Reservoir scheduling rule optimization method based on machine learning fused with multi-source remote sensing data

Abstract

The invention provides a reservoir scheduling rule optimization method based on machine learning fused with multi-source remote sensing data; the method comprises the steps: collecting short-series runoff observation data of a reservoir, and extracting a rainfall series, meteorological data and a land water reserve series of a drainage basin where the reservoir is located; according to the short-series runoff observation data and the meteorological data, establishing a hydrological model of a basin where the reservoir is located, and preliminarily simulating runoff; constructing a long-term and short-term memory neural network model and correcting the simulated runoff by adopting the long-term and short-term memory neural network model to obtain a corrected simulated runoff series; inputting the acquired long-series meteorological data into a hydrological model and the corrected simulated runoff system, and simulating a long-series reservoir inflow runoff process of the reservoir; and constructing a multi-objective optimization scheduling model according to the obtained reservoir long-series reservoir inflow runoff, and solving an optimized scheduling rule by adopting a genetic algorithm. According to the invention, multi-source remote sensing data is fused for simulating a long-series runoff process, and a reference basis is provided for reservoir scheduling and water resource planning.

Description

technical field [0001] The invention belongs to the technical field of reservoir dispatching, and in particular relates to a method for optimizing reservoir dispatching rules based on machine learning and fusion of multi-source remote sensing data. Background technique [0002] Hydrometeorological data are the basic basis for project planning, design, construction and operation management, and are also important data for assessing the flood control risk of water conservancy projects in the basin. However, some reservoirs in my country have only a small amount of measured hydrometeorological monitoring data. Therefore, how to invert the long series of runoff processes and guide the operation and scheduling of reservoirs is a major challenge for hydrologists. [0003] In recent years, satellite telemetry technology and data inversion algorithms have developed rapidly. The precipitation quantitative observation products based on satellite remote sensing inversion have a wider c...

AI Technical Summary

Problems solved by technology

[0004] However, the hydrological model is suitable for simulating the runoff process in the natural state. Engineering measures such as dams, reservoirs, agricultural irrigation, water diversion, and inter-basin water transfer often destroy the consistency of the underlying surface, resulting in large errors in the hydrological model of the basin. Restricts the accuracy of hydrological simulation

The existing literature fails to make full use of satellite telemetry meteorological information, fails to consider the error caused by human activity interference on runoff simulation, and cannot solve the long series of runoff simulation problems in areas with scarce data, and is difficult to be used in the application practice of optimizing reservoir dispatching rules

Images