In contemporary power systems,delving into the flexible regulation potential of demand-side resources is of paramount significance for the efficient operation of power grids.This research puts forward an innovative mu...In contemporary power systems,delving into the flexible regulation potential of demand-side resources is of paramount significance for the efficient operation of power grids.This research puts forward an innovative multivariate flexible load aggregation control approach that takes dynamic demand response into full consideration.In the initial stage,using generalized time-domain aggregation modelling for a wide array of heterogeneous flexible loads,including temperature-controlled loads,electric vehicles,and energy storage devices,a novel calculation method for their maximum adjustable capacities is devised.Distinct from conventional methods,this newly developed approach enables more precise and adaptable quantification of the load-adjusting capabilities,thereby enhancing the accuracy and flexibility of demand-side resource management.Subsequently,an SSA-BiLSTM flexible load classification prediction model is established.This model represents an innovative application in the field,effectively combining the advantages of the Sparrow Search Algorithm(SSA)and the Bidirectional Long-Short-Term Memory(BiLSTM)neural network.Furthermore,a parallel Markov chain is introduced to evaluate the switching state transfer probability of flexible loads accurately.This integration allows for a more refined determination of the maximum response capacity range of the flexible load aggregator,significantly improving the precision of capacity assessment compared to existing methods.Finally,in consonance with the intra-day scheduling plan,a newly developed diffuse filling algorithm is implemented to control the activation times of flexible loads precisely,thus achieving real-time dynamic demand response.Through in-depth case analysis and comprehensive comparative studies,the effectiveness of the proposed method is convincingly validated.With its innovative techniques and enhanced performance,it is demonstrated that this method has the potential to substantially enhance the utilization efficiency of demand-side resources in power systems,providing a novel and effective solution for optimizing power grid operation and demand-side management.展开更多
空调负荷的精准预测对建筑空调系统优化控制具有重要意义。为提高空调负荷预测精度,提出了一种基于奇异谱分析(SSA,Singular Spectrum Analysis)的卷积神经网络(CNN,Convolutional Neural Network)和双向长短时记忆网络(BiLSTM,Bidirect...空调负荷的精准预测对建筑空调系统优化控制具有重要意义。为提高空调负荷预测精度,提出了一种基于奇异谱分析(SSA,Singular Spectrum Analysis)的卷积神经网络(CNN,Convolutional Neural Network)和双向长短时记忆网络(BiLSTM,Bidirectional Long Short Term Memory)短期空调负荷预测模型。使用皮尔森相关系数选取与空调负荷高相关性特征。针对空调负荷的波动性和随机性,采用SSA将空调负荷分解为多个分量,同时将各个分量带入CNN-BiLSTM模型进行预测,该模型利用了CNN的特征提取和BiLSTM的双向学习能力,并将各个分量预测结果进行重构。通过不同建筑类型的空调数据对该模型进行验证分析,发现所提出模型在预测办公建筑空调负荷中RMSE、MAPE和MAE为19.47RT、14.72RT和2.33%,在预测商业建筑空调负荷中RMSE、MAPE和MAE为82.5RT、34.21RT和0.87%。结果表明,所提出的模型具有普适性且精度较高,可进行推广应用。展开更多
基金the Science and Technology Project of State Grid Shanxi Electric Power Co.,Ltd.,with the project number 52051L240001.
文摘In contemporary power systems,delving into the flexible regulation potential of demand-side resources is of paramount significance for the efficient operation of power grids.This research puts forward an innovative multivariate flexible load aggregation control approach that takes dynamic demand response into full consideration.In the initial stage,using generalized time-domain aggregation modelling for a wide array of heterogeneous flexible loads,including temperature-controlled loads,electric vehicles,and energy storage devices,a novel calculation method for their maximum adjustable capacities is devised.Distinct from conventional methods,this newly developed approach enables more precise and adaptable quantification of the load-adjusting capabilities,thereby enhancing the accuracy and flexibility of demand-side resource management.Subsequently,an SSA-BiLSTM flexible load classification prediction model is established.This model represents an innovative application in the field,effectively combining the advantages of the Sparrow Search Algorithm(SSA)and the Bidirectional Long-Short-Term Memory(BiLSTM)neural network.Furthermore,a parallel Markov chain is introduced to evaluate the switching state transfer probability of flexible loads accurately.This integration allows for a more refined determination of the maximum response capacity range of the flexible load aggregator,significantly improving the precision of capacity assessment compared to existing methods.Finally,in consonance with the intra-day scheduling plan,a newly developed diffuse filling algorithm is implemented to control the activation times of flexible loads precisely,thus achieving real-time dynamic demand response.Through in-depth case analysis and comprehensive comparative studies,the effectiveness of the proposed method is convincingly validated.With its innovative techniques and enhanced performance,it is demonstrated that this method has the potential to substantially enhance the utilization efficiency of demand-side resources in power systems,providing a novel and effective solution for optimizing power grid operation and demand-side management.
文摘空调负荷的精准预测对建筑空调系统优化控制具有重要意义。为提高空调负荷预测精度,提出了一种基于奇异谱分析(SSA,Singular Spectrum Analysis)的卷积神经网络(CNN,Convolutional Neural Network)和双向长短时记忆网络(BiLSTM,Bidirectional Long Short Term Memory)短期空调负荷预测模型。使用皮尔森相关系数选取与空调负荷高相关性特征。针对空调负荷的波动性和随机性,采用SSA将空调负荷分解为多个分量,同时将各个分量带入CNN-BiLSTM模型进行预测,该模型利用了CNN的特征提取和BiLSTM的双向学习能力,并将各个分量预测结果进行重构。通过不同建筑类型的空调数据对该模型进行验证分析,发现所提出模型在预测办公建筑空调负荷中RMSE、MAPE和MAE为19.47RT、14.72RT和2.33%,在预测商业建筑空调负荷中RMSE、MAPE和MAE为82.5RT、34.21RT和0.87%。结果表明,所提出的模型具有普适性且精度较高,可进行推广应用。
