To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobje...To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobjective optimization.First,a dual-convolution enhanced improved Crossformer prediction model is constructed,which employs parallel 1×1 global and 3×3 local convolutionmodules(Integrated Convolution Block,ICB)formultiscale feature extraction,combinedwith anAdaptive Spectral Block(ASB)to enhance time-series fluctuationmodeling.Based on high-precision predictions,a carbon-electricity cost joint optimization model is further designed to balance economic,environmental,and grid-friendly objectives.The model’s superiority was validated through a case study using real-world data from a renewable-heavy grid.Simulation results show that the proposed multi-objective strategy demonstrated a superior balance compared to baseline and benchmark models,achieving a 15.8%reduction in carbon emissions and a 5.2%reduction in economic costs,while still providing a substantial 22.2%reduction in the peak-valley difference.Its balanced performance significantly outperformed both a single-objective strategy and a state-of-the-art Model Predictive Control(MPC)benchmark,highlighting the advantage of a global optimization approach.This study provides theoretical and technical pathways for dynamic carbon factor-driven EV charging optimization.展开更多
为了解决高比例分布式电源(distributed generation,DG)大规模并网后实时量测数目缺失、传统预测辅助状态估计方法(forecasting-aided state estimation,FASE)估计精度有限等问题,提出了基于改进Crossformer伪量测构建的主动配电网FASE...为了解决高比例分布式电源(distributed generation,DG)大规模并网后实时量测数目缺失、传统预测辅助状态估计方法(forecasting-aided state estimation,FASE)估计精度有限等问题,提出了基于改进Crossformer伪量测构建的主动配电网FASE方法。首先,基于最大信息系数法(maximal information coefficient,MIC)筛选出高相关性的输入特征,提高预测模型的精度;然后,通过全变差正则化技术(total variation regularized,TV)优化鲁棒主成分分析法(robust principal component analysis,RPCA),构建TRPCA层,并将其嵌入到Crossformer中,以填补Crossformer无法有效处理非高斯噪声的空白;最后,利用改进的预测模型进行超短期负荷预测,经潮流计算得到节点伪量测,在量测不足情况下补全缺失数据,并结合扩展卡尔曼滤波器(extended Kalman filter,EKF)进行状态估计。在IEEE 33节点和IEEE 118节点标准配电网上进行仿真测试,结果表明所提方法在估计精度和鲁棒性等方面具有一定优势,可为主动配电网FASE提供参考。展开更多
基金Supported by State Grid Corporation of China Science and Technology Project:Research on Key Technologies for Intelligent Carbon Metrology in Vehicle-to-Grid Interaction(Project Number:B3018524000Q).
文摘To achieve low-carbon regulation of electric vehicle(EV)charging loads under the“dual carbon”goals,this paper proposes a coordinated scheduling strategy that integrates dynamic carbon factor prediction and multiobjective optimization.First,a dual-convolution enhanced improved Crossformer prediction model is constructed,which employs parallel 1×1 global and 3×3 local convolutionmodules(Integrated Convolution Block,ICB)formultiscale feature extraction,combinedwith anAdaptive Spectral Block(ASB)to enhance time-series fluctuationmodeling.Based on high-precision predictions,a carbon-electricity cost joint optimization model is further designed to balance economic,environmental,and grid-friendly objectives.The model’s superiority was validated through a case study using real-world data from a renewable-heavy grid.Simulation results show that the proposed multi-objective strategy demonstrated a superior balance compared to baseline and benchmark models,achieving a 15.8%reduction in carbon emissions and a 5.2%reduction in economic costs,while still providing a substantial 22.2%reduction in the peak-valley difference.Its balanced performance significantly outperformed both a single-objective strategy and a state-of-the-art Model Predictive Control(MPC)benchmark,highlighting the advantage of a global optimization approach.This study provides theoretical and technical pathways for dynamic carbon factor-driven EV charging optimization.
文摘为了解决高比例分布式电源(distributed generation,DG)大规模并网后实时量测数目缺失、传统预测辅助状态估计方法(forecasting-aided state estimation,FASE)估计精度有限等问题,提出了基于改进Crossformer伪量测构建的主动配电网FASE方法。首先,基于最大信息系数法(maximal information coefficient,MIC)筛选出高相关性的输入特征,提高预测模型的精度;然后,通过全变差正则化技术(total variation regularized,TV)优化鲁棒主成分分析法(robust principal component analysis,RPCA),构建TRPCA层,并将其嵌入到Crossformer中,以填补Crossformer无法有效处理非高斯噪声的空白;最后,利用改进的预测模型进行超短期负荷预测,经潮流计算得到节点伪量测,在量测不足情况下补全缺失数据,并结合扩展卡尔曼滤波器(extended Kalman filter,EKF)进行状态估计。在IEEE 33节点和IEEE 118节点标准配电网上进行仿真测试,结果表明所提方法在估计精度和鲁棒性等方面具有一定优势,可为主动配电网FASE提供参考。
