重构蓝图定义了故障状态下系统软硬件资源的重新配置方案，是实现综合模块化航空电子系统重构容错的关键。提出了一种基于改进Q学习的重构蓝图生成方法，综合考虑负载均衡、重构影响、重构时间、重构降级等多优化目标，并应用模拟退火框架改进探索策略，提高了传统Q学习算法的收敛性能。实验结果表明，与模拟退火算法、差分进化算法、传统Q学习算法相比，本文提出的改进Q学习算法效率更高，所生成重构蓝图质量更高。
Reconfiguration blueprint defines the reconfiguration scheme of system hardware and software resources in the fault status, and is critical to reconfiguration fault tolerance of the integrated modular avionics system. In this paper, we propose an approach for generating reconfiguration blueprints based on improved Q-learning, which considers multiple optimization objectives such as load balance, reconfiguration impact, reconfiguration time, and reconfiguration degradation. The simulated annealing framework is utilized to enhance the convergence performance of the traditional Q-learning strategy. Experimental results demonstrate that compared with the simulated annealing algorithm, the differential evolution algorithm, and the traditional Q-learning algorithm, the algorithm proposed has higher efficiency, and can generate the reconfiguration blueprints of better quality.
[1] PARR G R, EDWARDS R. Integrated modular avionics[J]. Air & Space Europe, 1999, 1(2):72-75.
[2] SUO D J, AN J X, ZHU J H. A new approach to improve safety of reconfiguration in Integrated Modular Avionics[C]//2011 IEEE/AIAA 30th Digital Avionics Systems Conference. Piscataway:IEEE Press, 2011:1C4-1.
[3] FU J P, WANG S H, LIU B. An original approach to constructing test model for IMA blueprints[C]//2017 Second International Conference on Reliability Systems Engineering (ICRSE). Piscataway:IEEE Press, 2017:1-6.
[4] JOLLIFFE G, NICHOLSON M. Exploring the possibilities towards a preliminary safety case for IMA blueprints[C]//Constituents of Modern System-Safety Thinking, 2005.
[5] ZHOU T R, XIONQ H, ZHANG Z. Hierarchical resource allocation for integrated modular avionics systems[J]. Journal of Systems Engineering and Electronics, 2011, 22(5):780-787.
[6] MONTANA D, HUSSAIN T, VIDAVER G. A genetic-algorithm-based reconfigurable scheduler[M]//Evolutionary Scheduling, 2007:577-611.
[7] GIRAULT A, KALLA H, SIGHIREANU M, et al. An algorithm for automatically obtaining distributed and fault-tolerant static schedules[C]//2003 International Conference on Dependable Systems and Networks. Piscataway:IEEE Press, 2003:159-168.
[8] OMIECINSKI T A. Reconfigurable integrated modular avionics[D]. Bristol:University of Bristol, 1999.
[9] XU J H, PU H J, SUN Z K. Study of fault tolerance design for Integrated Modular Avionics system[C]//Proceedings of Korean Aerospace Society Academic Conference, 2011:1710-1714.
[10] SUTTON R S, BARTO A G. Reinforcement learning:An introduction[J]. IEEE Transactions on Neural Networks, 1998, 9(5):1054.
[11] WATKINS C J C H, DAYAN P. Q-learning[J]. Machine Learning, 1992, 8(3-4):279-292.
[12] WANG R, PURSHOUSE R C, FLEMING P J. Preference-inspired coevolutionary algorithms for many-objective optimization[J]. IEEE Transactions on Evolutionary Computation, 2013, 17(4):474-494.
[13] 刘若辰, 李建霞, 刘静, 等. 动态多目标优化研究综述[J]. 计算机学报, 2020, 43(7):1246-1278. LIU R C, LI J X, LIU J, et al. A survey on dynamic multi-objective optimization[J]. Chinese Journal of Computers, 2020, 43(7):1246-1278(in Chinese).
[14] CUI Y Q, SHI J Y, WANG Z L. Backward reconfiguration management for modular avionic reconfigurable systems[J]. IEEE Systems Journal, 2018, 12(1):137-148.
[15] WANG R P, LU W T, ZENG C H, et al. Reliability modeling and verification method for dynamic reconfiguration system[C]//2018 Prognostics and System Health Management Conference (PHM-Chongqing). Piscataway:IEEE Press, 2018:941-947.
[16] WEI X M, DONG Y W, XIAO M R. Safety-based software reconfiguration method for integrated modular avionics systems in AADL model[C]//2018 IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C). Piscataway:IEEE Press, 2018:450-455.
[17] POURMOHSENI B, WILDERMANN S, GLAß M, et al. Hard real-time application mapping reconfiguration for NoC-based many-core systems[J]. Real-Time Systems, 2019, 55(2):433-469.
[18] ZHANG Q, WANG S H, LIU B. Approach for integrated modular avionics reconfiguration modelling and reliability analysis based on AADL[J]. IET Software, 2016, 10(1):18-25.
[19] DA FONTOURA A A, DO NASCIMENTO F A M, NADJM-TEHRANI S, et al. Timing assurance of avionic reconfiguration schemes using formal analysis[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 56(1):95-106.
[20] GUO R, ZHONG D M, SUN R, et al. Optimized design of resource sharing and isolation for integrated modular avionics[C]//2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS). Piscataway:IEEE Press, 2019:444-447.
[21] CLEMENTE J A, RAMO E P, RESANO J, et al. Configuration mapping algorithms to reduce energy and time reconfiguration overheads in reconfigurable systems[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2014, 22(6):1248-1261.
[22] WEGENER I. Simulated annealing beats metropolis in combinatorial optimization[C]//Automata, Languages and Programming, 2005.
[23] SINGH H K, RAY T, SMITH W. C-PSA:Constrained Pareto simulated annealing for constrained multi-objective optimization[J]. Information Sciences, 2010, 180(13):2499-2513.
[24] ZHANG Z S, XING L N, CHEN Y N, et al. Evolutionary algorithms for many-objective ground station scheduling problem[C]//Bio-Inspired Computing-Theories and Applications, 2016.
[25] ZHANG T, CHEN J Y, LV D, et al. Automatic generation of reconfiguration blueprints for IMA systems using reinforcement learning[J]. IEEE Embedded Systems Letters, 2021, 99:1-4.
[26] CHUAI G, ZHAO D, SUN L. Novel adaptive simulated annealing algorithm for constrained multi-objective optimization[J]. China Communications, 2012, 9(9):68-78(in Chinese).
[27] CHENG Y, WANG H X, WENG Z Y, et al. Optimization of flow shop scheduling control strategy based on improved differential evolution algorithm[C]//2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC). Piscataway:IEEE Press, 2018:43-46.
CJA