Distributed energy storage configuration method and system adaptive to random optimization decision

Abstract

The invention discloses a distributed energy storage configuration method and system adaptive to a random optimization decision, and belongs to the field of power distribution network planning, and the method comprises the steps: obtaining an observation state of a power distribution network at a t moment in a usual electricity price period and a peak time electricity price period; a corresponding energy storage discharge strategy is adopted according to the current state, a power distribution network instant return model is obtained, and training of a neural network based on a competition depth Q network is carried out; and acquiring a real-time observation state at the moment k, inputting the real-time observation state into the trained neural network, outputting an energy storage discharging strategy in the real-time observation state, and combining the energy storage discharging strategy with the charging strategy to obtain a complete energy storage charging and discharging strategy in the typical daily period. According to the method, an energy storage configuration planning model based on a Markov decision process is established, the influence of random power flow on energy storage power and capacity is analyzed, and energy storage scheduling optimization is embedded into energy storage configuration planning under the constraint condition of satisfying random fluctuation of a distributed power supply and a load, so that planning and operation integrated optimization of distributed energy storage is realized.

Description

technical field [0001] The invention belongs to the field of distribution network planning, and more specifically relates to a distributed energy storage configuration method and system adapted to stochastic optimization decision-making. Background technique [0002] In recent years, distributed power sources have been widely connected, and the fluctuation of renewable energy output combined with the uncertainty of user behavior has brought greater pressure on the balance of supply and demand in the distribution network. Distributed energy storage participating in the optimal operation of the distribution network is a new s solution. The distributed energy storage configuration method adapted to the optimal operation of the distribution network is the key technology to fully consume distributed power. [0003] At present, the optimal configuration method of distributed energy storage is generally based on the two-layer coupling model of planning and operation optimization, ...

AI Technical Summary

Problems solved by technology

[0004] The two-layer model currently established takes into account both investment and operation optimization. The solution of the model requires the use of intelligent algorithms to iteratively solve the optimization results based on the mutual feedback between the two layers, which increases the difficulty of calculation; the current solution algorithms such as genetic algorithms and differential evolution algorithms are difficult. find the optimal solution

Images