摘要
为了解决城市配电网电力负荷因规律复杂而难以有效预测的问题,本文提出了一种区分待预测日的城市电网短期负荷预测方法,根据待预测日的特征信息从历史负荷数据集中识别出相似日,建立9个基本负荷预测模型,将其负荷预测结果进行组合并比较,选择出待预测日最优组合模型的负荷预测值。为了验证这一方法的有效性,选取了6个专变用户对其未来200多天的负荷进行预测分析,其结果表明该方法具有较高的预测精度和更强的适应能力。
In order to solve the problem that the power distribution of urban distribution network is difficult to predict effectively due to the complicated rules,a short-term load forecasting method is proposed for urban power grid that distinguishes the day to be predicted,and identifies the historical load data set according to the characteristic information of the day to be predicted.On the similar day,nine basic load forecasting models are established,and their load forecasting results are combined and compared,and the load forecasting value of the optimal combined model to be predicted is selected.In order to verify the effectiveness of this method,six special-purpose users were selected to predict the load of the next 200 days.The results show that the method has higher prediction accuracy and stronger adaptability.
引文
[1] 冷松.浅析新一轮电力体制改革背景下供电企业的发展应对策略[J].现代经济信息,2015,(18).
[2] 张驰.国际电力体制改革经验及对中国的启发[J].电力技术经济,2007.
[3] 刘刚,叶雪峰.浅析城市配电网规划与实践[J].工程技术:全文版,2016,12.
[4] 俆军华,刘天琪.基于小波分解和人工神经网络的短期负荷预测[J].电网技术,2004,28(8).
[5] 雷绍兰,孙才新,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,2006,02(5).
[6] 吴景龙,杨淑霞,等.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报,2009,01.
[7] 师彪,李郁侠,等.基于改进粒子群-模糊神经网络的短期电力负荷预测[J].系统工程理论与实践,2010,01.
[8] 吴潇雨,和敬函,等.基于灰色投影改进随机森林算法的电力系统短期负荷预测[J].电力系统自动化,2015,12.
[9] 王继业.对电力体制改革后电力信息化的建设模式分析与探讨[J].电力信息与通信技术,2004,2(1):12-16.
[10] 李皎.大数据时代到来对电力行业发展的提出的新要求[J].华北电业,2013,(5).
[11] 唐四平,黄文杰,李娜.大数据时代电力营销何以应之[J].湖北电力,2013,(5).