Power load probabilistic prediction method based on chaotic population algorithm and Bayesian network

Abstract

The invention discloses a power load probability prediction method based on a chaotic population algorithm and a Bayesian network, and the method comprises the steps: 1, obtaining the actual data of an air temperature, relative humidity, wind power and power load time sequence, carrying out the preprocessing of each column of data, and dividing a training set and test set data; 2, performing wavelet threshold de-noising processing on the original data of the power load, and restoring real information of a time sequence of the power load; 3, constructing a Bayesian network model to obtain an initial prediction interval; 4, calculating an interval change amplitude range, and obtaining an optimal interval change amplitude by applying a chaotic population algorithm; 5, chaotic search is adopted in the neighborhood of the optimal interval change amplitude, and a final prediction interval is obtained. The uncertainty of the power load can be measured by constructing the prediction interval,so that an effective reference can be provided for the optimized operation of the power system.

Description

technical field

[0001] The invention relates to the field of power consumption, and mainly relates to a power load forecasting model method based on wavelet threshold denoising, Bayesian network and chaotic crowd search algorithm. Background technique

[0002] In recent years, the growth of consumption and the continuous improvement of production capacity have led to an increasing demand for electricity. Among them, the ever-increasing information flow and data flow are important components of the power system. By analyzing the characteristic data and power data, the online power load prediction is helpful to the stable operation of the power grid system and the status evaluation of hardware equipment. At the same time, due to the high proportion of electric energy in the use of various energy sources, the management and scheduling of electric energy has become extremely important. By making accurate and reliable predictions of power loads, power consumption can be saved to...

Examples

Embodiment Construction

[0080] In this embodiment, a probabilistic prediction method of power load based on chaotic crowd algorithm and Bayesian network, such as figure 1 As shown, including: obtaining the actual data of temperature, relative humidity, wind power and power load, and preprocessing the data; performing wavelet threshold de-drying processing on the original data of power load, restoring the real information of the time series of power load; establishing a Bayesian network model , to obtain the initial prediction interval; calculate the range of interval change amplitude, and use the chaotic crowd algorithm to obtain the optimal interval change range when the fitness function is optimal, so as to obtain the final prediction interval, and analyze and evaluate the prediction results. Specifically, proceed as follows:

[0081] Step 1. Obtain the actual values ​​of air temperature, relative humidity, wind force and electric load and perform data preprocessing:

[0082] Step 1.1, collect the...

technical field

[0001] The invention relates to the field of power consumption, and mainly relates to a power load forecasting model method based on wavelet threshold denoising, Bayesian network and chaotic crowd search algorithm. Background technique

[0002] In recent years, the growth of consumption and the continuous improvement of production capacity have led to an increasing demand for electricity. Among them, the ever-increasing information flow and data flow are important components of the power system. By analyzing the characteristic data and power data, the online power load prediction is helpful to the stable operation of the power grid system and the status evaluation of hardware equipment. At the same time, due to the high proportion of electric energy in the use of various energy sources, the management and scheduling of electric energy has become extremely important. By making accurate and reliable predictions of power loads, power consumption can be saved to...

Examples

Embodiment Construction

[0080] In this embodiment, a probabilistic prediction method of power load based on chaotic crowd algorithm and Bayesian network, such as figure 1 As shown, including: obtaining the actual data of temperature, relative humidity, wind power and power load, and preprocessing the data; performing wavelet threshold de-drying processing on the original data of power load, restoring the real information of the time series of power load; establishing a Bayesian network model , to obtain the initial prediction interval; calculate the range of interval change amplitude, and use the chaotic crowd algorithm to obtain the optimal interval change range when the fitness function is optimal, so as to obtain the final prediction interval, and analyze and evaluate the prediction results. Specifically, proceed as follows:

[0081] Step 1. Obtain the actual values ​​of air temperature, relative humidity, wind force and electric load and perform data preprocessing:

[0082] Step 1.1, collect the...

Images