An Evolutionary Algorithm With Memory Guidance for Data Transmission Scheduling Optimization in Communication Satellite Network

作者：Yingying Ren, Qiuli Li, Yue Zhang, Jiting Li, W. Pedrycz, P. Suganthan, Rammohan Mallipeddi, Yan-Jie Song · 发表于：IEEE Transactions on Systems, Man & Cybernetics. Systems · 年份：2026 · DOI：10.1109/tsmc.2025.3647265 · 被引用次数：17 · 研究领域：Computer Science

With the rapid development of satellite technology, communication satellites have become an indispensable part of modern infrastructure. They serve as a key pillar for the future integrated communication satellite network (CSN). However, the increasing number of communication satellites presents significant challenges for data transmission between the satellite and ground station. This article focuses on transmitting communication data by scheduling resources for communication tasks. The goal of data transmission scheduling optimization in CSN (DTSOCSN) is to design a scheduling scheme that maximizes task profit across satellite–ground links, considering the constraints of the two working modes of communication satellites. To solve DTSOCSN, a mixed-integer programming model is developed, which incorporates various constraints such as the conditions for feed switching operation and the limitations of task execution windows. Based on the complexity of the problem, we propose an evolutionary algorithm with memory guidance (MGEA). The algorithm takes into account the memory dependence of Caputo fractional-order differential and innovatively designs a crossover operator, called Caputo crossover (CX). This crossover method uses the genetic information stored in memory to guide the crossover operation of the next generation, thereby forming a smooth optimization path and improving the search efficiency of the algorithm. In addition, an elite opposition-based heuristic initialization...