牛安敏;张宏立;王聪;

• 1:新疆大学电气工程学院

摘要(Abstract)：

针对电力系统负荷序列非线性、非平稳特征,为对其进行准确短期预测,文章提出了基于VMD-Leaky-ESN的电力系统短期负荷多步预测方法.首先对原始负荷时间序列进行归一化处理,采用变分模态分解(Variational Mode Decomposition,VMD)方法对序列分解处理,得到不同频率尺度的子序列,并引入模态分量样本熵来降低任务量并改善预测效果;其次采用泄露积分型回声状态网络(Leaky Integrator Echo State Network,Leaky-ESN)结合多步预测,对组合后的模态分量序列进行短期电力负荷预测,最后通过5种短期负荷预测模型对比分析,证明该预测方法可有效避免预测过程中累计的迭代误差,具有更高的预测精度和泛化能力.

关键词(KeyWords)： 变分模态分解;回声状态网络;短期负荷预测;电力系统

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51767022;51967019);; 新疆维吾尔自治区自然科学基金项目(2019D01C082)

作者(Authors): 牛安敏;张宏立;王聪;

DOI: 10.13568/j.cnki.651094.651316.2019.12.20.0002

参考文献(References)：

• [1]马天男,王超,彭丽霖,等.计及需求响应和深度结构多任务学习的电力系统短期负荷预测[J].电测与仪表,2019,56(16):50-60.MA T N,WANG C,PENG L L,et al.Short term load forecasting of power system considering demand response and multi-task learning based on deep structure[J].Electrical Measurement&Instrumentation,2019,56 (16):50-60.(in Chinese)
• [2]SRIRAM L M K,GILANIFAR M,ZHOU Y,et al.Causal Markov elman network for load forecasting in multinetwork systems[J].IEEE Transactions on Industrial Electronics,2018,66(2):1434-1442.
• [3]魏立兵,赵峰,王思华.基于人群搜索算法优化参数的支持向量机短期电力负荷预测[J].电测与仪表,2016,53(8):45-49+74.WEI L B,ZHAO F,WANG S H.Short term power load forecasting of support vector machine based on parameters optimization of population search algorithm[J].Electrical Measurement&Instrumentation,2016,53(8):45-49+74.(in Chinese)
• [4]YANG A,LI W,YANG X.Short-term electricity load forecasting based on feature selection and Least Squares Support Vector Machines[J].Knowledge-Based Systems,2019,163:159-173.
• [5]杨芳君,王耀力,王力波,等.基于改进CS算法优化Elman-IOC神经网络的短期负荷预测[J].电测与仪表,2019,56(9):32-37.YANG F J,WANG Y L,WANG L B,et al.Short term load forecasting based on optimized Elman-IOC neuralnetwork with improved CS algorithm[J].Electrical Measurement&Instrumentation,2019,56(9):32-37.(in Chinese)
• [6]KONG W,DONG Z Y,JIA Y,et al.Short-term residential load forecasting based on LSTM recurrent neural network[J].IEEETransactions on Smart Grid,2017,10(1):841-851.
• [7]孔祥玉,郑锋,王鑫,等.基于深度信念网络的短期负荷预测方法[J].电力系统自动化,2018,42(5):133-139.KONG X Y,ZHENG F,WANG X,et al.Short-term load forecasting based on deep belief network[J].Automation of Electic Systems,2018,42(5):133-139.(in Chinese)
• [8]JAEGER H,LUKOˇsEVIˇCIUS M,POPOVICI D,et al.Optimization and applications of echo state networks with leaky-integrator neurons[J].Neural networks,2007,20(3):335-352.
• [9]LOPEZ C,ZHONG W,ZHENG M L.Short-term electric load forecasting based on wavelet neural network,particle swarm optimization and ensemble empirical mode decomposition[J].Energy Procedia,2017,105:3677-3682.
• [10]LOPEZ,CRISTIAN,ZHONG W,et al.Short-term Electric Load Forecasting Based on Wavelet Neural Network,Particle Swarm Optimization and Ensemble Empirical Mode Decomposition[J].Energy Procedia,2017,105:3677-3682.
• [11]孔祥玉,李闯,郑锋,等.基于经验模态分解与特征相关分析的短期负荷预测方法[J].电力系统自动化,2019,43(5):46-56.KONG X Y,LI C,ZHENG F,et al.Short-term load forecasting method based on empirical mode decomposition and feature correlation analysis[J].Automation of Electric Power Systemsn,2019,43(5):46-56.(in Chinese)
• [12]GHOFRANI M,GHAYEKHLOO M,ARABALI A,et al.A hybrid short-term load forecasting with a new input selection framework[J].Electric Power Systems Research,2015,119(119):138-148.
• [13]YU Y,LI W,SHENG D,et al.A hybrid short-term load forecasting method based on improved ensemble empirical mode decomposition and back propagation neural network[J].Journal of Zhejiang University-SCIENCE A,2016,17(2):101-114.
• [14]张淑清,宿新爽,陈荣飞,等.基于变分模态分解和FABP的短期电力负荷预测[J].仪器仪表学报,2018,39(4):67-73.ZHANG S Q,SU X S,CHEN R F,et al.Short-term load forecasting based on the VMD and FABP[J].Chinese Journal of Scientific Instrument,2018,39(4):67-73.(in Chinese)
• [15]WANG J,LI Y.Multi-step ahead wind speed prediction based on optimal feature extraction,long short term memory neural network and error correction strategy[J].Applied energy,2018,230:429-443.