电网典型电能质量稳态指标的准确预测对优化电网运行方式和提高电网供电质量具有重要意义。根据电能质量稳态指标似周期、非周期的特点,提出一种基于混沌理论和最小二乘支持向量机（least squares support vector machine,LSSVM）的电...电网典型电能质量稳态指标的准确预测对优化电网运行方式和提高电网供电质量具有重要意义。根据电能质量稳态指标似周期、非周期的特点,提出一种基于混沌理论和最小二乘支持向量机（least squares support vector machine,LSSVM）的电能质量稳态指标预测模型。首先采用混沌理论对典型电能质量稳态指标历史数据进行相空间重构,构造包含吸引子的新数据空间;其次利用最小二乘支持向量机在高维空间下进行样本训练,并结合粒子群算法优化最小二乘支持向量机参数;最后得到最佳预测模型。基于某地配电网电能质量实际监测数据,采用所提模型进行典型电能质量稳态指标预测,平均相对误差均在8%以下,优于传统BP神经网络预测方法。展开更多
In this paper, the online correction model predictive control （MPC） strategy is presented for partial dif- ferential equation （PDE） unknown spatially-distributed systems （SDSs）. The low-dimensional MIMO models a...In this paper, the online correction model predictive control （MPC） strategy is presented for partial dif- ferential equation （PDE） unknown spatially-distributed systems （SDSs）. The low-dimensional MIMO models are obtained using principal component analysis （PCA） method from the high-dimensional spatio-temporal data. Though the linear low- dimensional model is easy for control design, it is a linear approximation for nonlinear SDSs. Thus, the MPC strategy is proposed based on the online correction low-dimensional models, where the state at a previous time is used to correct the output of low-dimensional models and the spatial output is correct by the average deviation of the historical data. The simulations demonstrated show the accuracy and efficiency of the proposed methodologies.展开更多
基金博士点基金项目(20110141110032)教育部中央高校基本科研业务费专项资金资助(20112072020008)+1 种基金supported by Specialized Research Fund for Doctoral Program of Higher Education(No.20110141110032)supported by the Fundamental Research Funds for the Central University(No.20112072020008)
文摘电网典型电能质量稳态指标的准确预测对优化电网运行方式和提高电网供电质量具有重要意义。根据电能质量稳态指标似周期、非周期的特点,提出一种基于混沌理论和最小二乘支持向量机（least squares support vector machine,LSSVM）的电能质量稳态指标预测模型。首先采用混沌理论对典型电能质量稳态指标历史数据进行相空间重构,构造包含吸引子的新数据空间;其次利用最小二乘支持向量机在高维空间下进行样本训练,并结合粒子群算法优化最小二乘支持向量机参数;最后得到最佳预测模型。基于某地配电网电能质量实际监测数据,采用所提模型进行典型电能质量稳态指标预测,平均相对误差均在8%以下,优于传统BP神经网络预测方法。
基金supported by the National Nature Science Foundation of China (Nos. 60825302, 61074061)the High Technology Research and Development Program of China (No. 2007AA041403)+2 种基金the Program of Shanghai Subject Chief Scientist‘Shu Guang’ Project of Shanghai Municipal Education CommissionShanghai Education Development Foundation
文摘In this paper, the online correction model predictive control （MPC） strategy is presented for partial dif- ferential equation （PDE） unknown spatially-distributed systems （SDSs）. The low-dimensional MIMO models are obtained using principal component analysis （PCA） method from the high-dimensional spatio-temporal data. Though the linear low- dimensional model is easy for control design, it is a linear approximation for nonlinear SDSs. Thus, the MPC strategy is proposed based on the online correction low-dimensional models, where the state at a previous time is used to correct the output of low-dimensional models and the spatial output is correct by the average deviation of the historical data. The simulations demonstrated show the accuracy and efficiency of the proposed methodologies.
