Power distribution network random optimization scheduling method and device, and medium

Abstract

The embodiment of the invention discloses a power distribution network random optimization scheduling method and device and a medium. The method comprises the steps of obtaining a load historical value, a distributed power supply historical output value and a historical meteorological condition value of a power distribution network; performing cluster division on the distributed power supplies andloads based on fuzzy clustering to obtain a plurality of distributed power supply clusters and a plurality of load clusters; and processing each cluster by using the corresponding prediction model ofeach cluster to obtain an output prediction value and a load prediction value, wherein through cluster division, the accuracy of a prediction result is improved; establishing an objective function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output prediction value, the load prediction value and the costs of various power distribution networks; and solving the objective function under the constraint condition by using a hybrid intelligent algorithm to obtain a power distribution network scheduling result. The constraint condition fully considers the output of the distributed power supply and the randomness of the load, and can better meet the safe and stable operation of the power distribution network.

Description

technical field [0001] The present invention relates to the technical field of distribution network, in particular to a method, device and computer-readable storage medium for stochastic optimal scheduling of distribution network. Background technique [0002] The load is the basis for the operation and planning of the power system. With the increase of the penetration rate of distributed power generation, the scheduling potential of the user side has been greatly improved. In the development process of the dispatching technology of the active distribution network, there are two main problems that need to be solved urgently. One is how to accurately predict the output of distributed generation and user load, and the other is how to consider the output of distributed generation and the randomness of load. sex. [0003] In the conventional distribution network dispatching mode, the load and distributed output values ​​are often roughly forecasted, and the forecast error and r...

AI Technical Summary

Problems solved by technology

[0003] In the conventional distribution network dispatching mode, the load and distributed output values ​​are often roughly forecasted, and the forecast error and real-time fluctuations are adjusted through energy storage and flexible loads. However, this mode is often not accurate enough for load and distributed output forecasting. Scenarios even fail completely

And use flexible load or load shedding to balance distribution network load fluctuations and deal with distributed output, the randomness of load fluctuations will cause a lot of flexible load scheduling and backup costs, which is not conducive to the safe and stable operation of distribution network

Images