短期电力负荷预测在电网安全运行和制定合理调度计划方面发挥着重要作用。为了提高电力负荷时间序列预测的准确度,提出了一种由完整自适应噪声集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和基于注意力机制的长短期记忆神经网络(long short-term memory network based on attention mechanism, LSTM-Attention)相结合的短期电力负荷预测模型。完整自适应噪声集成经验模态分解有效地将负荷时间序列分解成多个层次规律平稳的本征模态分量,并通过神经网络模型预测极大值,结合镜像延拓方法抑制边界效应,提高分解精度,同时基于注意力机制的长短期记忆神经网络自适应地提取电力负荷数据输入特征并分配权重进行预测,最后各预测模态分量叠加重构后获得最终预测结果。通过不同实际电力负荷季节数据分别进行实验,并与其他电力负荷预测模型结果分析进行比较,验证了该预测方法在电力负荷预测精度方面具有更好的性能。

Short-term power load forecasting plays an important role in the safe operation of power grid and the formulation of reasonable dispatching plan. In order to improve the accuracy of power load time-series forecasting, a short-term power load forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and short-term memory neural network based on attention mechanism (LSTM-Attention) is proposed in this paper. The complete ensemble empirical mode decomposition with adaptive noise effectively decomposes the load time series into multiple levels of regular and stable eigenmode components, and suppresses the boundary effect through the neural network model prediction maximum combined with the image continuation method to improve the decomposition accuracy. At the same time, the long short-term memory neural network based on attention mechanism adaptively extracts the input characteristics of power load data and assigns weights for prediction. Finally, the final prediction results are obtained after superposition and reconstruction of each prediction modal component. Experiments are carried out on different seasonal data of actual power load, and the results of other power load forecasting models are analyzed and compared to verify that the forecasting method has better performance in power load forecasting accuracy.

准确预测短期多种能源负荷，是确保综合能源系统可靠、高效运行的必要前提。为此，提出了一种基于遗传粒子群混合优化(genetic algorithm particle swarm optimization, GAPSO)算法的卷积长短期记忆神经网络(convolutional neural network-long short-term memory, CNN-LSTM)综合能源系统多元负荷预测模型。首先，利用皮尔逊系数来描述各影响因素与负荷之间的相关性强弱。其次，采用GAPSO算法对长短期记忆(long short-term memory, LSTM)网络模型进行改进，然后构建卷积神经网络(convolutional neural networks, CNN)以提取小时级高阶特征，并通过改进后的LSTM网络模型对提取的隐含高阶特征进行分位数回归建模，构建了基于GAPSO-CNN-LSTM综合能源系统多元负荷预测模型。最后，以美国亚利桑那州立大学坦佩校区综合能源系统负荷数据为算例进行验证，结果表明：改进后的算法具有更好的收敛能力，模型具有更高的预测精度。

Accurate prediction of short-term multiple energy loads is a prerequisite to ensure the reliable and efficient operation of integrated energy system. For this reason, a convolutional neural network-long short-term memory (CNN-LSTM) model for integrated energy system multivariate load prediction based on genetic algorithm particle swarm optimization (GAPSO) is proposed. Firstly, Pearson's coefficient is used to describe the correlation between the influencing factors and the load. Secondly, GAPSO algorithm is used to improve the LSTM model, and then a one-dimensional CNN is constructed to extract the hourly higher-order features, and the extracted implicit higher-order features are partitioned by the improved long short-term memory (LSTM) modeling. The multivariate load forecasting model based on GAPSO-CNN-LSTM for integrated energy system is constructed through quantile regression modeling. Finally, the load data of integrated energy system of Arizona State University Tempe Campus is used as an example, and the results show that the improved algorithm has a better convergence ability and the model has a higher prediction accuracy.

针对输入数据特征多时负荷预测模型精度提升难的问题,文章提出一种并行多模型融合的混合神经网络超短期负荷预测方法。将卷积神经网络(convolutional neural network,CNN)与门控循环单元神经网络(gated recurrent unit neural network,GRU-NN)并行,分别提取局部特征与时序特征,将2个网络结构的输出拼接并输入深度神经网络(deep neural network,DNN),由DNN进行超短期负荷预测。最后应用负荷与温度数据进行预测实验,结果表明相比于GRU-NN网络结构、长短期记忆(long short term memory,LSTM)网络结构、串行CNN-LSTM网络结构与串行CNN-GRU网络结构,所提方法具有更好的预测性能。

For the purpose of addressing the difficulty of improving load forecasting accuracy brought by enormous input data features, a method based on hybrid neural network using parallel multi-model combination is proposed. In order to respectively extract local features and time-series features, this paper places the convolutional neural network (CNN) in parallel with the gated recurrent unit (GRU) structure, then concatenates the output of two network structures and inputs to a deep neural network, uses deep neural network to perform load forecasting. Through a prediction experiment of load and temperature data by using the proposed method, the experiment results show that, compared with GRU-NN model, long short term memory (LSTM) model, serial CNN-LSTM network model and serial CNN-GRU network model, the proposed method shows better prediction performance.

The vibration signal induced by bearing local fault has strong nonstationary and nonlinear property, which indicates that the conventional methods are difficult to recognize bearing fault patterns effectively. Hence, to obtain an efficient diagnosis result, the paper proposes an intelligent fault diagnosis approach for rolling bearing integrated symplectic geometry mode decomposition (SGMD), improved multiscale symbolic dynamic entropy (IMSDE) and multiclass relevance vector machine (MRVM). Firstly, SGMD is employed to decompose the original bearing vibration signal into several symplectic geometry components (SGC), which is aimed at reconstructing the original bearing vibration signal and achieving the purpose of noise reduction. Secondly, the bat algorithm (BA)-based optimized IMSDE is presented to evaluate the complexity of reconstruction signal and extract bearing fault features, which can solve the problems of missing of partial fault information existing in the original multiscale symbolic dynamic entropy (MSDE). Finally, IMSDE-based bearing fault features are fed to MRVM for achieving the identification of bearing fault categories. The validity of the proposed method is verified by the experimental and contrastive analysis. The results show that our approach can precisely identify different fault patterns of rolling bearings. Moreover, our approach can achieve higher recognition accuracy than several existing methods involved in this paper. This study provides a new research idea for improvement of bearing fault identification.