为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测...为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测方法。首先,基于快速傅里叶变换分析特高压直流输电系统暂态故障特征,使用相模变换和小波变换提取出故障特征量作为输入数据。其次,将输入数据输入到LSTM-RNN中进行前向传播,对系统故障特征进行深度学习,同时使用反向传播方式更新网络参数,将深层的特征量输入到Softmax分类器中进行分类,把故障识别分成区外故障、母线故障和线路故障,故障分类为正极故障、负极故障和双极故障,并输出识别结果。最后,在PSCAD/EMTDC仿真条件下,搭建特高压直流输电模型。验证结果表明:所提的方法在特高压直流输电线路继电保护的故障检测、故障选极上具有更好的效果,相比于人工神经网络、卷积神经网络、支持向量机,故障识别准确率分别提升4.71%、6.57%、9.32%。展开更多
The rapid advancement of the Internet ofThings(IoT)has heightened the importance of security,with a notable increase in Distributed Denial-of-Service(DDoS)attacks targeting IoT devices.Network security specialists fac...The rapid advancement of the Internet ofThings(IoT)has heightened the importance of security,with a notable increase in Distributed Denial-of-Service(DDoS)attacks targeting IoT devices.Network security specialists face the challenge of producing systems to identify and offset these attacks.This researchmanages IoT security through the emerging Software-Defined Networking(SDN)standard by developing a unified framework(RNN-RYU).We thoroughly assess multiple deep learning frameworks,including Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),Feed-Forward Convolutional Neural Network(FFCNN),and Recurrent Neural Network(RNN),and present the novel usage of Synthetic Minority Over-Sampling Technique(SMOTE)tailored for IoT-SDN contexts to manage class imbalance during training and enhance performance metrics.Our research has significant practical implications as we authenticate the approache using both the self-generated SD_IoT_Smart_City dataset and the publicly available CICIoT23 dataset.The system utilizes only eleven features to identify DDoS attacks efficiently.Results indicate that the RNN can reliably and precisely differentiate between DDoS traffic and benign traffic by easily identifying temporal relationships and sequences in the data.展开更多
本文以中石油股份为例,聚焦于股票价格预测,运用RNN模型与LSTM模型展开深入研究。使用RNN模型进行预测时,由于模型本身存在梯度消失或梯度爆炸的问题,其在处理长序列股价数据时存在显著缺陷,致使其难以捕捉股票价格序列中的长期依赖关系...本文以中石油股份为例,聚焦于股票价格预测,运用RNN模型与LSTM模型展开深入研究。使用RNN模型进行预测时,由于模型本身存在梯度消失或梯度爆炸的问题,其在处理长序列股价数据时存在显著缺陷,致使其难以捕捉股票价格序列中的长期依赖关系,在面对包含长期趋势、季节性变化的股价数据时表现欠佳。鉴于此,引入LSTM模型,该模型凭借独特的输入门、遗忘门和输出门机制,有效解决了长期依赖难题,能够选择性地记忆或遗忘信息,从而有效处理长序列数据。实验结果有力证实了LSTM模型不仅能精准模拟股价的真实走向,而且在模型评价指标上全面优于RNN模型。综上,LSTM模型在中石油股价预测领域展现出卓越的效果,相较于RNN模型更适用于股票预测任务。This study takes PetroChina Company Limited as an example, focuses on stock price prediction, and conducts an in-depth study using the RNN model and the LSTM model. When using the RNN model for prediction, due to the problems of gradient vanishing or gradient explosion in the model itself, it has significant defects in processing long-sequence stock price data. This makes it difficult for the RNN model to capture the long-term dependencies in the stock price sequence, and it performs poorly when dealing with stock price data containing long-term trends and seasonal changes. In view of this, the LSTM model is introduced. With its unique mechanisms of input gate, forget gate and output gate, the LSTM model effectively solves the problem of long-term dependencies. It can selectively remember or forget information, thus effectively handling long-sequence data. The experimental results strongly confirm that the LSTM model can not only accurately simulate the real trend of stock prices, but also comprehensively outperforms the RNN model in terms of model evaluation indicators. In conclusion, the LSTM model shows excellent results in the field of predicting PetroChina’s stock price and is more suitable for stock prediction tasks compared with the RNN model.展开更多
文摘为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测方法。首先,基于快速傅里叶变换分析特高压直流输电系统暂态故障特征,使用相模变换和小波变换提取出故障特征量作为输入数据。其次,将输入数据输入到LSTM-RNN中进行前向传播,对系统故障特征进行深度学习,同时使用反向传播方式更新网络参数,将深层的特征量输入到Softmax分类器中进行分类,把故障识别分成区外故障、母线故障和线路故障,故障分类为正极故障、负极故障和双极故障,并输出识别结果。最后,在PSCAD/EMTDC仿真条件下,搭建特高压直流输电模型。验证结果表明:所提的方法在特高压直流输电线路继电保护的故障检测、故障选极上具有更好的效果,相比于人工神经网络、卷积神经网络、支持向量机,故障识别准确率分别提升4.71%、6.57%、9.32%。
基金supported by NSTC 113-2221-E-155-055NSTC 113-2222-E-155-007,Taiwan.
