In order to enhance forecasting precision of problems about nonlinear time series in a complex industry system,a new nonlinear fuzzy adaptive variable weight combined forecasting model was established by using concept...In order to enhance forecasting precision of problems about nonlinear time series in a complex industry system,a new nonlinear fuzzy adaptive variable weight combined forecasting model was established by using conceptions of the relative error,the change tendency of the forecasted object,gray basic weight and adaptive control coefficient on the basis of the method of fuzzy variable weight.Based on Visual Basic 6.0 platform,a fuzzy adaptive variable weight combined forecasting and management system was developed.The application results reveal that the forecasting precisions from the new nonlinear combined forecasting model are higher than those of other single combined forecasting models and the combined forecasting and management system is very powerful tool for the required decision in complex industry system.展开更多
Two kinds of parameter estimation methods (I) and (II) of combining forecasting based on harmontic mean are proposed and compared through a lot of simulation forecasting examples. A very helpful conclusion is obtained...Two kinds of parameter estimation methods (I) and (II) of combining forecasting based on harmontic mean are proposed and compared through a lot of simulation forecasting examples. A very helpful conclusion is obtained, which can lay solid foundations for correct application of the above methods.展开更多
A new kind of combining forecasting model based on the generalized weighted functional proportional mean is proposed and the parameter estimation method of its weighting coefficients by means of the algorithm of quadr...A new kind of combining forecasting model based on the generalized weighted functional proportional mean is proposed and the parameter estimation method of its weighting coefficients by means of the algorithm of quadratic programming is given. This model has extensive representation. It is a new kind of aggregative method of group forecasting. By taking the suitable combining form of the forecasting models and seeking the optimal parameter, the optimal combining form can be obtained and the forecasting accuracy can be improved. The effectiveness of this model is demonstrated by an example.展开更多
This paper proposes artificial neural networks (ANN) as a tool for nonlinear combination of forecasts. In this study, three forecasting models are used for individual forecasts, and then two linear combining methods a...This paper proposes artificial neural networks (ANN) as a tool for nonlinear combination of forecasts. In this study, three forecasting models are used for individual forecasts, and then two linear combining methods are used to compare with the ANN combining method. The comparative experiment using real--world data shows that the prediction by the ANN method outperforms those by linear combining methods. The paper suggests that the ANN combining method can be used as- an alternative to conventional linear combining methods to achieve greater forecasting accuracy.展开更多
超短期电力负荷预测作为电力系统的基本组成,能为生产调度计划的制定提供重要依据。然而,电力负荷具有非线性、时变性和不确定性,充分挖掘其潜在特征并分别预测,是提升预测准确性的关键。提出一种基于自适应局部迭代滤波(adaptive local...超短期电力负荷预测作为电力系统的基本组成,能为生产调度计划的制定提供重要依据。然而,电力负荷具有非线性、时变性和不确定性,充分挖掘其潜在特征并分别预测,是提升预测准确性的关键。提出一种基于自适应局部迭代滤波(adaptive local iterative filtering,ALIF)的BiGRU-Attention-XGBoost电力负荷组合预测模型。该模型基于ALIF-SE实现将历史负荷序列分解重组为周期序列、波动序列和趋势序列;通过Attention机制对BiGRU模型进行改进,并结合XGBoost模型构建基于时变权重组合的电力负荷预测模型。实验分析表明,输入模型数据经过ALIF-SE处理后预测精度有明显提升;所提组合模型在工作日和节假日均具有较好的预测效果,预测误差大部分在5%以下;通过在不同负荷数据集下进行实验对比,验证了所提预测方法的可迁移性。实验结果证明,所提模型具有有效性、准确性和可行性。展开更多
负荷预测是综合能源系统(integrated energy system,IES)高效运行的前提,面对综合能源系统多元负荷强耦合相关性、强随机性的特点,单一模型在运行负荷特征提取方面存在不足。为充分利用负荷间的相关性、降低负荷数据的非平稳性、弥补单...负荷预测是综合能源系统(integrated energy system,IES)高效运行的前提,面对综合能源系统多元负荷强耦合相关性、强随机性的特点,单一模型在运行负荷特征提取方面存在不足。为充分利用负荷间的相关性、降低负荷数据的非平稳性、弥补单一模型的不足,提出一种基于TCN-TPABiLSTM组合模型和多任务学习框架的IES多元负荷超短期协同预测方法。首先对负荷间耦合相关性、负荷时间相关性和负荷影响因素进行分析以构建模型输入,再通过变分模态分解将负荷数据分解为一定数量的模态以降低非平稳性,最后以TCN-TPA-BiLSTM组合模型作为多任务学习框架的共享层进行预测。通过实际数据进行验证和对比,结果表明该方法能够充分发挥模型各部分优势,相较于其他模型也获得了更优的结果。展开更多
在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-W...在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-Winters模型和深度自回归模型(DeepAR)的组合预测模型STL-DeepAR-HW。先采用快速傅里叶变换和自相关函数提取数据的周期性特征,以提取到的最优周期对数据做STL分解,将数据分解为趋势项、季节项和余项;并用DeepAR和Holt-Winters分别预测趋势项和季节项,最后组合得到预测结果。在公开数据集AzurePublicDataset上进行实验,结果表明,与Transformer、Stacked-LSTM以及Prophet等模型相比,该组合模型在负载预测中具有更高的准确性和适用性。展开更多
基金Project(08SK1002) supported by the Major Project of Science and Technology Department of Hunan Province,China
文摘In order to enhance forecasting precision of problems about nonlinear time series in a complex industry system,a new nonlinear fuzzy adaptive variable weight combined forecasting model was established by using conceptions of the relative error,the change tendency of the forecasted object,gray basic weight and adaptive control coefficient on the basis of the method of fuzzy variable weight.Based on Visual Basic 6.0 platform,a fuzzy adaptive variable weight combined forecasting and management system was developed.The application results reveal that the forecasting precisions from the new nonlinear combined forecasting model are higher than those of other single combined forecasting models and the combined forecasting and management system is very powerful tool for the required decision in complex industry system.
