Wind power multi-scenario robust scheduling method based on gan scenario simulation

Abstract

The invention discloses a wind power multi-scenario robust dispatching method based on gan scene simulation, comprising the steps of: (1) determining the operating parameters of the dispatching system; (2) collecting historical wind speed scene data; (3) using a generative confrontation network to generate wind speed (4) Reduce the scene of the wind speed scene; (5) Build the robust scheduling model of the power system including the wind farm; (6) Use the robust optimization method to solve the built scheduling model. The invention adopts the generative confrontation network to simulate the wind speed scene of the wind farm, without introducing a complex wind speed prediction model, and does not need to use the probability distribution of the wind speed for sampling, which greatly simplifies the scene simulation process.

Description

technical field [0001] The invention relates to the field of optimal operation and control of electric power systems, in particular to a wind power multi-scenario robust scheduling method based on gan scene simulation. Background technique [0002] With the increasing penetration of renewable energy such as wind and solar power generation, the security and stability of the power system is severely challenged, and research on the scheduling and operation strategies of high-penetration renewable energy systems is also in full swing. [0003] At present, there are mainly stochastic optimization methods and robust optimization methods for the dispatching methods of power systems with high penetration of wind power. These two methods have their own advantages and disadvantages, and can solve the related wind power high penetration system scheduling problems in specific scenarios, but each of these two methods has an urgent problem to be solved: how to determine the probability di...

AI Technical Summary

Problems solved by technology

These two methods have their own advantages and disadvantages, and can solve the related wind power high penetration system scheduling problems in specific scenarios, but each of these two methods has an urgent problem to be solved: how to determine the probability distribution of wind power output in the stochastic optimization method And how to determine the worst scenario in the robust optimal scheduling method

The above two problems will more or less adopt probability sampling or empirical probability distribution model, but this method undoubtedly has the problem of idealization of the plan and actual engineering errors. At the same time, if the method of probability sampling is used, the sampling scene obtained If it is too much, it will increase the difficulty of scheduling calculation and affect the timeliness of scheduling. If it is too small, it will be less representative and the engineering practicability will be low.

Images