A Short-Term Load Forecasting Method Based on Similar Day Segmentation and lm-bp Network
A short-term load forecasting, daily load technology, applied in forecasting, neural learning methods, biological neural network models, etc., can solve the problem of not putting forward the quantitative calculation method of the load curve, and achieve the effect of improving the accuracy and forecasting accuracy.
Active Publication Date: 2021-12-10
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although the literature [6] proposed the method of segmenting the daily load curve and then selecting similar days in segments, this literature did not propose a method for quantitative calculation of the specific load curve segment, but simply carried out a qualitative calculation based on the load curve. section
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
[0070] Taking the historical load data and meteorological data of a certain place in 2014 as a sample of short-term load forecasting, the load forecasting is carried out for January 4-10, 2015. The sample data includes historical meteorological data, namely daily maximum temperature, minimum temperature, average temperature, average relative humidity and rainfall, and daily load data every 15 minutes as historical load data.
[0071] Take the load forecast on January 5, 2015 as an example for a detailed introduction. January 5, 2015 is a Monday, so first divide the historical load of all Mondays in the historical data into segments. The calculation results of the correlation coefficient and comprehensive correlation coefficient between the 96 point load vectors and the corresponding 5 meteorological feature vectors of all Monday historical days are as follows figure 1 shown.
[0072] Through comparison, it is found that the value of the comprehensive correlation coefficient ...
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 load forecasting method based on similar day segments and LM-BP network; the invention calculates the daily load curve to be forecasted according to the quantitative calculation of the comprehensive correlation coefficient between the meteorological factors and the corresponding historical load curve of the day to be forecasted Segmentation, the corresponding similar days are obtained for the forecasted load curves in different periods; and the multi-feature similarity judgment criteria based on the historical day meteorological similarity and historical load data trend similarity and shape similarity are considered comprehensively. For the selection of the day, select the similar day samples with the highest similarity from the same type of historical data; and for different periods of the forecast load, different neural network models are established through different training samples, thereby further improving the prediction accuracy of the neural network model . The invention improves the calculation speed and convergence speed of the prediction algorithm.
Description
technical field [0001] The invention belongs to the field of electric power system load forecasting, in particular to a short-term load forecasting method based on similar day segmentation and LM-BP neural network. Background technique [0002] As an important part of load forecasting work, short-term load forecasting of power system is mainly to forecast the load in the next few hours, one day or several days. Its prediction accuracy is of great significance to improve the utilization rate of power generation equipment and the effectiveness of economic dispatch, and to develop and improve the current power market. Short-term load forecasting methods can be divided into classical forecasting methods and modern forecasting methods according to their development history. Traditional forecasting methods are mainly based on the theory of probability and statistics, and common ones include time series method and regression analysis method. The modern prediction methods commonly...
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): G06Q10/04G06Q50/06G06N3/04G06N3/08
CPCG06N3/084G06Q10/04G06Q50/06G06N3/045
Inventor 罗平查道军程晟王坚陈巧勇孙伟华
Owner HANGZHOU DIANZI UNIV