基于云计算的电网负荷预测
|
摘要
负荷预测是电网管理的重要组成部分。准确及时的负荷预测对于制定经济合理的配电方案,提高电网运行的安全性和经济性,提高电能质量具有重要意义。为此,提出了一种基于人工鱼群和基因表达式编程的电力负荷预测函数挖掘算法。在此基础上,还提出了基于云计算的分布式负荷预测模型挖掘来解决大规模电力负荷预测问题。为了更好地提高模型的预测精度,在分布式负荷预测模型中引入了误差最小化交叉。实验结果表明,提出的算法在平均时间消耗、平均收敛数、预测精度以及并行计算性能方面具有优势。
Load forecasting is an important part of grid management. Accurate and timely load forecasting is of great significance for the formulation of economic and reasonable power distribution solutions,improving the safety and economy of power grid operation,and improving power quality. Therefore,this paper proposes an electric load forecasting function mining algorithm based on artificial fish school and gene expression programming. On this basis,also proposes a distributed load forecasting model mining based on cloud computing to solve large-scale power load forecasting problems. In order to improve the prediction accuracy of the model,the error minimization intersection is introduced in the distributed load forecasting model. The experimental results showed that the proposed algorithm had advantages in average time consumption,average convergence,prediction accuracy and parallel computing performance.
Load forecasting is an important part of grid management. Accurate and timely load forecasting is of great significance for the formulation of economic and reasonable power distribution solutions,improving the safety and economy of power grid operation,and improving power quality. Therefore,this paper proposes an electric load forecasting function mining algorithm based on artificial fish school and gene expression programming. On this basis,also proposes a distributed load forecasting model mining based on cloud computing to solve large-scale power load forecasting problems. In order to improve the prediction accuracy of the model,the error minimization intersection is introduced in the distributed load forecasting model. The experimental results showed that the proposed algorithm had advantages in average time consumption,average convergence,prediction accuracy and parallel computing performance.
引文
[1]姜代红,尹洪胜,张三友.采用基因表达式编程的自适应层次聚类方法[J].华侨大学学报(自然科学版),2018,39(3):435-438.Jiang Daihong,Yin Hongsheng,Zhang Sanyou. Adaptive hierarchi-cal clustering method based on gene expression programming[J].Journal of Huaqiao University(Natural Science),2018,39(3):435-438.
[2]王萍,李磊,胡聪,等.云计算环境下智能电网短期负荷预测方法[J].科学技术与工程,2018,18(7):153-158.Wang Ping,Li Lei,Hu Cong,et al. Short-term load forecastingmethod for smart grid in cloud computing environment[J]. ScienceTechnology and Engineering,2018,18(7):153-158.
[3]吴润泽,包正睿,宋雪莹,等.基于深度学习的电网短期负荷预测方法研究[J].现代电力,2018,35(2):43-48.Wu Runze,Bao Zhengrui,Song Xueying,et al. Research on short-term load forecasting method based on deep learning[J]. ModernElectric Power,2018,35(2):43-48.
[4]韦琦,杨明.改进神经网络算法的智能电网短期负荷预测[J].哈尔滨理工大学学报,2017,22(4):65-69.Wei Qi,Yang Ming. Short-term load forecasting of smart grid basedon improved neural network algorithm[J]. Journal of Harbin Uni-versity of Science and Technology,2017,22(4):65-69.
[5]王栋,蒋亮,江陈桢,等.基于混合GEP的配电低压台区综合评价算法[J].电测与仪表,2017,54(9):18-23.Wang Dong,Jiang Liang,Jiang Chenzhen,et al. A comprehensiveevaluation algorithm for distribution low-voltage stations based onhybrid GEP[J]. Electrical Measurement&Instrumentation,2017,54(9):18-23.
[6]张颖超,王雅晨,邓华,等.基于IAFSA-BPNN的短期风电功率预测[J].电力系统保护与控制,2017,45(7):58-63.Zhang Yingchao,Wang Yachen,Deng Hua,et al. Short-term windpower prediction based on IAFSA-BPNN[J]. Power System Protec-tion and Control,2017,45(7):58-63.
[7]万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.Wan Qiang,Wang Qingliang,Wang Ruihao,et al. Short-term loadforecasting of a regional power grid based on support vector ma-chine[J]. Power System and Clean Energy,2016,32(12):14-20.
