A novel continual reinforcement learning-based expert system for self-optimization of soft real-time systems

被引:1
|
作者
Masood, Zafar [1 ]
Jiangbin, Zheng [1 ]
Ahmad, Idrees [1 ,2 ]
Dongdong, Chai [3 ]
Shabbir, Wasif [4 ]
Irfan, Muhammad [1 ]
机构
[1] Northwestern Polytech Univ, Sch Software, Xian, Peoples R China
[2] Int Islamic Univ Islamabad, Dept Comp Sci & Software Engn, Islamabad, Pakistan
[3] Beijing Aerosp Test Technol Res Inst, Beijing, Peoples R China
[4] Northwestern Polytech Univ, Sch Automat, Xian, Peoples R China
关键词
Self-adaptive systems; Continual learning; Autonomic computing; Reinforcement learning; Learning classifier systems;
D O I
10.1016/j.eswa.2023.122309
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Virtual globes are soft real-time systems, which stream multi-resolution data sets and render world-scale landscapes in real-time. Such systems require an adaptation mechanism to fulfill user and quality of experience (QoE) requirements. Configuration and tuning of parameters to optimize system performance is challenging due to run-time uncertainties. In this work, we propose a continual reinforcement learning-based expert system for self-optimization of a soft real-time system to meet user and quality objectives. The proposed system is capable of learning continuously by utilizing the previously learned knowledge to fulfill adaptation requirements. The proposed managing system interacts with a managed system and evolves a knowledge base of adaptation rules for run-time optimization of the managed system to meet user and quality objectives. We devise a learning classifier system for the evolution, storage, and transfer of adaptation rules using a code fragments-based rich encoding scheme. We transform user goals, system states, and execution environment conditions into observable states. We validated the proposed system for the same and cross-domain knowledge transfer and reuse scenarios for different user goals and execution environments. The results of the proposed system are compared with baseline and state-of-the-art methods where the proposed system outperformed the methods in terms of adaptation accuracy.
引用
收藏
页数:17
相关论文
共 50 条
  • [41] Self-optimization of coverage and capacity based on a fuzzy neural network with cooperative reinforcement learning
    Fan, Shaoshuai
    Tian, Hui
    Sengul, Cigdem
    EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2014,
  • [42] Self-optimization of coverage and capacity based on a fuzzy neural network with cooperative reinforcement learning
    Shaoshuai Fan
    Hui Tian
    Cigdem Sengul
    EURASIP Journal on Wireless Communications and Networking, 2014
  • [43] Deep learning-based real-time detection of novel pathogens during sequencing
    Bartoszewicz, Jakub M.
    Genske, Ulrich
    Renard, Bernhard Y.
    BRIEFINGS IN BIOINFORMATICS, 2021, 22 (06)
  • [44] Learning-based state estimation in distribution systems with limited real-time measurements
    de la Varga, J. G.
    Pineda, S.
    Morales, J. M.
    Porras, A.
    ELECTRIC POWER SYSTEMS RESEARCH, 2025, 241
  • [45] Real-time Machine Learning-Based CLBF-MPC of Nonlinear Systems
    Wu, Zhe
    Rincon, David
    Christofides, Panagiotis D.
    IFAC PAPERSONLINE, 2020, 53 (02): : 11589 - 11594
  • [46] Reinforcement Learning Based on Real-Time Iteration NMPC
    Zanon, Mario
    Kungurtsev, Vyacheslav
    Gros, Sebastien
    IFAC PAPERSONLINE, 2020, 53 (02): : 5213 - 5218
  • [47] Reinforcement Learning-Based Insulin Injection Time And Dosages Optimization
    Wang, Zihao
    Xie, Zhiqiang
    Tu, Enmei
    Zhong, Alex
    Liu, Yingying
    Ding, Jichang
    Yang, Jie
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [48] Panda: Reinforcement Learning-Based Priority Assignment for Multi-Processor Real-Time Scheduling
    Lee, Hyunsung
    Lee, Jinkyu
    Yeom, Ikjun
    Woo, Honguk
    IEEE ACCESS, 2020, 8 : 185570 - 185583
  • [49] Self-learning Fuzzy Controllers Based On a Real-time Reinforcement Genetic Algorithm
    方建安
    苗清影
    郭钊侠
    邵世煌
    Journal of DongHua University, 2002, (02) : 19 - 22
  • [50] Self-learning fuzzy controllers based on a real-time reinforcement genetic algorithm
    Fang, Jian-An
    Miao, Qing-Ying
    Guo, Zhao-Xia
    Shao, Shi-Huang
    Journal of Dong Hua University (English Edition), 2002, 19 (02): : 19 - 22