文摘Two kinds of parameter estimation methods (I) and (II) of combining forecasting based on harmontic mean are proposed and compared through a lot of simulation forecasting examples. A very helpful conclusion is obtained, which can lay solid foundations for correct application of the above methods.
文摘A new kind of combining forecasting model based on the generalized weighted functional proportional mean is proposed and the parameter estimation method of its weighting coefficients by means of the algorithm of quadratic programming is given. This model has extensive representation. It is a new kind of aggregative method of group forecasting. By taking the suitable combining form of the forecasting models and seeking the optimal parameter, the optimal combining form can be obtained and the forecasting accuracy can be improved. The effectiveness of this model is demonstrated by an example.
文摘This paper proposes artificial neural networks (ANN) as a tool for nonlinear combination of forecasts. In this study, three forecasting models are used for individual forecasts, and then two linear combining methods are used to compare with the ANN combining method. The comparative experiment using real--world data shows that the prediction by the ANN method outperforms those by linear combining methods. The paper suggests that the ANN combining method can be used as- an alternative to conventional linear combining methods to achieve greater forecasting accuracy.
文摘超短期电力负荷预测作为电力系统的基本组成,能为生产调度计划的制定提供重要依据。然而,电力负荷具有非线性、时变性和不确定性,充分挖掘其潜在特征并分别预测,是提升预测准确性的关键。提出一种基于自适应局部迭代滤波(adaptive local iterative filtering,ALIF)的BiGRU-Attention-XGBoost电力负荷组合预测模型。该模型基于ALIF-SE实现将历史负荷序列分解重组为周期序列、波动序列和趋势序列;通过Attention机制对BiGRU模型进行改进,并结合XGBoost模型构建基于时变权重组合的电力负荷预测模型。实验分析表明,输入模型数据经过ALIF-SE处理后预测精度有明显提升;所提组合模型在工作日和节假日均具有较好的预测效果,预测误差大部分在5%以下;通过在不同负荷数据集下进行实验对比,验证了所提预测方法的可迁移性。实验结果证明,所提模型具有有效性、准确性和可行性。
文摘负荷预测是综合能源系统(integrated energy system,IES)高效运行的前提,面对综合能源系统多元负荷强耦合相关性、强随机性的特点,单一模型在运行负荷特征提取方面存在不足。为充分利用负荷间的相关性、降低负荷数据的非平稳性、弥补单一模型的不足,提出一种基于TCN-TPABiLSTM组合模型和多任务学习框架的IES多元负荷超短期协同预测方法。首先对负荷间耦合相关性、负荷时间相关性和负荷影响因素进行分析以构建模型输入,再通过变分模态分解将负荷数据分解为一定数量的模态以降低非平稳性,最后以TCN-TPA-BiLSTM组合模型作为多任务学习框架的共享层进行预测。通过实际数据进行验证和对比,结果表明该方法能够充分发挥模型各部分优势,相较于其他模型也获得了更优的结果。
文摘在信息化蓬勃发展的今日,大量云计算资源的高效管理是运维领域的重要难题。准确的负载预测是应对这一难题的关键技术。针对该问题提出一种基于局部加权回归周期趋势分解算法(Seasonal and Trend decomposition using Loess,STL)、Holt-Winters模型和深度自回归模型(DeepAR)的组合预测模型STL-DeepAR-HW。先采用快速傅里叶变换和自相关函数提取数据的周期性特征,以提取到的最优周期对数据做STL分解,将数据分解为趋势项、季节项和余项;并用DeepAR和Holt-Winters分别预测趋势项和季节项,最后组合得到预测结果。在公开数据集AzurePublicDataset上进行实验,结果表明,与Transformer、Stacked-LSTM以及Prophet等模型相比,该组合模型在负载预测中具有更高的准确性和适用性。
