In a“low-carbon”context,the power load is affected by the coupling of multiple factors,which gradually evolves from the traditional“pure load”to the generalized load with the dual characteristics of“load+power su...In a“low-carbon”context,the power load is affected by the coupling of multiple factors,which gradually evolves from the traditional“pure load”to the generalized load with the dual characteristics of“load+power supply.”Traditional time-series forecasting methods are no longer suitable owing to the complexity and uncertainty associated with generalized loads.From the perspective of image processing,this study proposes a graphical short-term prediction method for generalized loads based on modal decomposition.First,the datasets are normalized and feature-filtered by comparing the results of Xtreme gradient boosting,gradient boosted decision tree,and random forest algorithms.Subsequently,the generalized load data are decomposed into three sets of modalities by modal decomposition,and red,green,and blue(RGB)images are generated using them as the pixel values of the R,G,and B channels.The generated images are diversified,and an optimized DenseNet neural network was used for training and prediction.Finally,the base load,wind power,and photovoltaic power generation data are selected,and the characteristic curves of the generalized load scenarios under different permeabilities of wind power and photovoltaic power generation are obtained using the density-based spatial clustering of applications with noise algorithm.Based on the proposed graphical forecasting method,the feasibility of the generalized load graphical forecasting method is verified by comparing it with the traditional time-series forecasting method.展开更多
Load forecasting is critical for a variety of applications in modern energy systems.Nonetheless,forecasting is a difficult task because electricity load profiles are tied with uncertain,non-linear,and non-stationary s...Load forecasting is critical for a variety of applications in modern energy systems.Nonetheless,forecasting is a difficult task because electricity load profiles are tied with uncertain,non-linear,and non-stationary signals.To address these issues,long short-term memory(LSTM),a machine learning algorithm capable of learning temporal dependencies,has been extensively integrated into load forecasting in recent years.To further increase the effectiveness of using LSTM for demand forecasting,this paper proposes a hybrid prediction model that incorporates LSTM with empirical mode decomposition(EMD).EMD algorithm breaks down a load time-series data into several sub-series called intrinsic mode functions(IMFs).For each of the derived IMFs,a different LSTM model is trained.Finally,the outputs of all the individual LSTM learners are fed to a meta-learner to provide an aggregated output for the energy demand prediction.The suggested methodology is applied to the California ISO dataset to demonstrate its applicability.Additionally,we compare the output of the proposed algorithm to a single LSTM and two state-of-the-art data-driven models,specifically XGBoost,and logistic regression(LR).The proposed hybrid model outperforms single LSTM,LR,and XGBoost by,35.19%,54%,and 49.25%for short-term,and 36.3%,34.04%,32%for longterm prediction in mean absolute percentage error,respectively.展开更多
由于用户级综合能源系统(integrated energy system,IES)的多元负荷序列之间复杂的耦合关系及易受外部因素影响等原因,综合能源系统多元负荷的精准预测面临很大困难。为此,提出一种基于Spearman相关性分析阈值寻优(threshold optimizati...由于用户级综合能源系统(integrated energy system,IES)的多元负荷序列之间复杂的耦合关系及易受外部因素影响等原因,综合能源系统多元负荷的精准预测面临很大困难。为此,提出一种基于Spearman相关性分析阈值寻优(threshold optimization,TO)和变分模态分解结合长短期记忆网络(variational mode decomposition based long short-term memory network,VMD-LSTM)的多元负荷预测方法。首先,使用斯皮尔曼等级(Spearman rank,SR)相关系数定量计算多元负荷间以及负荷与其他气候因素间的相关关系并通过循环寻优确定最优相关阈值,然后采用VMD算法将以最优阈值筛选出的负荷特征序列分解成更简单、平稳、有规律性的本征模态函数(intrinsic mode function,IMF)后与最优气象特征一起输入LSTM模型进行负荷预测。通过某用户级IES的实际数据对所提方法的有效性进行了验证,结果表明,所提方法能有效提高IES的多元负荷预测精度。展开更多
针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(sin...针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。展开更多
针对电力负荷数据的非线性和不稳定性问题,提出了一种基于经验模态分解改进麻雀搜索算法双向长短期记忆神经网络相结合的EMD ISSA BiLSTM预测模型。首先采用EMD处理非线性负荷数据,将原始负荷数据分解为多个不同尺度的本征模态函数(IMF)...针对电力负荷数据的非线性和不稳定性问题,提出了一种基于经验模态分解改进麻雀搜索算法双向长短期记忆神经网络相结合的EMD ISSA BiLSTM预测模型。首先采用EMD处理非线性负荷数据,将原始负荷数据分解为多个不同尺度的本征模态函数(IMF),引入反向学习策略和Levy飞行策略分别改进麻雀搜索算法(SSA)的收敛速度慢和容易陷入局部最优问题,利用改进麻雀搜索算法(ISSA)对BiLSTM神经网络进行参数寻优。然后再利用优化后的BiLSTM模型对每个分量进行预测,并将各预测结果叠加组合,得到整个负荷序列的预测结果。最后通过实际算例分析,证明该方法相对于传统的预测方法具有更好的预测精度和稳定性,可作为一种有效的短期负荷预测方法。展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62063016).
