计算机科学
概率逻辑
异步通信
人工神经网络
马尔可夫链
马尔可夫过程
可靠性(半导体)
电信网络
实时计算
人工智能
计算机网络
机器学习
物理
数学
功率(物理)
统计
量子力学
作者
Na Liu,Wenjie Qin,Jun Cheng,Jinde Cao,Dan Zhang
标识
DOI:10.1016/j.neunet.2024.106556
摘要
This paper addresses the asynchronous control problem for semi-Markov reaction-diffusion neural networks (SMRDNNs) under probabilistic event-triggered protocol (PETP) scheduling. A semi-Markov process with a deterministic switching rule is introduced to characterize the stochastic behavior of these networks, effectively mitigating the impacts of arbitrary switching. Leveraging statistical data on communication-induced delays, a novel PETP is proposed that adjusts transmission frequencies through a probabilistic delay division method. The dynamic adjustment of event trigger conditions based on real-time neural network is realized, and the responsiveness of the system is enhanced, which is of great significance for improving the performance and reliability of the communication system. Additionally, a dynamic asynchronous model is introduced that more accurately captures the variations between system modes and controller modes in the network environment. Ultimately, the efficacy and superiority of the developed strategies are validated through a simulation example.
科研通智能强力驱动
Strongly Powered by AbleSci AI