Power system short-term load probability forecasting method, device and system
A probabilistic forecasting and short-term load technology, applied in forecasting, instrumentation, data processing applications, etc., can solve the problems that the optimization performance is greatly affected by the selection of the initial value, and the number of iterations is difficult to determine.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0114] Such as figure 1 As shown, the embodiment of the present invention provides a short-term load probability prediction method of a power system, specifically a Gaussian process quantile regression-based power system short-term load probability prediction method, including the following steps:
[0115] Step 1: Obtain input variables; the input variables include: meteorological factors, historical load values, real-time electricity prices, and forecast date types.
[0116] Step 2. Preprocessing the input variables; in a specific implementation of the embodiment of the present invention, the preprocessing of the input variables is to perform normalization processing on the input variables, and the normalization formula is:
[0117]
[0118] in, is the normalized data value of an input variable; x(i) is the original data of the input variable; x max 、x min are the maximum and minimum values of the raw data of the input variables, respectively.
[0119] Step 3. Estab...
Embodiment 2
[0198] Based on the same inventive concept as in Embodiment 1, the embodiment of the present invention provides a short-term load probability forecasting device for a power system, which includes:
[0199] Obtain module, used to obtain input variables;
[0200] The preprocessing module is used to preprocess the input variables;
[0201] A model building module, used to set up a load probability forecasting model based on Gaussian process quantile regression;
[0202] The optimal input variable determination module is used to determine the optimal input variable set based on the preprocessed input variables;
[0203] The model optimization module is used to optimize the hyperparameters in the load probability prediction model by using the particle swarm optimization algorithm, and obtain an optimized load probability prediction model based on Gaussian process quantile regression;
[0204] The prediction output module is used to substitute the optimal input variable set into t...
Embodiment 3
[0209] Based on the same inventive concept as in Embodiment 1, the embodiment of the present invention provides a short-term load probability forecasting system for a power system, including:
[0210] a processor adapted to implement the instructions; and
[0211] The storage device is suitable for storing a plurality of instructions, and the instructions are suitable for being loaded by the processor and executing the steps described in any one of Embodiment 1.
[0212]To sum up: the present invention discloses a short-term load probability forecasting method, device and system of a power system. By selecting the optimal input variable set that affects the load, a short-term load probability density forecasting model of Gaussian process quantile regression is established. First, the random forest algorithm is used to give the importance score of the input variables, and the degree of influence of each input variable is sorted; secondly, the particle swarm optimization algorit...
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