基于蜂群优化极限学习算法的用电功率预测  

Electric power forecasting based on bee colony optimized extreme learning machine algorithm

作　　者：刘耀东 姜文超 廖宇航 LIU Yaodong;JIANG Wenchao;LIAO Yuhang(Jiangsu Productivity Promotion Center,Nanjing 210042,China;Southeast University,School of Instrument Science and Engineering,Nanjing 210096,China)

机构地区：[1]江苏省生产力促进中心,江苏南京210042 [2]东南大学仪器科学与工程学院,江苏南京210096

出　　处：《电气应用》2022年第1期21-25,I0005,共6页Electrotechnical Application

摘　　要：针对用电功率负荷序列随机性强、负荷预测准确度不足等问题,提出一种基于人工蜂群算法(ABC)优化极限学习机(ELM)的用电功率预测模型。将原始电力负荷序列进行模态平稳化处理,得到包含不同时间尺度的局部特征信号的本征模函数分量和残差分量;利用人工蜂群算法优化极限学习机模型学习各模态分量的时序规律并进行分量预测,将各模态分量预测值融合叠加得到最终预测结果。实验结果表明,所提出的预测模型能够对用电功率作出准确预测,具有更好的泛化性能和更高的预测准确度。Aiming at the problems of strong randomness of electric power load sequence and insufficient load forecasting accuracy, an electric power forecasting model based on artificial bee colony algorithm(ABC) optimized extreme learning machine(ELM) is proposed. The empirical mode decomposition method is used to stabilize the original power load sequence, and the eigenmode function components and residual components containing local characteristic signals of different time scales are obtained;the artificial bee colony algorithm is used to optimize the extreme learning machine model to learn each mode. The time sequence law of the components and the component prediction are performed, and the predicted values of the modal components are fused and superimposed to obtain the final prediction result. The experimental results show that the proposed prediction model can accurately predict the power consumption, and has better generalization performance and higher prediction accuracy.

关 键 词：电力负荷预测 极限学习机 模态分解 人工蜂群算法 

分 类 号：TM715[电气工程—电力系统及自动化] TP18[自动化与计算机技术—控制理论与控制工程]