文摘The rapid advancement of the Internet ofThings(IoT)has heightened the importance of security,with a notable increase in Distributed Denial-of-Service(DDoS)attacks targeting IoT devices.Network security specialists face the challenge of producing systems to identify and offset these attacks.This researchmanages IoT security through the emerging Software-Defined Networking(SDN)standard by developing a unified framework(RNN-RYU).We thoroughly assess multiple deep learning frameworks,including Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),Feed-Forward Convolutional Neural Network(FFCNN),and Recurrent Neural Network(RNN),and present the novel usage of Synthetic Minority Over-Sampling Technique(SMOTE)tailored for IoT-SDN contexts to manage class imbalance during training and enhance performance metrics.Our research has significant practical implications as we authenticate the approache using both the self-generated SD_IoT_Smart_City dataset and the publicly available CICIoT23 dataset.The system utilizes only eleven features to identify DDoS attacks efficiently.Results indicate that the RNN can reliably and precisely differentiate between DDoS traffic and benign traffic by easily identifying temporal relationships and sequences in the data.
文摘本文以中石油股份为例,聚焦于股票价格预测,运用RNN模型与LSTM模型展开深入研究。使用RNN模型进行预测时,由于模型本身存在梯度消失或梯度爆炸的问题,其在处理长序列股价数据时存在显著缺陷,致使其难以捕捉股票价格序列中的长期依赖关系,在面对包含长期趋势、季节性变化的股价数据时表现欠佳。鉴于此,引入LSTM模型,该模型凭借独特的输入门、遗忘门和输出门机制,有效解决了长期依赖难题,能够选择性地记忆或遗忘信息,从而有效处理长序列数据。实验结果有力证实了LSTM模型不仅能精准模拟股价的真实走向,而且在模型评价指标上全面优于RNN模型。综上,LSTM模型在中石油股价预测领域展现出卓越的效果,相较于RNN模型更适用于股票预测任务。This study takes PetroChina Company Limited as an example, focuses on stock price prediction, and conducts an in-depth study using the RNN model and the LSTM model. When using the RNN model for prediction, due to the problems of gradient vanishing or gradient explosion in the model itself, it has significant defects in processing long-sequence stock price data. This makes it difficult for the RNN model to capture the long-term dependencies in the stock price sequence, and it performs poorly when dealing with stock price data containing long-term trends and seasonal changes. In view of this, the LSTM model is introduced. With its unique mechanisms of input gate, forget gate and output gate, the LSTM model effectively solves the problem of long-term dependencies. It can selectively remember or forget information, thus effectively handling long-sequence data. The experimental results strongly confirm that the LSTM model can not only accurately simulate the real trend of stock prices, but also comprehensively outperforms the RNN model in terms of model evaluation indicators. In conclusion, the LSTM model shows excellent results in the field of predicting PetroChina’s stock price and is more suitable for stock prediction tasks compared with the RNN model.
