电力调度交换机短期负荷智能预测方法研究
|
摘要
针对电力调度交换机短期负荷预测,采用传统方法受到外界因素影响,导致预测效率较低,为了解决该问题,提出了基于神经网络短期负荷智能预测。综合时间和气温数据,设计训练样本选取流程。根据选取结果,分析神经网络接入方式,通过明确输入、输出和隐含层节点数量,对不同神经元进行训练,形成10-6-1的神经网络结构。在该结构下,计算一天某刻负荷均值和方差,并对温度和天气数据分别进行量化和编码处理,由此实现短期负荷智能预测。通过对比结果可知,该方法最高预测效率可达到98%,为电力调度交换机稳定运行提供数据支持。
For short-term load forecasting of power dispatching exchanges,traditional methods are affected by external factors,resulting in low forecasting efficiency.To solve this problem,an intelligent short-term load forecasting method based on neural network is proposed.Integrating time and temperature data,the training sample selection process is designed. According to the selected results,the access mode of neural network is analyzed.By defining the number of input,output and hidden layer nodes,different neurons are trained to form a 10-6-1 neural network structure.Under this structure,the average and variance of load at acertain moment of a day are calculated,and the temperature and weather data are quantified and coded respectively,thus realizing intelligent short-term load forecasting.The results show that the maximum prediction efficiency of this method can reach 98%,which providesdata support for the stable operation of power dispatching switch.
For short-term load forecasting of power dispatching exchanges,traditional methods are affected by external factors,resulting in low forecasting efficiency.To solve this problem,an intelligent short-term load forecasting method based on neural network is proposed.Integrating time and temperature data,the training sample selection process is designed. According to the selected results,the access mode of neural network is analyzed.By defining the number of input,output and hidden layer nodes,different neurons are trained to form a 10-6-1 neural network structure.Under this structure,the average and variance of load at acertain moment of a day are calculated,and the temperature and weather data are quantified and coded respectively,thus realizing intelligent short-term load forecasting.The results show that the maximum prediction efficiency of this method can reach 98%,which providesdata support for the stable operation of power dispatching switch.
引文
[1]周红标,王乐,卜峰,等.基于PSO-WPESN的短期电力负荷预测方法[J].电测与仪表,2017,54(6):113-119.
[2]刘畅,刘天琪,陈振寰,等.基于KPCA和BP神经网络的短期负荷预测[J].电测与仪表,2016,53(10):57-61.
[3]朱斌,姜宁,霍雪松,等.南京城市电网核心区短期负荷特性分析及预测[J].中国电力,2016,48(2):67-72.
[4]周末,金敏.多算法多模型与在线第二次学习结合的短期电力负荷预测方法[J].计算机应用,2017,37(11):3317-3322.
[5]林顺富,郝朝,汤晓栋,等.基于数据挖掘的楼宇短期负荷预测方法研究[J].电力系统保护与控制,2016,44(7):83-89.
[6]苏适,周立栋,万筱钟,等.计及气象因素的用电负荷短期分时分类预测模型与方法[J].电力建设,2017,38(10):76-83.
[7]雷涛,吕勇,马淑慧.基于改进灰色理论的主动配电网中长期负荷预测[J].电网与清洁能源,2016,32(9):22-28.
[8]王宁,谢敏,邓佳梁,等.基于支持向量机回归组合模型的中长期降温负荷预测[J].电力系统保护与控制,2016,44(3):92-97.
[9]陈艳平,毛弋,陈萍,等.基于EEMD-样本熵和Elman神经网络的短期电力负荷预测[J].电力系统及其自动化学报,2016,28(3):59-64.
[10]王保义,王冬阳,张少敏.基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备,2016,36(1):117-122.
[11]魏立兵,赵峰,王思华.基于人群搜索算法优化参数的支持向量机短期电力负荷预测[J].电测与仪表,2016,53(8):45-49.
[12]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.
[13]王惠中,刘轲,周佳,等.电力系统短期负荷预测建模仿真研究[J].计算机仿真,2016,33(2):175-179.
[14]王灵矫,夏伟,谭貌,等.供电系统电力短期负荷预测优化仿真研究[J].计算机仿真,2018,22(1):25-29.
[15]郭敏,李宁.一种基于云模型的负荷频率控制方法[J].电子设计工程,2018,26(6):157-160.
[16]陈本阳,张成刚,倪鸣,等.基于模糊信息粒化支撑向量机的电网负荷预测[J].电子设计工程,2018,26(6):56-59.
[2]刘畅,刘天琪,陈振寰,等.基于KPCA和BP神经网络的短期负荷预测[J].电测与仪表,2016,53(10):57-61.
[3]朱斌,姜宁,霍雪松,等.南京城市电网核心区短期负荷特性分析及预测[J].中国电力,2016,48(2):67-72.
[4]周末,金敏.多算法多模型与在线第二次学习结合的短期电力负荷预测方法[J].计算机应用,2017,37(11):3317-3322.
[5]林顺富,郝朝,汤晓栋,等.基于数据挖掘的楼宇短期负荷预测方法研究[J].电力系统保护与控制,2016,44(7):83-89.
[6]苏适,周立栋,万筱钟,等.计及气象因素的用电负荷短期分时分类预测模型与方法[J].电力建设,2017,38(10):76-83.
[7]雷涛,吕勇,马淑慧.基于改进灰色理论的主动配电网中长期负荷预测[J].电网与清洁能源,2016,32(9):22-28.
[8]王宁,谢敏,邓佳梁,等.基于支持向量机回归组合模型的中长期降温负荷预测[J].电力系统保护与控制,2016,44(3):92-97.
[9]陈艳平,毛弋,陈萍,等.基于EEMD-样本熵和Elman神经网络的短期电力负荷预测[J].电力系统及其自动化学报,2016,28(3):59-64.
[10]王保义,王冬阳,张少敏.基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备,2016,36(1):117-122.
[11]魏立兵,赵峰,王思华.基于人群搜索算法优化参数的支持向量机短期电力负荷预测[J].电测与仪表,2016,53(8):45-49.
[12]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.
[13]王惠中,刘轲,周佳,等.电力系统短期负荷预测建模仿真研究[J].计算机仿真,2016,33(2):175-179.
[14]王灵矫,夏伟,谭貌,等.供电系统电力短期负荷预测优化仿真研究[J].计算机仿真,2018,22(1):25-29.
[15]郭敏,李宁.一种基于云模型的负荷频率控制方法[J].电子设计工程,2018,26(6):157-160.
[16]陈本阳,张成刚,倪鸣,等.基于模糊信息粒化支撑向量机的电网负荷预测[J].电子设计工程,2018,26(6):56-59.