Data-driven scheduling method based on renewable energy consumption capacity

Abstract

A data-driven scheduling method based on renewable energy consumption capacity, based on the deviation between the actual output of renewable energy and the predicted output, grid security constraints, that is, the conditions that need to be met to maintain safe and stable operation of the grid, and the capacity and creep of thermal power units Slope capacity, the constraints that need to be considered when constructing the renewable energy consumption range of the power grid; according to the probability distribution characteristics of the deviation between the actual output of renewable energy and the predicted output, a variable distribution robust joint opportunity constraint is established to measure the renewable energy Energy consumption capacity; based on variable distribution robust chance constraints and renewable energy consumption capacity, with grid pre-scheduling costs and renewable energy consumption probability as the objective function, a joint optimization stochastic scheduling model is established; then the distribution robust joint Chance constraints are converted into second-order cone constraints, and the two-stage distribution robust optimization problem is transformed into a second-order cone programming problem by using the robust optimization standard technology, and the consumption range of renewable energy is obtained through the solution, and the consumption range is issued To the corresponding renewable energy unit, as the scheduling guidance of the renewable energy unit. This method significantly enhances the energy consumption capacity and improves the out-of-sample performance of renewable energy consumption.

Description

technical field [0001] The present invention relates to a technology in the field of distribution network resource optimization, in particular to a data-driven scheduling method based on renewable energy consumption capacity. Background technique [0002] Compared with existing energy sources, the output of renewable energy has stronger volatility and uncertainty. Existing scheduling methods usually regard renewable energy as non-schedulable resources, and the power grid adjusts the output of other schedulable resources to meet the requirements of system supply and demand balance, and often does not give scheduling instructions for renewable energy. For grids with large-scale access to renewable energy, if renewable energy is not dispatched, the operating cost of the grid may be too high, and even in some cases there is no feasible dispatch solution, especially when the proportion of renewable energy is relatively low. When the value is high, the problem occurs more frequen...

AI Technical Summary

Problems solved by technology

In recent years, a lot of research has been done on the issue of the maximum consumption range of renewable energy at home and abroad, but most of the research lacks the consideration of the output probability information of renewable energy, so the optimal solution obtained does not realize the optimal solution between different renewable energy sources. Reasonable distribution of the sample, the performance out of the sample is unsatisfactory

Images