Power distribution network voltage reactive power optimization method based on BART algorithm

Abstract

The invention discloses a power distribution network voltage reactive power optimization method based on a BART algorithm. The BART algorithm is an integrated predication method, an accumulative regression tree model is decomposed into a plurality of weak regression trees through a non-parametric Bayesian regression method, and an integrated predication system is formed through an integrated method. Each weak regression tree is in charge of a small part in the entire integrated predication system, and the influence, on predication, of a single regression tree module is weakened to improve the predication effect of the entire integrated model. According to the power distribution network voltage reactive power optimization method based on the BART algorithm, based on self learning of historical sample data and under the premise that voltages are in a reasonable controlled range is guaranteed, the actions of adjusting a transformer tap and the actions of switching of a capacitor bank are as less as possible, under the idea state that the voltages on the lower voltage side of a transformer and the reactive power are small in transmission loss, complex optimization models do no need to be solved in the optimization process, the influences of loads, the voltages and the reactive power are completely considered, and flexible adjusting is conducted on reactive power.

Description

technical field [0001] The invention belongs to the field of electric power system relay protection automation, and relates to a distribution network voltage and reactive power optimization control method, in particular to a distribution network voltage and reactive power optimization control method based on BART algorithm. Background technique [0002] In the power system, the power distribution system needs reactive power management to ensure that the voltage is within the normal control range and reduce network losses. Factors affecting system voltage and reactive power include engine voltage, transformer tap position, shunt capacitor, reactor group and system load, etc. At present, the main equipment used for voltage and reactive power adjustment in most substations in my country is on-load tap changer and Parallel compensation capacitor bank, adjust the voltage and reactive power by adjusting the transformer tap position and switching the parallel capacitor bank. [000...

AI Technical Summary

Problems solved by technology

[0003] The literature "Research on Voltage and Reactive Power Control Strategies of Substations under AVC Decentralized Control Mode" lists several voltage and reactive power control strategies commonly used in substations: (1) Control according to the power factor: if the power factor is lower than the lower limit, the capacitor bank will be used, and the high If the upper limit is lower than the upper limit, the capacitor bank will be removed; however, the power factor is only a part of the reactive component and cannot accurately reflect the reactive component of the grid load. (2) Control according to the bus voltage level: mainly adjust the voltage and reactive power based on the voltage level

The defect is that the condition of reactive power balance is not considered. According to the actual operation results, the compensation effect of this method is relatively poor; (3) Comprehensive control based on the nine-area map: the current operating area is judged by real-time voltage and reactive power information, and then based on The control strategy of the nine-area map adjusts gears and switches capacitor banks; in the control strategy of the nine-area map, the boundaries of voltage and reactive power are fixed, which cannot reflect the mutual influence of voltage and reactive power, and there are no restrictions on the use of control equipment. It meets the actual operation requirements and may lead to voltage instability; (4) seek the optimal control strategy based on global planning based on short-term load forecasting. According to the short-term load forecasting value, the transformer tap and capacitor bank maximum The number of actions is the optimization condition, establish the objective function involving the secondary side voltage of the state variable and the reactive power of the incoming line, solve the optimization problem to determine the position of the voltage tap and the switching of the capacitor; the difficulty lies in the establishment and solution of the objective function; (5) based on Fuzzy control of artificial intelligence: extract fuzzy rules on the basis of nine-zone map control, and optimize adjustment strategies

However, the robustness and reliability of fuzzy control are poor, and it is subjective, and cannot make full use of the characteristics of sample data; (6) Artificial neural network control: Introduce the learning and self-adaptive ability of neural network into voltage and reactive power regulation Among the problems, this method has strong fault tolerance, but the structure and operation mode of the power system are constantly changing, and there are not enough training samples, so it is difficult to quickly train the neural network model

Images