期刊
IEEE ACCESS
卷 10, 期 -, 页码 50023-50036出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3168549
关键词
Signal to noise ratio; Throughput; Power demand; Delays; Real-time systems; Internet of Things; Ultra reliable low latency communication; Artificial intelligence; Cognitive Internet of Things; transmission delay; packet error rate
资金
- Universiti Tun Hussein Onn Malaysia [E15216]
- University of Tabuk, Saudi Arabia [S-0237-1438]
- Deanship of Scientific Research at Taif University, Saudi Arabia, through Taif University Researchers Supporting Project [TURSP-2020/265]
- European Union's Horizon 2020 Research and Innovation Program under the Marie Skodowska-Curie [847577]
- Science Foundation Ireland (SFI) through thr Ireland's European Structural and Investment Funds Programs
- European Regional Development Fund (2014-2020) [16/RC/3918]
The convergence of Artificial Intelligence plays a significant role in the Cognitive Internet of Things, improving throughput and transmission rates while reducing energy consumption and transmission delays.
The convergence of Artificial Intelligence (AI) can overcome the complexity of network defects and support a sustainable and green system. AI has been used in the Cognitive Internet of Things (CIoT), improving a large volume of data, minimizing energy consumption, managing traffic, and storing data. However, improving smart packet transmission scheduling (TS) in CIoT is dependent on choosing an optimum channel with a minimum estimated Packet Error Rate (PER), packet delays caused by channel errors, and the subsequent retransmissions. Therefore, we propose a Generative Adversarial Network and Deep Distribution Q Network (GAN-DDQN) to enhance smart packet TS by reducing the distance between the estimated and target action-value particles. Furthermore, GAN-DDQN training based on reward clipping is used to evaluate the value of each action for certain states to avoid large variations in the target action value. The simulation results show that the proposed GAN-DDQN increases throughput and transmission packet while reducing power consumption and Transmission Delay (TD) when compared to fuzzy Radial Basis Function (fuzzy-RBF) and Distributional Q-Network (DQN). Furthermore, GAN-DDQN provides a high rate of 38 Mbps, compared to actor-critic fuzzy-RBF's rate of 30 Mbps and the DQN algorithm's rate of 19 Mbps.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据