基于QPSO-ELM-KF的电力系统短期负荷预测  

Power System Short-term Load Forecasting Based on QPSO-ELM-KF

作　　者：杨晋岭[1] 靳云龙 YANG Jin-ling;JIN Yun-long(College of Electrical and Information Engineering,Taiyuan University of Science and Technology,Taiyuan 030024,China)

机构地区：[1]太原科技大学电子信息工程学院,太原030024

出　　处：《太原科技大学学报》2023年第1期27-33,共7页Journal of Taiyuan University of Science and Technology

基　　金：山西省科技重大专项(20191102010);山西省关键核心技术和共性技术研发攻关专项(20201102011)。

摘　　要：为保证日常电力系统的正常运行,满足其生产活动安排、电力经济调度以及电网安全分析的要求,必须要进行电力系统短期负荷的预测。为提高预测精度和稳定性,提出了一种基于量子粒子群(QPSO)优化极限学习机(ELM)与卡尔曼滤波(KF)相结合的电力系统短期负荷预测模型。该模型首先通过ELM预测各时间点的电力负荷值,其中,根据QPSO算法本身的特性以及在参数寻优方面的优势,利用其对ELM网络结构中输入层-隐含层的权值和隐含层的阈值进行寻优;然后,利用KF算法将得到的预测值做进一步的更新和优化,从而得到各时刻的最优估计值,最终以实现对短期电力负荷的精准预测。实验表明,使用QPSO-ELM-KF预测模型进行短期电力负荷预测,预测精度有进一步的提高。In order to ensure the normal operation of the daily power system and meet the requirements of its production activity arrangement,power economic dispatch and grid safety analysis,it is necessary to predict the short-term load of the power system.To improve the accuracy and stability of prediction,a short-term load forecasting model of power system which is composed of the quantum particle swarm optimization(QPSO)optimized extreme learning machine(ELM)and Kalman filter(KF)is proposed.The model first predicts the power load value at each time point through ELM.Among them,on the basis of the QPSO algorithm properties and its advantages in parameter optimization,the weights and thresholds of the input layer-hidden layer in the ELM network structure are optimized;then,the KF algorithm is used to make further renewal and majorization of the obtained predicted value,so as to obtain the optimal estimated value at each moment,and finally the accurate prediction of the short-term electric load is realized.Experiments show that QPSO-ELM-KF model for short-term load forecasting is able to further enhance the forecasting accuracy.

关 键 词：短期电力负荷预测 量子粒子群算法 极限学习机 卡尔曼滤波 

分 类 号：TM715[电气工程—电力系统及自动化]