About the journal


Cobiss

Computer Science and Information Systems 2024 Volume 21, Issue 4, Pages: 1335-1357
https://doi.org/10.2298/CSIS231129035C
Full text ( 495 KB)


A method for solving reconfiguration blueprints based on multi-agent reinforcement learning

Cheng Jing (School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China), chengjing@xatu.edu.cn
Tan Wen (School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China), tanwen@st.xatu.edu.cn
Lv Guangzhe (Xi’an Institute of Aeronautical Computing Technology (XICT), Xi’an, China), guangzhe lv@163.com
Li Guodong (Aviation Industry First Aircraft Design and Research Institute, Xi’an, China), guodonglee@.com
Zhang Wentao (School of Software, Northwestern Polytechnical University, Xi’an, China), wentaoz@gmail.com
Liu Zihao (Leihua Electronic Technology Research Institute of Aviation Industry Corporation of China (AVIC), Wuxi, China), 2020264414@mail.nwpu.edu.cn

Integrated modular avionics systems primarily achieve system fault tolerance by reconfiguring the system configuration blueprints. In the design of manual reconfiguration, the quality of reconfiguration blueprints is influenced by various unstable factors, leading to a certain degree of uncertainty. The effectiveness of reconfiguration blueprints depends on various factors, including load balancing, the impact of reconfiguration, and the time required for the process. Solving high-quality reconfiguration configuration blueprints can be regarded as a type of multi-objective optimization problem. Traditional algorithms have limitations in solving multi-objective optimization problems. Multi-Agent Reinforcement Learning (MARL) is an important branch in the field of machine learning. It enables the accomplishment of more complex tasks in dynamic real-world scenarios through interaction and decision-making. Combining Multi-Agent Reinforcement Learning algorithms with reconfiguration techniques and utilizing MARL methods to generate blueprints can optimize the quality of blueprints in multiple ways. In this paper, an Improved Value-Decomposition Networks (VDN) based on the average sequential cumulative reward is proposed. By refining the characteristics of the integrated modular avionics system, mathematical models are developed for both the system and the reconfiguration blueprint. The Improved VDN algorithm demonstrates superior convergence characteristics and optimization effects compared with traditional reinforcement learning algorithms such as Q-learning, Deep Q-learning Network (DQN), and VDN. This superiority has been confirmed through experiments involving single and continuous faults.

Keywords: Integrated modular avionics system, Multi-Agent Reinforcement Learning, reconfiguration blueprint, multi-objective optimization problem


Show references