基于ARMA与ANN模型组合交叉方法的电网日负荷预测Daily Grid Load Forecasting Based on ARMA and ANN Model Combined Crossing Method
范金骥
FAN Jinji
摘要(Abstract)：
用电负荷的预测是一个包含很多不确定因素的复杂问题,通常根据已有负荷数据建立模型进行预测,将近期负荷数据与远期负荷数据相结合,综合不同特征的负荷数据信息。针对单项预测模型在电网实时日负荷预测的局限性,建立了由ARMA模型和ANN模型为基础结合纵横交叉算法的混合预测模型。该模型采用时间序列模型处理连续纵向负荷数据,采用神经网络技术处理断续横向负荷数据,对计算得到的纵向、横向预测值加权计算,获得交叉预测值。提出的对纵向连续负荷数据和横向断续数据分别建模的纵横交叉预测法,以获取尽可能多的重要预测信息,提高预测精度。在某电网上进行了实例测试,具有较好的效果。
Power load forecasting is quite complex due to various uncertainties. Based on the forecasting model established by historical load data, the recent load data should be combined with the forward load data to synthesize the load data of different characteristics. Aiming at the limitations of single forecasting model in real-time daily load forecasting, a CSO-based hybrid forecasting model combining auto-regressive and moving average model(ARMA) and neural network algorithm(ANN) is established. The model proposes a time series model to deal with continuous longitudinal load data, and neural network technology to deal with intermittent lateral load data; the weighted calculation on the longitudinal and horizontal predictive is conducted to obtain cross prediction value. A vertical and horizontal cross prediction method for longitudinal continuous load data and transverse intermittent data is proposed to obtain important predictive information as much as possible to improve the prediction accuracy. The method is used in a power grid and achieves favorable effect.
关键词(KeyWords)：
短期负荷预测;ARMA模型;ANN模型;纵横交叉算法
short-term load forecasting;ARMA model;ANN model;crisscross optimization
基金项目(Foundation):
作者(Author):
范金骥
FAN Jinji
DOI: 10.19585/j.zjdl.201808006
参考文献(References)：
- [1]廖旎焕,胡智宏,马莹莹,等.电力系统短期负荷预测方法综述[J].电力系统保护与控制,2011,39(1):147-152.
- [2]金鑫,罗滇生,孙广强,等.中长期电力负荷预测模型筛选与组合方法[J].电力系统及其自动化学报,2012,24(4):150-156.
- [3]李龙,魏靖,黎灿兵,等.基于人工神经网络的负荷模型预测[J].电工技术学报,2015,30(8):225-230.
- [4]YANG H,HUANG C,HUANG C.Identification of AR-MAX model for short term load forecasting:an evolutionary programming approach[C]//Power Industry Computer Application Conference.Salt Lake City UT,1995:325-330.
- [5]WANG B,TAI N,ZHAI H,et a1.A new ARMAX model based on evolutionary algorithm and particle swarm optimization for short-term load forecasting[J].Electric Power Systems Research,2008,78(10):1679-1685.
- [6]雷绍兰,孙才新,周淙,等.电力短期负荷的多变量时间序列线性回归预测方法研究[J].中国电机工程学报,2006,26(2):25-29.
- [7]崔和瑞,彭旭.基于ARIMAX模型的夏季短期电力负荷预测[J].电力系统保护与控制,2015,43(4):108-114.
- [8]HERN魣NDEZ L,BALADR魷N C,AGUIAR J M,et al.Artificial neural networks for short-term load forecasting in micro grids environment[J].Energy,2014,75(1):252-264.
- [9]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(2):68-71.
- [10]严凤,刘亚男,苗倩.基于径向基神经网络的配电网单相接地故障研究[J].电测与仪表,2013,50(5):5-9.
- [11]牛东晓,邢棉,孟明.基于联合数据挖掘技术的神经网络负荷预测模型研究[J].电工技术学报,2004,19(9):62-68.
- [12]王蒙,张国友,田丽,等.基于最优组合预测模型的电力负荷预测研究[J].重庆工商大学学报:自然科学版,2012,29(9):65-69.
- [13]李海亮,曹彦朝,孟安波,等.基于有效度遴选和纵横交叉算法的负荷组合预测[J].电测与仪表,2016,53(12):87-91.
- [14]刘凯.纵横交叉算法在地区电网无功优化中的研究与应用[D].广州:广东工业大学,2015.
- [15]张魁,王亚明,刘明,等.基于大数据及智能算法的连云港电量负荷预测研究[J].江苏电机工程,2016,35(3):49-52.
- [16]樊唯钦,张伟,李勇钢,等.基于改进人体舒适指数的微电网短期负荷预测[J].广东电力,2017,30(4):137-142.
- [17]丁晓,孙虹,郑海雁,等.基于配用电大数据的短期负荷预测[J].电力工程技术,2018,37(3):21-27.
- [18]张冰玉.基于数据挖掘技术的短期电力负荷预测[J].电力大数据,2017,20(10):18-21.
- [19]王鸿玺,李飞,李翀,等.基于大数据分析的混沌神经网络模型在负荷预测中的应用[J].电力大数据,2017,20(8):1-5.
- [20]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.
- [21]刘宇,郭林,阳锋,等.基于改进灰色理论的中长期负荷预测方法研究[J].电网与清洁能源,2016,32(8):51-56.