Hao Jiang

The protection link within the wind farm is the key link that affects the transient characteristics of the wind farm, and also has the greatest impact on the complexity of scene construction. Therefore, it is urgent to study the method that can quickly build the chopper circuit and crowbar circuit action scene during the evaluation of the equivalent model of the wind farm. In this paper, a fast generation method of wind farm protection state scenarios based on Deep Belief Network (DBN) is proposed. Firstly, characteristic quantities that affect the protection action of a single fan in a wind farm are extracted, such as terminal voltage drop (the junction voltage of a single fan is equal to the terminal voltage), wind speed, etc. Simulation is carried out on a single fan in scenarios with different characteristic quantities, and records of characteristic quantities and protection actions are put into the DBN model for training as a sample set. Through training, a DBN model which can directly and accurately generate the fan protection state according to the characteristic quantity is obtained. Then, the topological structure and line impedance information of the wind farm are obtained, and the relationship between the voltage drop at the junction point and the voltage drop at the end of each fan in the wind farm is obtained. Combined with the voltage drop at the end of each fan in the wind farm and the deep belief network model, the fan protection action scene in the wind farm can be quickly generated for equivalent model evaluation. Finally, a numerical example is given to verify the effectiveness of the proposed method.

Cybercriminals often register many pornographic or gambling domains (known as abusive domains) with similar character compositions in bulk to reduce their investment in buying domains and make it easier for clients to remember and spread them. Therefore, this study combines the ideas of text similarity and text generation and proposes an abusive domain generation model based on GRU for rapidly generating new abusive domain names from known ones. Additionally, we develop a two-layer detection system for pornography and gambling domains using fastText and CNN models to obtain an abusive domain dataset for model training and validation. In the end, our detection system identifies pornographic and gambling domains with 99% precision while balancing correctness and speed. By inputting 40,000 random keywords into the abusive domain generation model, we obtained 130,220 online domains that served web pages, of which about 66% were pornographic or gambling domains. The results show that by exploiting cybercriminals’ behaviors in registering abusive domain names, such as bulk registration of similar domain names, we can prospectively acquire a large number of new abusive domains based on known ones. This study demonstrates that predicting new abusive domains not only expands the domain blacklist but also allows researchers to target the generated suspicious domains and dispose of them in time before they show abusive behavior.