[8]周东清,彭世玉,程春田,等.梯级水电站群长期优化调度云计算随机动态规划算法[J].中国电机工程学报,2017,37(12):3437-3448,3671.Zhou Dongqing,Peng Shiyu,Cheng Chuntian,et al. A stochasticdynamic programming algorithm for cloud computing of cascadedhydropower station groups[J]. Proceedings of the CSEE,2017,37(12):3437-3448,3671.
[9]钱志.基于改进型SVR的电网短期负荷预测[J].中国电力,2016,49(8):54-58.Qian Zhi. Short-term load forecasting of power grid based on im-proved SVR[J]. China Electric Power,2016,49(8):54-58.
[10]周建中,吴巍,卢鹏,等.响应电网负荷需求的梯级水电站短期调峰调度[J].水力发电学报,2016,35(6):1-10.Zhou Jianzhong,Wu Wei,Lu Peng,et al. Short-term peak-shiftscheduling of cascade hydropower stations in response to grid loaddemand[J]. Journal of Hydroelectric Engineering,2016,35(6):1-10.
[11]纪昌明,吴昊,黄锋,等.基于CAFSA的水库发电优化调度双层并行计算[J].中国农村水利水电,2016(5):183-188,192.Ji Changming,Wu Hao,Huang Feng,et al. Two-tier parallel com-puting of reservoir power generation optimization scheduling basedon CAFSA[J]. China Rural Water and Hydropower,2016(5):183-188,192.
[12]王永翔,陈国初.基于改进鱼群优化支持向量机的短期风电功率预测[J].电测与仪表,2016,53(3):80-84.Wang Yongxiang,Chen Guochu. Short-term wind power predictionbased on improved fish swarm optimization support vector machine[J]. Electrical Measurement&Instrumentation,2016,53(3):80-84.
[13]刘晓悦,郭强.海量用电数据并行聚类分析[J].辽宁工程技术大学学报(自然科学版),2016,35(1):76-80.Liu Xiaoyue,Guo Qiang. Parallel clustering analysis of massive e-lectricity data[J]. Journal of Liaoning Technical University(Natu-ral Science Edition),2016,35(1):76-80.
[14]苏尤丽.基于人工神经网络的微电网短期负荷预测[J].内蒙古师范大学学报(自然科学汉文版),2016,45(1):43-45.Su Youli. Short-term load forecasting of microgrid based on artifi-cial neural network[J]. Journal of Inner Mongolia Normal Univer-sity(Natural Science Edition),2016,45(1):43-45.
[15]张建宾,章健,张超慧,等.基于基因表达式编程的电力负荷建模[J].电测与仪表,2015,52(24):96-100.Zhang Jianbin,Zhang Jian,Zhang Chaohui,et al. Electric loadmodeling based on gene expression programming[J]. ElectricalMeasurement&Instrumentation,2015,52(24):96-100.
[16]王昕,黄柯,郑益慧,等.改进的人工鱼群算法在电力系统经济负荷分配中的应用[J].水电能源科学,2015,33(9):205-208.Wang Xin,Huang Ke,Zheng Yihui,et al. Application of improvedartificial fish swarm algorithm in power system economic load dis-tribution[J]. International Journal Hydroelectric Energy,2015,33(9):205-208.
[17]刘念,张清鑫,刘海涛.基于核函数极限学习机的微电网短期负荷预测方法[J].电工技术学报,2015,30(8):218-224.Liu Nian,Zhang Qingxin,Liu Haitao. A short-term load forecastingmethod for microgrid based on kernel function extreme learningmachine[J]. Transactions of China Electrotechnical Society,2015,30(8):218-224.
[2]王萍,李磊,胡聪,等.云计算环境下智能电网短期负荷预测方法[J].科学技术与工程,2018,18(7):153-158.Wang Ping,Li Lei,Hu Cong,et al. Short-term load forecastingmethod for smart grid in cloud computing environment[J]. ScienceTechnology and Engineering,2018,18(7):153-158.
[3]吴润泽,包正睿,宋雪莹,等.基于深度学习的电网短期负荷预测方法研究[J].现代电力,2018,35(2):43-48.Wu Runze,Bao Zhengrui,Song Xueying,et al. Research on short-term load forecasting method based on deep learning[J]. ModernElectric Power,2018,35(2):43-48.
[4]韦琦,杨明.改进神经网络算法的智能电网短期负荷预测[J].哈尔滨理工大学学报,2017,22(4):65-69.Wei Qi,Yang Ming. Short-term load forecasting of smart grid basedon improved neural network algorithm[J]. Journal of Harbin Uni-versity of Science and Technology,2017,22(4):65-69.
