Deep-Reinforcement-Learning-Based Energy-Efficient Resource Management for Social and Cognitive Internet of Things

Abstract

Internet of things (IoT) has attracted much interest due to its wide applications such as smart city, manufacturing, transportation, and healthcare. Social and cognitive IoT is capable of exploiting the social networking characteristics to optimize the network performance. Considering the fact that IoT devices have different quality of service (QoS) requirements (ranging from ultra-reliable and low-latency communications (URLLC) to minimum data rate), this paper presents a QoS-driven socialaware enhanced device-to-device (D2D) communication network model for social and cognitive IoT by utilizing social orientation information. We model the optimization problem as a multi-agent reinforcement learning formulation, and a novel coordinated multi-agent deep reinforcement learning based resource management approach is proposed to optimize the joint radio block assignment and transmission power control strategy. Meanwhile, prioritized experience replay (PER) and coordinated learning mechanisms are employed to enable communication links to work cooperatively in a distributed manner, which enhances the network performance and access success probability. Simulation results corroborate the superiority in the performance of the presented resource management approach, and it outperforms other existing approaches in terms of meeting the energy efficiency and the QoS requirements.

Data Transmission and Processing Analysis of Power Economic Management Terminal Based on the Internet of Things

“…Yang et al put forward a 14-point action plan on the Internet of Things industry, and Japan put forward the "u-japan plan" on the Internet of Things. These global government plans regard the Internet of Things as one of the primary strategic objectives of the current national economic construction and scientific and technological development [10].…”

The Applicability of Reinforcement Learning Methods in the Development of Industry 4.0 Applications

“…However, network resources may be over-consumed during the training and data transmission process. To solve the complex and dynamic control issues, a federated deep reinforcement learning-based [101,107,108,118,123,133,134,136,144,145,154,159,161,165,167,168,171], [174-177, 179, 183, 188, 192, 198, 200], [204,208,210,213,216,221,222,[225][226][227] [177-179, 181, 187, 188, 190, 196, 197, 200, 201, 203, 206, 207, 211, 214, 218, 223], [234,236,239,243,245,248,252,254,258,275,[277][278][279], [284, 286-292, 294, 297, 300], [305,306, Wireless, radio, antenna, signal [14,18,28…”

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence

“…To abstract, allocate, and optimize resources, the joint resource orchestration strategy is learned by the double dueling DQN algorithm with the aid of the SDN controller and NFV. Similar to the multihidden-layer neural network design in [20], [174] for URLLC-enabled IoT applications, an advanced multilayer convolutional neural network is proposed to improve the learning efficiency. Owing to the dynamic crowd in various sectors of smart cities, the double DQN-based smart routing algorithm was devised to reduce network congestion and balance the network workload in [169].…”