为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosti...为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosting decision tree,k-shape-STL-GBDT)。首先分析用户用电时序特征,利用k-shape时间序列聚类算法根据负荷曲线划分用户聚类,其次,使用STL算法将不同簇的负荷数据划分为季节项、趋势项与随机项。然后,结合温度、湿度等影响因素搭建预测模型,以麻省大学smart*可再生能源项目的公开数据集为例进行分析,并与多种主流聚类分解预测模型进行对比。结果表明新提出的模型框架MAPE减少了4%以上,针对短期负荷预测表现出了较好的性能与预测精度。展开更多
Nowadays,there is considerable research interest in proposing modern permanent magnet(PM)electric machine structures for applications such as electric vehicles.Several radial and axial topologies with different arrang...Nowadays,there is considerable research interest in proposing modern permanent magnet(PM)electric machine structures for applications such as electric vehicles.Several radial and axial topologies with different arrangements of PM in the stator and rotor have been introduced for PM Vernier motors(PMVM)with the aim of increasing the performance characteristics such as power factor,efficiency,rotational torque torque density and wider constant torque-speed region.Meanwhile,the spoke PM arrangement has provided higher torque density than the surface and V-shaped arrangement.But in contrast,the V-shaped arrangement has a more sinusoidal flux and less cogging torque.In this paper,a 620 W,12-slot 16-pole Vernier PM motor with a fractional slot arrangement.Consequent K-shaped pole is introduced,which has the advantages of spoke and V-shaped magnetic arrangements.After presenting and confirming the concept of the proposed structure based on functional comparison with conventional structures,an analytical modeling based on the harmonic analysis method is introduced to accurately predict the performance of the machine,and finally the proposed structure is prototyped and the experimental results are simulated and modeling are compared.展开更多
In recent years,the expansion of the power grid has led to a continuous increase in the number of consumers within the distribution network.However,due to the scarcity of historical data for these new consumers,it has...In recent years,the expansion of the power grid has led to a continuous increase in the number of consumers within the distribution network.However,due to the scarcity of historical data for these new consumers,it has become a complex challenge to accurately forecast their electricity demands through traditional forecasting methods.This paper proposes an innovative short-term residential load forecasting method that harnesses advanced clustering,deep learning,and transfer learning technologies to address this issue.To begin,this paper leverages the domain adversarial transfer network.It employs limited data as target domain data and more abundant data as source domain data,thus enabling the utilization of source do-main insights for the forecasting task of the target domain.Moreover,a K-shape clustering method is proposed,which effectively identifies source domain data that align optimally with the target domain,and enhances the forecasting accuracy.Subsequently,a composite architecture is devised,amalgamating attention mechanism,long short-term memory network,and seq2seq network.This composite structure is integrated into the domain adversarial transfer network,bolstering the performance of feature extractor and refining the forecasting capabilities.An illustrative analysis is conducted using the residential load dataset of the Independent System Operator to validate the proposed method empirically.In the case study,the relative mean square error of the proposed method is within 30 MW,and the mean absolute percentage error is within 2%.A signifi-cant improvement in accuracy,compared with other comparative experimental results,underscores the reliability of the proposed method.The findings unequivocally demonstrate that the proposed method advocated in this paper yields superior forecasting results compared with prevailing mainstream forecast-ing methods.展开更多
风电机组的大规模接入导致电力系统惯量明显下降,并对系统频率安全稳定造成威胁。针对风电高渗透电力系统区域惯量辨识中频率最优测点选择困难和惯量估计误差较大等问题,提出了一种基于组合模型的风电高渗透电力系统区域惯量辨识方法。...风电机组的大规模接入导致电力系统惯量明显下降,并对系统频率安全稳定造成威胁。针对风电高渗透电力系统区域惯量辨识中频率最优测点选择困难和惯量估计误差较大等问题,提出了一种基于组合模型的风电高渗透电力系统区域惯量辨识方法。首先,采用基于形状距离(shape-based distance,SBD)指标的K-shape聚类算法对频率响应曲线进行聚类,并确定各区域内频率动态响应曲线的最优测量路径。其次,结合最小二乘支持向量机(least squares support vector machine,LSSVM)和受控自回归滑动平均模型(autoregressive moving average with exogenous input,ARMAX)对不同风电渗透率下各区域惯量水平进行辨识,并与传统ARMAX模型的惯量辨识结果进行对比分析。最后,通过改进的IEEE10机39节点系统对所提方法的有效性进行仿真验证。结果表明,所提方法有效提高了区域和全系统惯量辨识精度。展开更多
