].电力系统保护与控制(Power System Protection and Control),2015,43(2):90-95.
[15]王继东,宋智林,冉冉(Wang Jidong,Song Zhilin,Ran Ran).基于改进支持向量机算法的光伏发电短期功率滚动预测(Short-term photovoltaic power generation rolling forecast based on optimized SVM)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2016,28(11):9-13.
[16]李霄,王昕,郑益慧,等(Li Xiao,Wang Xin,Zheng Yihui,et al).基于改进最小二乘支持向量机和预测误差校正的短期风电负荷预测(Short-term wind load forecasting based on improved LSSVM and error forecasting correction)[J].电力系统保护与控制(Power System Protection and Control),2015,43(11):63-69.
[17]王贺,胡志坚,张翌晖,等(Wang He,Hu Zhijian,Zhang Yihui,et al).基于聚类经验模态分解和最小二乘支持向量机的短期风速组合预测(A hybrid model for shortterm wind speed forecasting based on ensemble empirical mode decomposition and least squares support vector machines)[J].电工技术学报(Transactions of China Electrotechnical Society),2014,29(4):237-245.
[18]王宁,谢敏,邓佳梁,等(Wang Ning,Xie Min,Deng Jialiang,et al).基于支持向量机回归组合模型的中长期降温负荷预测(Mid-long term temperature-lowering load forecasting based on combination of support vector machine and multiple regression)[J].电力系统保护与控制(Power System Protection and Control),2016,44(3):92-97.
[19]王东,史晓霞,尹交英(Wang Dong,Shi Xiaoxia,Yin Jiaoying).不同核函数的支持向量机用于空调负荷预测的对比研究(Prediction on hourly load of air conditioning by RBF support vector machine)[J].电工技术学报(Transactions of China ElectrotechnicalSociety),2015,30(增刊1):531-535.
[2]李博,门德月,严亚勤,等(Li Bo,Men Deyue,Yan Yaqin,et al).基于数值天气预报的母线负荷预测(Bus load forecasting based on numerical weather prediction)[J].电力系统自动化(Automation of Electric Power Systems),2015,39(1):137-140.
[3]韩锋(Han Feng).基于负荷分配与最小二乘的母线负荷预测研究(The Study on Bus Load Forecasting Based on load Distribution and the Least Square Model)[D].济南:山东大学电气工程学院(Jinan:College of Electrical Engineering,Shandong University),2016.
[4]董瑞(Dong Rui).基于聚类分析的母线负荷预测研究(Research of Bus Load Forecasting Based on Clustering Analysis)[D].杭州:浙江大学电气工程学院(Hangzhou:College of Electrical Engineering,Zhejiang University),2015.
[5]龙丹丽,黎静华,韦化(Long Danli,Li Jinghua,Wei Hua).粗糙集法解多环境因素影响的母线负荷预测问题(Solution of multi environmental factor-influenced bus load forecasting by rough set method)[J].电网技术(Power System Technology),2013,37(5):1335-1340.
[6]尹星露,肖先勇,孙晓璐(Yin Xinglu,Xiao Xianyong,Sun Xiaolu).母线负荷异常数据复杂不确定性检测与基于综合云的修正模型(Complex uncertainty detection and synthesized cloud correction model for abnormal bus load data)[J].电力自动化设备(Electric Power Automation Equipment),2015,35(6):117-122.
[7]杨理才,张文磊,周勇,等(Yang Licai,Zhang Wenlei,Zhou Yong,et al).间接预测法在母线负荷预测中的应用(Application of indirect forecasting method in bus load forecasting)[J].电网技术(Power System Technology),2011,35(12):177-182.
[8]颜宏文,李欣然(Yan Hongwen,Li Xinran).基于差分进化的含分布式电源母线净负荷预测(Uncertainty analysis on net load forecasting for busbar containing distributed energy sources based on differential evolution and rough sets reduction)[J].电网技术(Power System Technology),2013,37(6):1602-1606.
[9]李宇佳(Li Yujia).考虑风电并网的短期负荷预测方法研究(Research on Short-term Load Forecasting by Considering Grid-connected Wind Power)[D].北京:华北电力大学电气与电子工程学院(Beijing:School of Electrical and Electronic Engineering,North China Electric Power University),2011.
[10]朱泽磊,程鑫,杨桂钟(Zhu Zelei,Cheng Xin,Yang Guizhong).基于母线负荷预测改进的省地协同发电计划优化方法(Collaborative scheduling optimization method for provincial grid and regional grid based on refined busload forecast)[J].中国电机工程学报(Proceedings of the CSEE),2017,37(3):665-675.
[11]王贺,胡志坚,仉梦林(Wang He,Hu Zhijian,Zhang Menglin).基于模糊信息粒化和最小二乘支持向量机的风电功率波动范围组合预测模型(A combined forecasting model for range of wind power fluctuation based on fuzzy information granulation and least squares support vector machine)[J].电工技术学报(Transactions of China Electrotechnical Society),2014,29(12):218-224.
[12] Huang Wenwei,Zhao Yun,QiziHuangpeng. SOC prediction of Lithium battery based on fuzzy information granulation and support vector regression[C]//4th International Conference on Electrical and Electronic Engineering. Ankara,Turkey,2017:177-180.
[13] Yu Fusheng,Cai Ruiqiong. Optimized fuzzy information granulation of temporal data[C]//7th International Conference on FSKD. Yatai,China,2010:419-423.
[14]刘爱国,薛云涛,胡江鹭,等(Liu Aiguo,XueYuntao,Hu Jianglu,et al).基于GA优化SVM的风电功率的超短期预测(Ultra-short-term wind power forecasting based on SVM optimized by GA)[J].电力系统保护与控制(Power System Protection and Control),2015,43(2):90-95.
[15]王继东,宋智林,冉冉(Wang Jidong,Song Zhilin,Ran Ran).基于改进支持向量机算法的光伏发电短期功率滚动预测(Short-term photovoltaic power generation rolling forecast based on optimized SVM)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2016,28(11):9-13.
[16]李霄,王昕,郑益慧,等(Li Xiao,Wang Xin,Zheng Yihui,et al).基于改进最小二乘支持向量机和预测误差校正的短期风电负荷预测(Short-term wind load forecasting based on improved LSSVM and error forecasting correction)[J].电力系统保护与控制(Power System Protection and Control),2015,43(11):63-69.
[17]王贺,胡志坚,张翌晖,等(Wang He,Hu Zhijian,Zhang Yihui,et al).基于聚类经验模态分解和最小二乘支持向量机的短期风速组合预测(A hybrid model for shortterm wind speed forecasting based on ensemble empirical mode decomposition and least squares support vector machines)[J].电工技术学报(Transactions of China Electrotechnical Society),2014,29(4):237-245.
[18]王宁,谢敏,邓佳梁,等(Wang Ning,Xie Min,Deng Jialiang,et al).基于支持向量机回归组合模型的中长期降温负荷预测(Mid-long term temperature-lowering load forecasting based on combination of support vector machine and multiple regression)[J].电力系统保护与控制(Power System Protection and Control),2016,44(3):92-97.
[19]王东,史晓霞,尹交英(Wang Dong,Shi Xiaoxia,Yin Jiaoying).不同核函数的支持向量机用于空调负荷预测的对比研究(Prediction on hourly load of air conditioning by RBF support vector machine)[J].电工技术学报(Transactions of China ElectrotechnicalSociety),2015,30(增刊1):531-535.