A5033665407- Electric Power System Optimization
- Advanced Computational Techniques and Applications
- Auction Theory and Applications
- Advanced Sensor and Control Systems
- Antenna Design and Analysis
- Big Data Technologies and Applications
- Advanced Algorithms and Applications
- Smart Grid and Power Systems
- Graph Theory and Algorithms
- Integrated Energy Systems Optimization
- Antenna Design and Optimization
- Optimal Power Flow Distribution
- Power Systems and Technologies
- Time Series Analysis and Forecasting
- Advanced Graph Neural Networks
- Anomaly Detection Techniques and Applications
- Satellite Communication Systems
- Stochastic processes and financial applications
- Energy Load and Power Forecasting
State Grid Corporation of China (China)
2021-2024
China University of Geosciences
2014
Recognizing handwritten Chinese documents can improve efficiency and productivity, which makes it a crucial task for power grid enterprises. This paper proposes novel document recognition method to enhance accuracy. First, spatial features are extracted from the input images using an inception module, captures multi-scale characteristics. Subsequently, space channel parallel attention module is employed emphasize significant suppress interference. The then transformed by bidirectional long...
A matching method based on a hybrid neural network is proposed to improve the accuracy of online for power grid fault handling plan. First, ERNIE 3.0 encoding and double-pointer decoding module are used replace generative model in universal information extraction (UIE) framework, mapping relationship between entities entity labels plan trained by adjusting hyperparameters UIE framework. Then, semantic distance equipment, type, phenomenon, calculated residual vector-embedding vector-encoded...
The 14th Five-Year Plan is a crucial period for achieving emission peak, the government has formulated Central China power system. However, current plan may face challenges of uncoordinated development between generation and grid, requiring mathematical modeling to analyze optimize strategy. This paper proposes model applied system, optimizing policies, including investment deployment various sources, expansion transmission lines optimal commissioning scale pumped hydro storage. Our...
The personalized and diverse demands of modern communication present new challenges to antenna design. While the emergence Software-Defined Everything provides an innovative hardware design idea that structure is modeled in a software way designed with intelligence optimization algorithms. Inspired by idea, this paper we propose software-defined intelligent method for optimal variables are described method, target determined performance method. Based on above model will be abstracted, which...
Abstract Abnormal data in the power system will reduce accuracy of state estimation and affect safe operation dispatch system. This paper proposes a anomaly identification model based on time series neural network, which establishes for various measuring points control master station, creates group associated network topology, extracts sample characteristics series. The is used to realize intelligent normal abnormal data. recognition results are compared with distribution DBSCAN density...
In the field of power dispatching, more and tasks have adopted artificial intelligence solutions, related research literature are also showing an exponential explosive growth. order to solve problem information overload in dispatching scenario, facilitate researchers with experience but lacking use algorithm models effectively conveniently their work, this paper constructs a domain knowledge graph for proposes model recommendation method based on scene label matching. According cosine...