A power system online dynamic safety assessment method based on an integrated decision tree
A dynamic security and power system technology, applied in the direction of instruments, character and pattern recognition, data processing applications, etc., can solve the difficulties in providing preventive/emergency control measures for on-site operators, real-time power flow analysis and time-domain simulation of accidental accidents, Can not meet the requirements of high reliability of power supply and other problems, to achieve the effect of improving the accuracy and reliability of evaluation, improving the level of safe operation of the power grid, and accurate dynamic safety evaluation decision-making
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] Example 1: image 3 The expressed IEEE-39 node system is a test system for the present invention to strictly verify its effectiveness and simulate it. Eight PMU units are installed in the system, according to figure 1As described in step 1, select 111 numerical attributes, including: the voltage magnitude of 8 PMU nodes; the active / reactive power flows and currents on 75 branches; and the voltage phase difference of 28 nodes. To enrich the knowledge base, the node load (active / reactive power) is randomly varied between 90% and 110% of the initial value.
[0066] Using V-cross-validation to determine the optimal tree height J and the optimal number of small decision trees L. Randomly divide the training samples in the initial knowledge base into V subsets. For a given fixed tree height J and the number of decision trees L, use V-1 subsets to train the classification model, and use other subsets for testing. The training process totals Repeat V times, each subset is us...
Embodiment 2
[0068] Embodiment 2: The test power system used in this embodiment is a part of the Western Electricity Coordinating Council (WesternFlectricity Coordinating Council, WECC) system, and it consists of more than 600 nodes (wherein there are 33 nodes equipped with PMU devices), 700 transmission lines lines and 100 generators.
[0069] Figure 5 The expression is based on this system using the integrated decision tree-based online dynamic security assessment method for power systems of the present invention, compared with the single decision tree, the result of misclassification error rate obtained. It can be seen that, for two different simulation sub-cycles, the learning method based on the integrated decision tree has a higher accuracy rate than the single decision tree, achieving the purpose of the present invention.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com