Multi-satellite distributed cooperative rescheduling method for emergency tasks

Abstract

The invention provides an emergency task-oriented multi-satellite distributed cooperative rescheduling method. The method comprises the following steps of: 1, generating a plurality of offline feasible solutions on the ground; 2, sending the offline feasible solution to a solution trainer to obtain an optimal scheduling strategy of how each satellite executes an action in different states facing emergency task insertion; 3, uploading the offline feasible solution and the optimal scheduling strategy to the satellite; 4, when the emergency task is received, calculating the income of the feasiblesolution after the emergency task is inserted; 5, evaluating the state of the current satellite by using an evaluator, and matching the state with the state corresponding to the optimal scheduling strategy; 6, selecting an optimal action from the optimal scheduling strategy; and 7, enabling the optimal action to update the currently executed feasible solution. According to the method, the optimalscheduling strategy in various possible states of the emergency task is trained by using the strong computing power of the ground, so that the on-satellite complex scheduling problem becomes a simpleselection problem, and the solving quality which is not worse than the ground can be obtained in a short time.

Description

technical field [0001] The invention belongs to the field of satellite mission planning and dispatching, in particular to a multi-satellite distributed cooperative rescheduling method oriented to emergency missions. Background technique [0002] Earth observation satellite (EOS) is the main platform for space image collection, and its main task is to obtain observation information on the earth's surface according to user needs. Because of its advantages such as wide coverage, long imaging time, and no border restrictions , Earth observation satellites are playing an increasingly important role in tasks such as economic development, disaster relief, and emergency monitoring. [0003] In recent years, with the development of satellite technology, a new generation of satellites already has certain computing and processing capabilities, which makes it possible for satellite control to reduce human intervention and make autonomous decisions. The current research on autonomous sa...

AI Technical Summary

Problems solved by technology

[0006] Another difficulty in online rescheduling is the multi-satellite cooperative scheduling problem under the limitation of communication between multiple satellites and between satellites and the ground

Using the centralized coordination method, due to the limitation of the communication window between the satellite and the ground, a large number of observation opportunities will be lost when considering the random arrival problem of emergency tasks; another distributed coordination method, which is currently more common, includes multi-agent Contract network architecture, collaboration using pheromone graphs, etc., but these methods rely too much on frequent inter-satellite communications, which consume a high cost

However, the greedy search strategy adopted by Skobelev et al., due to the lack of global information in the decision-making of each satellite, conflicts and repeated observations are likely to exist between the generated solutions, and it is difficult to improve the income.

Images