Unit commitment optimization method considering new energy consumption

Abstract

The invention relates to a unit commitment optimization method considering new energy consumption. The method comprises the following steps: step 1, constructing a day-ahead new energy consumption dynamic evaluation model; step 2, predicting the short-term generating capacity of the new energy unit based on an LSTM neural network, including preprocessing historical data and completing prediction of the generating capacity of the new energy unit by using the LSTM neural network; step 3, converting a unit commitment problem into a Markov decision process, including design of a power grid state st, an action at, a reward value Rt and a transfer function; and step 4, according to the historical operation data characteristics of the power grid, intelligent agent construction is completed based on a parameter adaptive neural network, an intelligent agent is trained, and a unit output plan meeting a new energy consumption target is obtained. According to the invention, the stability of a novel power system taking new energy as a main body can be improved, efficient utilization of clean energy is realized, and consumption of the new energy is completed on the premise of reliable operation of a power grid.

Description

technical field [0001] The invention belongs to the technical field of self-adaptive real-time dispatching of power systems, and relates to a unit combination optimization method, in particular to a unit combination optimization method considering new energy consumption. Background technique [0002] The new power system is based on new energy, supported by source-grid-load-storage interaction and multi-energy complementarity, and has the basic characteristics of clean and low-carbon, safe and controllable, flexible and efficient. The new power system has developed rapidly in recent years, but there are relatively few domestic and foreign researches on energy supply, safe operation and clean consumption. The control problem of the new power system has been transformed from a single optimization problem to a multi-layer, multi-region and multi-objective optimization problem in complex scenarios. Traditional dispatching methods first mathematically model the unit combination ...

AI Technical Summary

Problems solved by technology

[0003] After searching, no documents of the prior art identical or similar to the present invention were found

Images