Cascade reservoir random optimization scheduling method based on deep Q learning

Abstract

The invention discloses a cascade reservoir random optimization scheduling method based on deep Q learning. The method comprises the following steps: describing the reservoir diameter process of a reservoir; establishing a Markov decision process MDPS model; establishing a probability transfer matrix; establishing a cascade reservoir random optimization scheduling model; determining a constraint function of the model: introducing a deep neural network, extracting runoff state characteristics of the cascade reservoir, Meanwhile, realizing approximate representation and optimization of a targetvalue function of the scheduling model; applying reinforcement learning to reservoir random optimization scheduling; establishing a DQN model; and solving the cascade reservoir stochastic optimizationscheduling model by adopting a deep reinforcement learning algorithm. According to the cascade reservoir stochastic optimization scheduling method based on deep Q learning, cascade reservoir stochastic optimization scheduling is realized, so that the generator set is fully utilized in the scheduling period, the power demand and various constraint conditions are met, and the annual average power generation income is maximum.

Description

Technical field [0001] The invention relates to the field of random optimized dispatching of cascade reservoirs, in particular to a method for random optimized dispatching of cascade reservoirs based on deep Q learning. Background technique [0002] Hydropower energy is a renewable clean energy. Our country is rich in hydropower resources and has broad application prospects. A large number of hydropower stations have been built based on the distribution of water resources. Cascade hydropower stations have become the main hydropower system in our country, with multiple benefits such as flood control, power generation, irrigation, and water supply. There are not only power connections between the various power stations of the cascade hydropower stations, but also the reasonable distribution of water resources. While meeting the power system operation requirements, the coordination between power generation and water use must also be considered to achieve maximum comprehensive benefi...

AI Technical Summary

Problems solved by technology

These methods can obtain the optimal solution or near-optimal solution, but the problem of "curse of dimensionality" has not been solved well. At the same time, due to the influence of hydropower station operation accumulation deviation, load demand deviation and runoff forecast deviation, the operation status of hydropower station Deviations will occur, the original optimal scheduling scheme has poor practical guiding significance

Images