Patent
Microgrid attack identification method based on convolutional neural network and microgrid coordination controller
Liu Yongliang,Xu Chengbin,He Shengguo,Tong Qiang,Chen Rui,Ding Kai,Chen Yuansheng,Zhan Jiewen,Wang Qiangang,Zhu Xiaofan,Chang Hongliang,Wang Huiqin,Deng Wei,He Hongyan,Huang Zhiwei,Xiao Shengyuan,Xi Wei,Kuang Xiaoyun,Yao Hao,Yu Yang,Jian Ganyang,Yang Yiwei +21 more
- 12 May 2020
TL;DR: In this paper, a microgrid attack identification method based on a convolutional neural network is proposed, which comprises the steps of collecting a data stream; preprocessing the acquired data streams; inputting the preprocessed data flow into a CNN model for real-time detection and classification; outputting a classification result, wherein the classification comprises a normal class and an abnormal class, and the classification result is the classification condition of each piece of data in the data stream, intercepting or forwarding the data flow according to the classification results; when the abnormal class exists in the classification
read more
Abstract: The invention provides a microgrid attack identification method based on a convolutional neural network. The microgrid attack identification method comprises the steps of collecting a data stream; preprocessing the acquired data streams; inputting the preprocessed data flow into a convolutional neural network model for real-time detection and classification; outputting a classification result, wherein the classification comprises a normal class and an abnormal class, and the classification result is the classification condition of each piece of data in the data stream; intercepting or forwarding the data flow according to the classification result; when the abnormal class exists in the classification result, sending out a corresponding alarm prompt and generating a log record according tothe classification of the data in the abnormal class; and when the classification results are all normal classes, forwarding the data streams. The invention also provides a microgrid coordination controller. Compared with the prior art, safe and reliable operation of the microgrid is ensured.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
References
Patent
Intelligent substation network intrusion detection system and detection method based on deep learning
Song Xiaofan,Jin Man,Fan Qingling,Chen Chen,Dong Pingxian,Zhang Qingfeng,Shen Yanfei,Wang Hui,Chen Jinghua,Bai Pingping,Ma Hui,Guo Fang +11 more
- 02 Aug 2019
TL;DR: In this article, the authors proposed an intelligent transformer substation network intrusion detection system and method based on deep learning. But the system is used for intrusion detection aiming at network attacks of an IEC61850 communication protocol of an intelligent substation.
9
Patent
Deep belief network feature extraction-based analogue circuit fault diagnosis method
Yigang He,Chaolong Zhang,Zhang Hui,Yin Baiqiang,Jiang Jinguang,He Liulu,Duan Jiajun +6 more
- 08 Aug 2019
TL;DR: In this paper, a Deep Belief Network (DBN) feature extraction-based analogue circuit fault diagnosis method comprises the following steps: a time domain response signal of a tested analogue circuit is acquired, where the acquired time-domain response signal is an output voltage signal of the tested analog circuit; DBN-based feature extraction is performed on the acquired voltage signal, wherein learning rates of restricted Boltzmann machines in a DBN are optimized and acquired by virtue of a quantum-behaved particle swarm optimization (QPSO); a support vector machine (SVM)-based fault diagnosis model
8
Patent
A DDoS attack detection method
Tian Qiuting,Han Dezhi,Wang Jun,Bi Kun +3 more
- 25 Jan 2019
TL;DR: Wang et al. as mentioned in this paper proposed a DDoS attack detection method, which comprises the following steps: collecting data streams in a network and preprocessing the collected data streams; optimizing the weights and thresholds of BP neural network by using the global unbiased search strategy bee colony algorithm, and training the DDoS detection model with the preprocessed data.
4