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
杨晋岭,靳云龙
摘要(Abstract)：
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。
关键词(KeyWords)： 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
基金项目(Foundation): 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)
作者(Author): 杨晋岭,靳云龙
参考文献(References)：
- [1] MWIFUNYI R J,KISSAKA M M,MVUNGI N H.Short-Term Load Forecasting for Improved Service Restoration in Electrical Power Systems:A Case of Tanzania[C]//2020 International Conference on Artificial Intelligence and Signal Processing(AISP).Amaravati,India,IEEE,2020:1-5.
- [2] JIN Y,GUO H G,WANG J Z,et al.A Hybrid System Based on LSTM for Short-Term Power Load Forecasting[J].Energies,2020,13(23):6241-6241.
- [3] LEI J,JIN T,HAO J,et al.Short-Term Load Forecasting with Clustering-Regression Model in Distributed Cluster[J].Cluster Computing,2019,22(7):10163-10173.
- [4] 宋占党，李湘华，王海宾，等.大数据环境下的电力负荷预测研究[J].电子测量技术，2019,42(12):57-60.
- [5] LEBOTSA M E,SIGAUKE C,BERE A,et al.Short Term Electricity Demand Forecasting Using Partially Linear Additive Quantile Regression with An Application to the Unit Commitment Problem[J].Applied Energy,2018,222:104-118.
- [6] 郑睿程，顾洁，金之俭，等.数据驱动与预测误差驱动融合的短期负荷预测输入变量选择方法研究[J].中国电机工程学报，2020,40(2):487-499.
- [7] LANG K,ZHANG M,YUAN Y,et al.Short-Term Load Forecasting Based on Multivariate Time Series Prediction and Weighted Neural Network with Random Weights and Kernels[J].Cluster Computing,2018,22(12):12589-12597.
- [8] YIN L,SUN Z,GAO F,et al.Deep Forest Regression for Short-Term Load Forecasting of Power Systems[J].IEEE Access,2020,8:49090-49099.
- [9] FAN C,DING C,ZHENG J,et al.Empirical Mode Decomposition Based Multi-Objective Deep Belief Network for Short-Term Power Load Forecasting[J].Neurocomputing,2020,388:110-123.
- [10] 石德琳.基于神经网络的电力负荷预测研究与实现[D].济南：山东大学，2016.
- [11] 李冬辉，尹海燕，郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术，2018,42(2):585-590.
- [12] BO H,NIE Y,WANG J.Electric Load Forecasting Use a Novelty Hybrid Model on the Basic of Data Preprocessing Technique and Multi-objective Optimization Algorithm[J].IEEE Access,2020,8:13858-13874.
- [13] 段炼，洪海生，乡立，等.考虑分时段负荷行为的短期负荷预测方法[J].电力需求侧管理，2021,23(1):77-83.
- [14] 熊晖.基于RBF神经网络与粒子滤波算法的用户电力短期负荷预测及其系统实现[D].深圳：中国科学院大学，2019.
- [15] ZHANG H,YANG J,JIA G,et al.ELM-MC:Multi-label Classification Framework Based on Extreme Learning Machine[J].International Journal of Machine Learning and Cybernetics,2020,11(3):2261-2274.
- [16] 施珮，匡亮，袁永明，等.基于改进极限学习机的水体溶解氧预测方法[J].农业工程学报，2020,36(19):233-240.
- [17] GAN W,ZHU D,JI D.QPSO-Model Predictive Control-Based Approach to Dynamic Trajectory Tracking Control for Unmanned Underwater Vehicles[J].Ocean Engineering,2018,158(15):208-220.
- [18] NIU W J,FENG Z K,CHENG C T,et al.Forecasting Daily Runoff by Extreme Learning Machine Based on Quantum-Behaved Particle Swarm Optimization[J].Journal of Hydrologic Engineering,2018,23(3):1-10.
- [19] HUANG Y,ZHANG Y,WU Z,et al.A Novel Adaptive Kalman Filter with Inaccurate Process and Measurement Noise Covariance Matrices[J].IEEE Transactions on Automatic Control,2018,63(2):594-601.
- [20] 陈则王，杨丽文，赵晓兵，等.基于改进无迹卡尔曼滤波的锂电池SOC在线估计[J].计量学报，2019,40(1):40-48.