李鹏;何帅;韩鹏飞;郑苗苗;黄敏;孙健;

• 1:华北电力大学电气与电子工程学院
• 2:国网北京市电力公司

摘要(Abstract)：

在电力市场改革与智能电网建设的大背景下,电力将逐渐回归商品属性,电价也将实时波动,并对负荷产生影响。通过分析得出电价与负荷具有相关性,因此在预测模型中考虑了实时电价的影响,并对考虑实时电价的负荷预测模型与价格型需求侧响应之间的关系进行了讨论。针对前馈型神经网络不能处理序列间关联信息与传统循环神经网络无法记忆久远关键信息的缺陷,提出了基于长短期记忆循环神经网络的负荷预测模型,使用自适应矩估计算法进行深度学习。最后通过美国某地区的实际负荷和电价数据,验证了所提模型具有更高的预测精度。

关键词(KeyWords)： 负荷预测;长短期记忆;实时电价;需求侧响应;深度学习

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51577068);; 国家电网公司科技项目(520201150012)~~

作者(Author): 李鹏;何帅;韩鹏飞;郑苗苗;黄敏;孙健;

Email:

DOI: 10.13335/j.1000-3673.pst.2018.0433

参考文献(References)：

• [1]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社,2007.
• [2]Li P,Xu D,Zhou Z,et al. Stochastic optimal operation of microgrid basedonchaoticbinaryparticleswarmoptimization[J]. IEEE Transactions on Smart Grid,2017,7(1):66-73.
• [3]康重庆,夏清,张伯明.电力系统负荷预测研究综述与发展方向的探讨[J].电力系统自动化,2004,28(17):1-11.Kang Chongqing,Xia Qing,Zhang Boming.Review of power system load forecasting and its development[J].Automation of Electric Power Systems,2004,28(17):1-11(in Chinese).
• [4]朱陶业,李应求,张颖,等.提高时间序列气象适应性的短期电力负荷预测算法[J].中国电机工程学报,2006,26(23):14-19.ZhuTaoye,LiYingqiu,ZhangYing,etal.Anewalgorithmof advancing weather adaptability based on ARIMA model for day-ahead power load forecasting[J].Proceedings of the CSEE,2006,26(23):14-19(in Chinese).
• [5]Song K B,Baek Y S,Hong D H,et al.Short-term load forecasting fortheholidaysusingfuzzylinearregressionmethod[J]. IEEE Transactions on Power Systems,2005,20(1):96-101.
• [6]高亚静,孙永健,杨文海,等.基于新型人体舒适度的气象敏感负荷短期预测研究[J].中国电机工程学报,2017,37(7):1946-1954.Gao Yajing,Sun Yongjian,Yang Wenhai,et al.Weather-sensitive load’sshort-termforecastingresearchbasedonnewhumanbody amenityindicator[J].ProceedingsoftheCSEE,2017,37(7):1946-1954(in Chinese).
• [7]牛东晓,王建军,李莉,等.基于粗糙集和决策树的自适应神经网络短期负荷预测方法[J].电力自动化设备,2009,29(10):30-34.Niu Dongxiao,Wang Jianjun,Li Li,et al.Short-term load forecasting using adaptive ANN based on rough set and decision tree[J].Electric Power Automation Equipment,2009,29(10):30-34(in Chinese).
• [8]Pandey A S,Singh D,Sinha S K.Intelligent hybrid wavelet models forshort-termloadforecasting[J]. IEEETransactionsonPower Systems,2010,25(3):1266-1273.
• [9]曾鸣,吕春泉,田廓,等.基于细菌群落趋药性优化的最小二乘支持向量机短期负荷预测方法[J].中国电机工程学报,2011,31(34):93-99.Zeng Ming,LüChunquan,Tian Kuo,et al.Least squares-support vectormachineloadforecastingapproachoptimizedbybacterial colonychemotaxismethod[J].ProceedingsoftheCSEE,2011,31(34):93-99(in Chinese).
• [10]张素香,赵丙镇,王风雨,等.海量数据下的电力负荷短期预测[J].中国电机工程学报,2015,35(1):37-42.ZhangSuxiang,ZhaoBingzhen,WangFengyu,etal.Short-term powerloadforecastingbasedonbigdata[J].Proceedingsofthe CSEE,2015,35(1):37-42(in Chinese).
