摘要
针对非平稳、非线性中期负荷序列分解预测的精度问题,提出了基于奇异谱分析与神经网络的中期负荷分解预测方法。考虑中期负荷长期趋势性与季节性周期波动性特点,在中期负荷序列趋势提取的基础上,利用频谱分析确定序列主要周期成分并引入奇异谱分析方法对序列主要周期成分进行滤波分解,对分解所得的各子序列构建神经网络模型进行预测,各子序列预测结果叠加作为最终的电量预测值。结合某地历史数据,将所提算法与经验模态分解/神经网络方法、传统滤波/神经网络方法预测结果进行对比,结果表明该方法在进行中期电量预测时能够获得更为平稳的、精度较高的预测结果。
Aiming at accuracy of decomposition forecast for non-stationary nonlinear medium-term load sequence, a forecast method based on singular spectrum analysis and neural network is proposed. Taking into consideration the long-term trend and seasonal cyclical fluctuation of medium-term load, the main periodic components of the sequence are determined with spectral analysis based on trend extraction of medium-term load sequence. Singular spectrum analysis is introduced to filter the main periodic components and a neural network model is established to carry out forecast for each sub-sequence. The forecast results of each sub-sequence are superimposed to give final load forecast value. Taking historical data in certain region as an example, the forecast results of empirical mode decomposition-neural network method and traditional filtering-neural network method are compared with those of the method proposed in this paper, showing that a more stationary and accurate result can be obtained with the proposed method for medium-term load forecasting.
作者
陈浩文
刘文霞
李月乔
CHEN Haowen;LIU Wenxia;LI Yueqiao(State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources(North China Electric Power University),Changping District,Beijing 102206,China)
出处
《电网技术》
EI
CSCD
北大核心
2020年第4期1333-1342,共10页
Power System Technology
关键词
中期负荷预测
分解预测
奇异谱分析
神经网络
medium-term load forecast
decomposition forecast
singular spectrum analysis
neural network
