A method and device for short-term power load forecasting
A power load, short-term technology, applied in the field of data analysis, can solve problems such as low prediction accuracy and increase operating costs of power companies, and achieve strong robustness, strong robustness, and accurate prediction effects
Active Publication Date: 2021-01-26
GUANGDONG UNIV OF TECH
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] However, in the existing technology, the prediction accuracy is generally not high, which will increase the operating cost of the power company
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] The core of the present invention is to provide a short-term power load forecasting method. In the prior art, the electric load is usually forecasted by using artificial neural network combined with the least square method. In the specific operation, it is necessary to establish a corresponding forecasting model in advance according to the historical power data of the power company, and then predict the power load data in the subsequent period of time according to the input real-time power load data. As the most basic method for estimating regression coefficients, the least squares method describes the influence of the independent variable X on the mean of the dependent variable Y, but the least squares method needs to make distribution assumptions in advance for the random disturbance of the power data input in the prediction model, such as presupposition The random disturbance is mean distribution, normal distribution and so on. However, in real life, the above assum...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a short-term power load forecasting method, which uses a hybrid forecasting model optimized by a hybrid particle swarm optimization algorithm (PSOGSA) to predict the power load through a comprehensive quantile regression and a robust extreme learning machine. Quantile regression uses multiple quantiles of historical power data influencing factors to obtain the corresponding quantile equation of the conditional distribution of power load forecast data at a certain point in the future. The random disturbance of the input power data in quantile regression does not need to do anything The assumption on the distribution can describe the statistical distribution of the predicted load value in detail, making the whole forecasting model have strong robustness; while the robust extreme learning machine is more robust to abnormal load values, combining the above two methods Combined together, the hybrid model formed by PSOGSA optimization can accurately predict the electric load; the present invention also provides a short-term electric load forecasting device, which also has the above beneficial effects.
Description
technical field [0001] The invention relates to the field of data analysis, in particular to a method and device for short-term power load forecasting. Background technique [0002] Due to the fact that electricity cannot be stored directly, in today's society, power is always generated and used at any time. However, in daily life, people's power consumption generally fluctuates, and there are peaks and valleys, but people's power consumption status can be predicted, so that the power company can provide accurate power supply. [0003] Short-term power load forecasting is of great economic significance to the operation and planning of power systems. Accurate power load forecasting helps power companies to make reasonable power generation plans and can effectively reduce the operating costs of power companies. [0004] In the prior art, the electric load is usually forecasted by using artificial neural network combined with the least square method. In the specific operation...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06N3/04G06N3/08G06Q50/06
CPCG06N3/08G06Q10/04G06Q50/06G06N3/048
Inventor 王星华鲁迪彭显刚贺小平郑伟钦
Owner GUANGDONG UNIV OF TECH