A Risk-Aware Deep Learning-Driven Limit Transmission Capacity Adjustment Method

Abstract

The invention discloses a risk-aware deep learning-driven limit transmission capacity adjustment method, which includes the following steps: embedding the limit transmission capacity predictor into the adjustment model, replacing the most complicated and time-consuming calculation part, and obtaining deep confidence A two-layer model assisted by a network agent; construct a prediction interval based on a deep confidence network, and adjust the prediction interval according to the coverage probability of the prediction interval, the normalized average bandwidth of the prediction interval, and the cumulative bandwidth deviation, and obtain the optimal prediction interval through integrated learning training; Based on the trained prediction interval, the probability R of the TTC value falling within the interval is obtained, and the risk probability of prevention and control failure is evaluated according to the probability R; the probability R is introduced into the objective function of the two-layer model assisted by a deep confidence network agent, and the limit transmission capacity is adjusted. value. Through the invention, the balance between adjusting cost and controlling risk can be realized.

Description

Technical field [0001] The present invention is directed to a specific transmission capacity adjustment method for a deep learning drive of a perceived risk. Background technique [0002] TTC's preventive control issues are not only necessary to quickly perceive TTC, but also need to develop TTC preventive adjustment strategies within a minute time. Some scholars propose sensitivity techniques to adjust the trend of the section, however, for the calculation of sensitivity is too rough and more expected, the episode is not considered in this study. In general, there is currently a safe economic study for TTC prevention schedules, so there is an urgent need to solve this problem. In recent years, some scholars have proposed an optimization strategy for surrogate-associisted, sa. The policy uses machine learning agent rules instead of optimizing high-dimensional non-linear or complex differential equations in the model, greatly reducing optimization model solving complexity, and is ...

AI Technical Summary

Problems solved by technology

If some studies propose to add a certain margin to the control model to make the operating point of the system farther away from the critical safety point, however, this scheme is difficult to ensure the economy of regulation, and will lead to a decrease in the convergence of optimization in practical applications; some scholars also propose Use ensemble learning to quantify the prediction error with probability. However, this scheme is only for classification decision trees, and the compatibility of machine learning methods and regression problems still needs to be studied.

Images