• [11]Simon Haykin.神经网络原理[M].北京:机械工业出版社,2004.
• [12]庞清乐.基于粗糙集理论的神经网络预测算法及其在短期负荷预测中的应用[J].电网技术,2010,34(12):168-173.PangQingle.Aroughset-basedneuralnetworkloadforecasting algorithm and its application in short-term load forecasting[J].Power System Technology,2010,34(12):168-173(in Chinese).
• [13]Bashir Z A,El-Hawary M E.Applying wavelets to short-term load forecastingusingPSO-basedneuralnetworks[J].IEEETransactions on Power Systems,2009,24(1):20-27.
• [14]邹政达,孙雅明,张智晟.基于蚁群优化算法递归神经网络的短期负荷预测[J].电网技术,2005,29(3):59-63.ZouZhengda, SunYaming, ZhangZhisheng. Short-termload forecastingbasedonrecurrentneuralnetworkusingantcolony optimization algorithm[J].Power System Technology,2005,29(3):59-63(in Chinese).
• [15]葛少云,贾鸥莎,刘洪.基于遗传灰色神经网络模型的实时电价条件下短期电力负荷预测[J].电网技术,2012,36(1):224-229.GeShaoyun,JiaOusha,LiuHong.Agrayneuralnetworkmodel improvedbygeneticalgorithmforshort-termloadforecastingin price-sensitiveenvironment[J].PowerSystemTechnology,2012,36(1):224-229(in Chinese).
• [16]HochreiterS,SchmidhuberJ.Long short-termmemory[J].Neural Computation,1997,9(8):1735-1780.
• [17]李鹏,窦鹏冲,李雨薇,等.微电网技术在主动配电网中的应用[J].电力自动化设备,2015,35(4):8-16.Li Peng,Dou Pengchong,Li Yuwei,et al.Application of microgrid technologyinactivedistributionnetwork[J]. ElectricPower Automation Equipment,2015,35(4):8-16(in Chinese).
• [18]何耀耀,刘瑞,撖奥洋.基于实时电价与支持向量分位数回归的短期电力负荷概率密度预测方法[J].中国电机工程学报,2017,37(3):768-775.He Yaoyao,Liu Rui,Han Aoyang.Short-term power load probability density forecasting method based on real time price and support vector quantileregression[J].ProceedingsoftheCSEE,2017,37(3):768-775(in Chinese).
• [19]PJM.Data Directory[EB/OL].Valley Forge,Pennsylvania:PJM,(2017-01-01)[2018-01-13].http://www.pjm.com/markets-andoperations/data-dictionary.aspx.
• [20]Hu A S,Lie T T,Gooi H B.Load forecast for customers under real timepricingsystems[C]//InternationalConferenceonElectricUtility DeregulationandRestructuringandPowerTechnologies.2000:538-543.
• [21]王冬容.价格型需求侧响应在美国的应用[J].电力需求侧管理,2010,12(4):74-77.Wang Dongrong.Application of price-based demand side response in the U.S.A.[J].Power DSM,2010,12(4):74-77(in Chinese).
• [22]阮文骏,王蓓蓓,李扬,等.峰谷分时电价下的用户响应行为研究[J].电网技术,2012,36(7):86-93.RuanWenjun,WangBeibei,LiYang,etal.Customerresponse behavior in time-of-use price[J].Power System Technology,2012,36(7):86-93(in Chinese).
• [23]NimaN, Najafi-RavadaneghS, AminK. Probabilisticoptimal schedulingofnetworkedmicrogridsconsideringtime-baseddemand response programs under uncertainty[J].Applied Energy,2017(198):267-279.
• [24]KingmaD,BaJA.Amethodforstochasticoptimization[EB/OL].Ithaca,NewYork:arXiv,(2017-01-30)[2018-01-15].https://arxiv.org/abs/1412.6980.