Learning type genetic algorithm-based multi-task and multi-resource rolling distribution method

Abstract

The invention discloses a learning type genetic algorithm-based multi-task and multi-resource rolling distribution method. According to the method, based on the rolling time domain control principle,a multi-task and multi-resource dynamic rolling distribution mechanism is constructed. The multi-task and multi-resource dynamic rolling distribution mechanism comprises a prediction window, a rollingwindow, a sub-problem distributing element and a rolling mechanism element. According to the invention, the task information is updated in real time through a current prediction window, wherein the current rolling window is determined on the basis of the prediction window. During the sub-problem distributing process, a local distribution problem is constructed according to the construction of thecurrent rolling window at each planning moment. The rolling mechanism is used for determining an execution position at the ending of a distribution scheme and a next planning moment after the distribution of a sub-problem is well solved. Through the distribution mechanism, a complex dynamic distribution problem is converted into a plurality of simple and static distribution sub-problems. After that, the optimal solutions of sub-problems are combined to replace the optimal solution of the original problem. As a result, the solving difficulty of the original problem is greatly reduced.

Description

technical field [0001] The invention relates to the technical field of remote sensing satellites, in particular to an observation task allocation method, in particular to a learning genetic algorithm-based multi-task and multi-resource rolling allocation method. Background technique [0002] A remote sensing satellite is an artificial satellite used as a remote sensing platform for outer space. The remote sensing technology using satellite as a platform is called satellite remote sensing. Typically, remote sensing satellites remain in orbit for several years. Satellite orbits can be determined as needed. Remote sensing satellites can cover the entire earth or any designated area within a specified period of time. When running along a geosynchronous orbit, they can continuously remote sense a designated area on the earth's surface. All remote sensing satellites need a remote sensing satellite ground station. The image data obtained by the satellite is transmitted to the gr...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems in the prior art, the object of the present invention is to provide a method for assigning observation tasks (multi-task and multi-resource dynamic rolling allocation method), or a multi-task and multi-resource rolling allocation method based on learning genetic algorithm, so The method described above adopts the multi-task and multi-resource dynamic rolling allocation mechanism, by decomposing the complex dynamic scheduling problem into multiple simple static scheduling sub-problems, and then combining the optimal solutions of the sub-problems to replace the optimal solution of the original problem. Greatly reduces the difficulty of solving the original problem

Images