Electricity price prediction method based on quantum immune optimization BP neural network algorithm
A BP neural network and quantum immune technology, applied in the field of electricity price prediction based on quantum immune optimization BP neural network algorithm, can solve problems such as low accuracy, slow learning speed, easy to fall into local minimum points, etc., to achieve improved accuracy, nonlinear The effect of strong mapping ability, saving human and financial resources
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] Embodiment 1 of the present invention provides an electricity price prediction method based on the quantum immune optimization BP neural network algorithm. Using the BP neural network of the quantum immune optimization algorithm to analyze the electricity price can effectively improve the efficiency and accuracy of electricity price prediction. This method utilizes the characteristics of BP neural network, and uses the quantum immune BP neural network scheme to realize the nonlinear relationship of electricity price changes. Consider electricity price forecasting as a system with multiple inputs (input layer) and multiple outputs (output layer), in which there is an intermediate link (hidden layer) of complex changes and mappings between inputs and outputs. details as follows:
[0063] Input the index values of multiple groups of electricity price influencing factors into the electricity price prediction model; among them,
[0064] Each group of electricity price inf...
Embodiment 2
[0099] Such as image 3 As shown, Embodiment 2 of the present invention provides an electricity price prediction method based on a quantum immune optimized BP neural network.
[0100] Before training the neural network, the training parameters should be initialized first. Table: 3 shows several main parameter values and their meanings in the network training. It should be noted here that if the network training parameters are not assigned before training, the system will select default values (default values) as the training parameters.
[0101] The function of the transfer function is to calculate the output of the basis function to obtain the final output function, which can be regarded as the second processing of the input signal by the neuron. There are many types of transfer functions of the neuron, and different functions With different characteristics and properties, these various functions can be used to construct the entire neural network.
[0102] Table 2: Main...
Embodiment 3
[0115] In Embodiment 3 of the present invention, a BP neural network electricity price prediction method based on quantum immune optimization is provided, and the short-term historical electricity prices and loads of a certain regional electricity market from March 8, 2014 to April 8, 2014 are selected as samples, Then the data samples were divided into two parts, one part was training samples from March 8th to April 2nd, and the other part was prediction samples from April 3rd to April 8th to verify the prediction accuracy of the model. Among them, a total of 60 sets of original data are used as the sample set of the model network, 48 of which are selected as training samples, and the remaining 12 sets of data are used as test sample sets, so the input and output of the neural network can be determined, and some of its training sample data are as follows: Table 3 shows:
[0116] Table 3: Oil chromatography training sample set
[0117]
[0118]
[0119] Some test sample...
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