The network attacks targeted at the power system become much more complex and covert. However, traditional security protection methods cannot well detect such unknown attacks or multi-step attacks, which leads to a constant threat. How to use the massive log and warning data generated from various types of traditional security equipment to effectively detect and trace the advanced network threats becomes more and more important. "Graph" is a data structure that can better represent the power network system and thus enforcing correlation analysis on the network graph is an important detection method. This paper first reviews the graph construction methods and graph representation learning method. Furthermore Dynamic-Graph Neural Network (DGNN) based method to detect attack behavior is proposed. The experimental evaluation shows that DGNN based method can achieve better performance compared with both shallow embedding method and static-GNN method.
KEYWORDS: Unmanned aerial vehicles, RGB color model, Data modeling, 3D modeling, Internet, Visual process modeling, Sensors, Convolutional neural networks, Convolution, Information visualization
With the advancement of technology, unmanned method has become a promising approach for data collection from the ubiquitous Internet of Things (IoT) in the power industry. However, making autonomous obstacle avoidance on unmanned aerial vehicles (UAVs) is a challenging problem. It is much harder when the UAV is small since only very lightweight sensors can be carried on. In this paper, we focus on this problem and propose a novel model through deep reinforcement learning to achieve autonomous obstacle avoidance for UAVs. Different from prior similar works, the proposed model adopts the policy iteration-based method and requires only raw RGB images obtained by a monocular camera. Simulation results show that the proposed model performs better when compared to the other models based on value iteration.
The rapid development of information technology makes the network environment more complex and changeable, and also brings more complex network attack methods, which makes the power monitoring network face more challenges. Under such circumstances, deep learning techniques are increasingly becoming an important part of the attack detection field. Deep learning technology can make self-adaptive judgments on different network attack methods, realize the detection of network attacks, and then improve the accuracy of attack detection technology. This paper builds a power monitoring network attack detection system based on the convolutional neural network and deep neural network in deep learning, which can accurately identify network attacks and reduce the false alarm rate of the system, thereby ensuring the smooth operation of the power monitoring network.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.