A Forecast-Aided Power System State Estimation Method
A state estimation and power system technology, applied in electrical components, circuit devices, AC network circuits, etc., can solve the problems of complex power system structure, system state value errors, and difficulty in obtaining accurate power system models, and achieve good reference effects. Effect
Active Publication Date: 2022-02-08
FUSHUN POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER SUPPLY +3
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Static state estimation has been developed for a long time and is very mature, but static state estimation cannot reflect the dynamics of the system
At present, the dynamic state estimation mainly uses the unscented Kalman filter algorithm, but due to the complex structure of the power system, it is difficult to obtain an accurate model of the power system, so it is difficult to obtain the state transition matrix of the power system from the structure to obtain the predicted value of the system at the next moment , the currently commonly used two-parameter exponential method only has a good effect when the system state is stable, and has a large error when the system state value fluctuates greatly, and the prediction effect is worse at the "inflection point"
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
[0060] The invention will be further described below in conjunction with the accompanying drawings and specific implementation examples. The present invention proposes a prediction-assisted power system state estimation method, such as figure 1 As shown, the specific process is:
[0061] Step 1: According to the historical data of the power grid, train the extreme learning machine, such as figure 2 shown.
[0062] Step 1.1: Initial setting of extreme learning machine;
[0063] Set the initial value to: Randomly generate the weight vector ω of the i-th hidden layer node and the input node i =[ω 1 ,ω 2 …, ω K ] T and activation function; take a total of 7k historical load data of the power grid at k times a day in the first seven days as training samples. In the seven-day data, when the data of the d-th day is taken as the input training data, the corresponding next day is taken as The data of day d+1 is used as the output training data. So there are 6 training samples ...
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 present invention proposes a prediction-assisted power system state estimation method, the process includes: training the extreme learning machine according to the historical data of the power grid; using unscented transformation to construct a Sigma point set; calculating the state transition function at time k; obtaining k+1 The Sigma point set of the time prediction value, the inverse transformation of the unscented transformation is performed on the Sigma point set, and the predicted state value of the power grid at k+1 time is obtained; according to the power system prediction data and measurement data, both can be regarded as random Gaussian distribution, according to The Kalman filter algorithm principle is used to obtain the estimated state value of the power grid at k+1 time; and the above steps are repeated according to the judgment conditions; the present invention obtains the predicted data based on the extreme learning machine and the real-time estimated value using state estimation through linear extrapolation The weighted combination of predicted data is carried out, and the weight value is adaptively adjusted through the accuracy of the actual estimated data to obtain more accurate predicted data; more accurate and fast power system state estimation is realized.
Description
technical field [0001] The invention belongs to the technical field of power system information data processing, and in particular relates to a prediction-assisted power system state estimation method. Background technique [0002] State estimation refers to eliminating as many errors as possible from the "raw data" collected by the power system information collection device through redundant measurement and other available information, and identifying bad data among them, so as to obtain data that can be used for subsequent Accurate "cooked data" for analysis. The state estimation of the power system is one of the core functions of the energy management system (EMS) of the power system dispatching center. The data obtained by the state estimation can be used for other applications, including ensuring the economic operation of the system and when the system fails. Security assessment analysis, etc. State estimation is the key link in EMA to ensure the real-time data qualit...
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): H02J3/00
CPCH02J3/00H02J2203/20
Inventor 裴玉杰刘鑫蕊张磊潘奕林顾耀鼎黄博南孙秋野吴巍梁李国
Owner FUSHUN POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER SUPPLY