文摘In a“low-carbon”context,the power load is affected by the coupling of multiple factors,which gradually evolves from the traditional“pure load”to the generalized load with the dual characteristics of“load+power supply.”Traditional time-series forecasting methods are no longer suitable owing to the complexity and uncertainty associated with generalized loads.From the perspective of image processing,this study proposes a graphical short-term prediction method for generalized loads based on modal decomposition.First,the datasets are normalized and feature-filtered by comparing the results of Xtreme gradient boosting,gradient boosted decision tree,and random forest algorithms.Subsequently,the generalized load data are decomposed into three sets of modalities by modal decomposition,and red,green,and blue(RGB)images are generated using them as the pixel values of the R,G,and B channels.The generated images are diversified,and an optimized DenseNet neural network was used for training and prediction.Finally,the base load,wind power,and photovoltaic power generation data are selected,and the characteristic curves of the generalized load scenarios under different permeabilities of wind power and photovoltaic power generation are obtained using the density-based spatial clustering of applications with noise algorithm.Based on the proposed graphical forecasting method,the feasibility of the generalized load graphical forecasting method is verified by comparing it with the traditional time-series forecasting method.
文摘Load forecasting is critical for a variety of applications in modern energy systems.Nonetheless,forecasting is a difficult task because electricity load profiles are tied with uncertain,non-linear,and non-stationary signals.To address these issues,long short-term memory(LSTM),a machine learning algorithm capable of learning temporal dependencies,has been extensively integrated into load forecasting in recent years.To further increase the effectiveness of using LSTM for demand forecasting,this paper proposes a hybrid prediction model that incorporates LSTM with empirical mode decomposition(EMD).EMD algorithm breaks down a load time-series data into several sub-series called intrinsic mode functions(IMFs).For each of the derived IMFs,a different LSTM model is trained.Finally,the outputs of all the individual LSTM learners are fed to a meta-learner to provide an aggregated output for the energy demand prediction.The suggested methodology is applied to the California ISO dataset to demonstrate its applicability.Additionally,we compare the output of the proposed algorithm to a single LSTM and two state-of-the-art data-driven models,specifically XGBoost,and logistic regression(LR).The proposed hybrid model outperforms single LSTM,LR,and XGBoost by,35.19%,54%,and 49.25%for short-term,and 36.3%,34.04%,32%for longterm prediction in mean absolute percentage error,respectively.
文摘由于用户级综合能源系统(integrated energy system,IES)的多元负荷序列之间复杂的耦合关系及易受外部因素影响等原因,综合能源系统多元负荷的精准预测面临很大困难。为此,提出一种基于Spearman相关性分析阈值寻优(threshold optimization,TO)和变分模态分解结合长短期记忆网络(variational mode decomposition based long short-term memory network,VMD-LSTM)的多元负荷预测方法。首先,使用斯皮尔曼等级(Spearman rank,SR)相关系数定量计算多元负荷间以及负荷与其他气候因素间的相关关系并通过循环寻优确定最优相关阈值,然后采用VMD算法将以最优阈值筛选出的负荷特征序列分解成更简单、平稳、有规律性的本征模态函数(intrinsic mode function,IMF)后与最优气象特征一起输入LSTM模型进行负荷预测。通过某用户级IES的实际数据对所提方法的有效性进行了验证,结果表明,所提方法能有效提高IES的多元负荷预测精度。
文摘针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。
文摘针对电力负荷数据的非线性和不稳定性问题,提出了一种基于经验模态分解改进麻雀搜索算法双向长短期记忆神经网络相结合的EMD ISSA BiLSTM预测模型。首先采用EMD处理非线性负荷数据,将原始负荷数据分解为多个不同尺度的本征模态函数(IMF),引入反向学习策略和Levy飞行策略分别改进麻雀搜索算法(SSA)的收敛速度慢和容易陷入局部最优问题,利用改进麻雀搜索算法(ISSA)对BiLSTM神经网络进行参数寻优。然后再利用优化后的BiLSTM模型对每个分量进行预测,并将各预测结果叠加组合,得到整个负荷序列的预测结果。最后通过实际算例分析,证明该方法相对于传统的预测方法具有更好的预测精度和稳定性,可作为一种有效的短期负荷预测方法。