文摘为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosting decision tree,k-shape-STL-GBDT)。首先分析用户用电时序特征,利用k-shape时间序列聚类算法根据负荷曲线划分用户聚类,其次,使用STL算法将不同簇的负荷数据划分为季节项、趋势项与随机项。然后,结合温度、湿度等影响因素搭建预测模型,以麻省大学smart*可再生能源项目的公开数据集为例进行分析,并与多种主流聚类分解预测模型进行对比。结果表明新提出的模型框架MAPE减少了4%以上,针对短期负荷预测表现出了较好的性能与预测精度。
文摘Nowadays,there is considerable research interest in proposing modern permanent magnet(PM)electric machine structures for applications such as electric vehicles.Several radial and axial topologies with different arrangements of PM in the stator and rotor have been introduced for PM Vernier motors(PMVM)with the aim of increasing the performance characteristics such as power factor,efficiency,rotational torque torque density and wider constant torque-speed region.Meanwhile,the spoke PM arrangement has provided higher torque density than the surface and V-shaped arrangement.But in contrast,the V-shaped arrangement has a more sinusoidal flux and less cogging torque.In this paper,a 620 W,12-slot 16-pole Vernier PM motor with a fractional slot arrangement.Consequent K-shaped pole is introduced,which has the advantages of spoke and V-shaped magnetic arrangements.After presenting and confirming the concept of the proposed structure based on functional comparison with conventional structures,an analytical modeling based on the harmonic analysis method is introduced to accurately predict the performance of the machine,and finally the proposed structure is prototyped and the experimental results are simulated and modeling are compared.
基金supported by the National Natural Science Foundation of China(No.52177087)Guangdong Basic and Applied Basic Research Foundation,China(No.2022B1515250006).
文摘In recent years,the expansion of the power grid has led to a continuous increase in the number of consumers within the distribution network.However,due to the scarcity of historical data for these new consumers,it has become a complex challenge to accurately forecast their electricity demands through traditional forecasting methods.This paper proposes an innovative short-term residential load forecasting method that harnesses advanced clustering,deep learning,and transfer learning technologies to address this issue.To begin,this paper leverages the domain adversarial transfer network.It employs limited data as target domain data and more abundant data as source domain data,thus enabling the utilization of source do-main insights for the forecasting task of the target domain.Moreover,a K-shape clustering method is proposed,which effectively identifies source domain data that align optimally with the target domain,and enhances the forecasting accuracy.Subsequently,a composite architecture is devised,amalgamating attention mechanism,long short-term memory network,and seq2seq network.This composite structure is integrated into the domain adversarial transfer network,bolstering the performance of feature extractor and refining the forecasting capabilities.An illustrative analysis is conducted using the residential load dataset of the Independent System Operator to validate the proposed method empirically.In the case study,the relative mean square error of the proposed method is within 30 MW,and the mean absolute percentage error is within 2%.A signifi-cant improvement in accuracy,compared with other comparative experimental results,underscores the reliability of the proposed method.The findings unequivocally demonstrate that the proposed method advocated in this paper yields superior forecasting results compared with prevailing mainstream forecast-ing methods.
文摘风电机组的大规模接入导致电力系统惯量明显下降,并对系统频率安全稳定造成威胁。针对风电高渗透电力系统区域惯量辨识中频率最优测点选择困难和惯量估计误差较大等问题,提出了一种基于组合模型的风电高渗透电力系统区域惯量辨识方法。首先,采用基于形状距离(shape-based distance,SBD)指标的K-shape聚类算法对频率响应曲线进行聚类,并确定各区域内频率动态响应曲线的最优测量路径。其次,结合最小二乘支持向量机(least squares support vector machine,LSSVM)和受控自回归滑动平均模型(autoregressive moving average with exogenous input,ARMAX)对不同风电渗透率下各区域惯量水平进行辨识,并与传统ARMAX模型的惯量辨识结果进行对比分析。最后,通过改进的IEEE10机39节点系统对所提方法的有效性进行仿真验证。结果表明,所提方法有效提高了区域和全系统惯量辨识精度。
