Data driving scheduling method based on renewable energy consumption capability

Abstract

The invention discloses a data driving scheduling method based on renewable energy consumption capability. The method comprises the steps: obtaining a scheduling result according to the deviation between the actual output and predicted output of renewable energy, the safety constraint of a power grid, i.e., the conditions required by the power grid for maintaining safe and stable operation, and the capacity and climbing capability of a thermal power generating unit; constructing constraint conditions needing to be considered when the renewable energy consumption range of the power grid is constructed; establishing a variable distribution robust joint chance constraint according to the probability distribution characteristic of the deviation between the actual output and the predicted output of the renewable energy source, and measuring the absorption capacity of the renewable energy source; based on the variable distribution robust opportunity constraint and the renewable energy consumption capability, establishing a joint optimization random scheduling model by taking the power grid pre-scheduling cost and the renewable energy consumption probability as target functions; then converting the distribution robustness joint chance constraint into a second-order cone constraint, converting a two-stage distribution robustness optimization problem into a second-order cone programmingproblem by applying a robustness optimization standard technology, obtaining an absorption range of renewable energy sources by solving, and issuing the absorption range to a corresponding renewableenergy source unit; the method is used as scheduling guidance of renewable energy units. According to the method, the energy consumption capacity is remarkably enhanced, and the sample exterior performance of renewable energy consumption is improved.

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