Power system standby shortage risk scene identification method

Abstract

The invention relates to a power system standby shortage risk scene identification method. The method comprises the following steps of: S1, selecting sample features influencing positive and negative standby, and constructing an initial sample set; S2, screening sample features with relatively large mutual information as training sample features, and constructing a training sample set; S3, constructing a decision tree model, and determining an optimal division feature of the decision tree model according to the Gini index of the training sample set under each training sample feature division; S4, selecting the minimum sample number of the optimal leaf nodes by adopting a cross validation method; S5, generating a decision tree sequence with an error correction mechanism; S6, pruning the decision tree sequence to generate an optimal decision tree sequence with error correction codes; S7, evaluating the decision tree model with the error correction mechanism; and S8, utilizing the evaluated decision tree model to identify the standby shortage risk scene of a power system. According to the method, the possible positive and negative standby shortage risk of the power system can be pre-judged, so that the safety of the power system is ensured.

Description

technical field [0001] The invention relates to the technical field of power system security, in particular to a method for identifying risk scenarios of insufficient power system reserve. Background technique [0002] In recent years, the proportion of wind power generation in the total power generation of the power system in various countries has gradually increased. However, wind power has volatility and uncertainty, which brings great security risks to the operation of the power system, such as power imbalance, line overload, and insufficient positive and negative backup. In the real-time operation of the system, the conventional unit combination and scheduling plan have been determined in advance, but due to the fluctuation of wind power output and the limited accuracy of forecasting, for power systems with large-scale wind power access, extreme wind power output often leads to system failures. risk. For example, if the actual wind power output is much smaller than th...

AI Technical Summary

Problems solved by technology

However, wind power has volatility and uncertainty, which brings great security risks to the operation of the power system, such as power imbalance, line overload, and insufficient positive and negative reserves.

In the real-time operation of the system, the conventional unit combination and scheduling plan have been determined in advance, but due to the fluctuation of wind power output and the limited prediction accuracy, for power systems with large-scale wind power access, extreme wind power output often leads to system failures. risk

For example, if the actual wind power output is much smaller than the predicted output, even if the conventional units that start up reach the maximum output, they cannot meet the load demand, and there will be a risk of insufficient power supply; if the actual wind power output is much greater than the predicted output, even if the normal The minimum output cannot meet the full consumption of wind / light, resulting in power shortage and the risk of insufficient negative backup

[0003] However, in view of the risk of insufficient reserve in the power system, a large number of scenarios are often simulated by stochastic simulation methods, and then complex and time-consuming calculation methods are used to determine whether there is a risk of insufficient reserve. Therefore, it is urgent to propose an efficient real-time online risk scenario identification method to ensure the safety of the power system.

Images