# Adaptive ε-greedy exploration for stable reconfiguration in next-gen aviation IMA systems

## TL;DR

The paper introduces a new adaptive exploration method to improve the stability and efficiency of next-gen aviation systems using container technology.

## Contribution

A novel embedded container reconfiguration method using Double Dueling DQN with adaptive ε-greedy exploration is proposed for IMA systems.

## Key findings

- D3QNAE reduces the first feasible solution time by 34% in large-scale deployments.
- The method achieves 15.6% higher maximum reward and 100% migration impact rate under continuous faults.
- The proposed approach enhances fault tolerance and system stability in container-based IMA systems.

## Abstract

The next-generation aviation Integrated Modular Avionics (IMA) system adopts an architecture based on container technology, offering higher resource utilization and task configuration flexibility while increasing system reconfiguration complexity. Efficient reconfiguration strategies enhance adaptability and fault tolerance, ensuring stable operation and reduced maintenance costs. However, existing manual and heuristic-based methods struggle to meet current fault tolerance requirements. We propose an embedded container reconfiguration method using a Double Dueling DQN with Adaptive \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\varepsilon$$\end{document}-Greedy Exploration (D3QNAE), which incorporates adaptive exploration to efficiently generate stable strategies in complex environments. Experimental results demonstrate that D3QNAE reduces the first feasible solution time by 34\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\%$$\end{document} compared to the best baseline (D3QN) in large-scale deployments (500-task scenarios), while achieving a 15.6\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\%$$\end{document} higher maximum reward value and a 100\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\%$$\end{document} migration impact rate under continuous faults. This method provides enhanced fault tolerance for container-based IMA systems, significantly improving stability.