[5]王栋,蒋亮,江陈桢,等.基于混合GEP的配电低压台区综合评价算法[J].电测与仪表,2017,54(9):18-23.Wang Dong,Jiang Liang,Jiang Chenzhen,et al. A comprehensiveevaluation algorithm for distribution low-voltage stations based onhybrid GEP[J]. Electrical Measurement&Instrumentation,2017,54(9):18-23.
[6]张颖超,王雅晨,邓华,等.基于IAFSA-BPNN的短期风电功率预测[J].电力系统保护与控制,2017,45(7):58-63.Zhang Yingchao,Wang Yachen,Deng Hua,et al. Short-term windpower prediction based on IAFSA-BPNN[J]. Power System Protec-tion and Control,2017,45(7):58-63.
[7]万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.Wan Qiang,Wang Qingliang,Wang Ruihao,et al. Short-term loadforecasting of a regional power grid based on support vector ma-chine[J]. Power System and Clean Energy,2016,32(12):14-20.
[8]周东清,彭世玉,程春田,等.梯级水电站群长期优化调度云计算随机动态规划算法[J].中国电机工程学报,2017,37(12):3437-3448,3671.Zhou Dongqing,Peng Shiyu,Cheng Chuntian,et al. A stochasticdynamic programming algorithm for cloud computing of cascadedhydropower station groups[J]. Proceedings of the CSEE,2017,37(12):3437-3448,3671.
[9]钱志.基于改进型SVR的电网短期负荷预测[J].中国电力,2016,49(8):54-58.Qian Zhi. Short-term load forecasting of power grid based on im-proved SVR[J]. China Electric Power,2016,49(8):54-58.
[10]周建中,吴巍,卢鹏,等.响应电网负荷需求的梯级水电站短期调峰调度[J].水力发电学报,2016,35(6):1-10.Zhou Jianzhong,Wu Wei,Lu Peng,et al. Short-term peak-shiftscheduling of cascade hydropower stations in response to grid loaddemand[J]. Journal of Hydroelectric Engineering,2016,35(6):1-10.
[11]纪昌明,吴昊,黄锋,等.基于CAFSA的水库发电优化调度双层并行计算[J].中国农村水利水电,2016(5):183-188,192.Ji Changming,Wu Hao,Huang Feng,et al. Two-tier parallel com-puting of reservoir power generation optimization scheduling basedon CAFSA[J]. China Rural Water and Hydropower,2016(5):183-188,192.
[12]王永翔,陈国初.基于改进鱼群优化支持向量机的短期风电功率预测[J].电测与仪表,2016,53(3):80-84.Wang Yongxiang,Chen Guochu. Short-term wind power predictionbased on improved fish swarm optimization support vector machine[J]. Electrical Measurement&Instrumentation,2016,53(3):80-84.
[13]刘晓悦,郭强.海量用电数据并行聚类分析[J].辽宁工程技术大学学报(自然科学版),2016,35(1):76-80.Liu Xiaoyue,Guo Qiang. Parallel clustering analysis of massive e-lectricity data[J]. Journal of Liaoning Technical University(Natu-ral Science Edition),2016,35(1):76-80.
[14]苏尤丽.基于人工神经网络的微电网短期负荷预测[J].内蒙古师范大学学报(自然科学汉文版),2016,45(1):43-45.Su Youli. Short-term load forecasting of microgrid based on artifi-cial neural network[J]. Journal of Inner Mongolia Normal Univer-sity(Natural Science Edition),2016,45(1):43-45.
[15]张建宾,章健,张超慧,等.基于基因表达式编程的电力负荷建模[J].电测与仪表,2015,52(24):96-100.Zhang Jianbin,Zhang Jian,Zhang Chaohui,et al. Electric loadmodeling based on gene expression programming[J]. ElectricalMeasurement&Instrumentation,2015,52(24):96-100.
[16]王昕,黄柯,郑益慧,等.改进的人工鱼群算法在电力系统经济负荷分配中的应用[J].水电能源科学,2015,33(9):205-208.Wang Xin,Huang Ke,Zheng Yihui,et al. Application of improvedartificial fish swarm algorithm in power system economic load dis-tribution[J]. International Journal Hydroelectric Energy,2015,33(9):205-208.
[17]刘念,张清鑫,刘海涛.基于核函数极限学习机的微电网短期负荷预测方法[J].电工技术学报,2015,30(8):218-224.Liu Nian,Zhang Qingxin,Liu Haitao. A short-term load forecastingmethod for microgrid based on kernel function extreme learningmachine[J]. Transactions of China Electrotechnical Society,2015,30(8):218-224.