Space-based resource capacity virtualization method and system based on situation and demand hybrid drive

• Main Authors: YANG YUXUAN, LEE YOUNG-OK, MENG XIN
• Format: Patent
• Language: Chinese; English
• Published: 02.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention belongs to the technical field of space-based resource management and scheduling, and particularly relates to a space-based resource capacity virtualization method and system based on situation and demand hybrid drive. The method comprises the steps that heterogeneous situation data and task demand data of a single satellite or a satellite cluster are collected, feature extraction is conducted on different types of data, then fusion is conducted, and preprocessing is achieved; a deep learning method is adopted for the preprocessed data, and high-dimensional feature vectors are output; and based on the high-dimensional feature vector, according to resource feature constraints, task element constraints and situation environment constraints, generating virtualization capability description through a basic algorithm, a constraint algorithm and an evaluation algorithm. According to the method, more comprehensive and more accurate space-based system state description can be provided, the accuracy of r