30 September 2022 in Future Generation Computer Systems
7 July 2023 in IEEE Internet of Things Journal
With the recent explosive growth of the Internet of Things (IoT), edge computing is emerging as a modern computing paradigm that coexists with the cloud to process massive amounts of data particularly distributed at the edge network. Meanwhile, edge computing directly permits the use of artificial intelligent (AI) models at the edge. Currently in numerous IoT applications, a tremendous amount of data is being measured and transmitted from IoT sensors to monitor surrounding information in real-time. Considering that continuous transmission of sensed data substantially requires high energy consumption of IoT sensors, this paper proposes a PPO-based autonomous transmission period control (PPO-ATPC) system in IoT edge computing that can automatically and adaptively control the transmission period of each IoT sensor. Here, the design of state, action, and reward is shaped in an unprecedented way and furthermore, a proximal policy optimization (PPO), which is one of the most effective model-free deep reinforcement learning (DRL) algorithms, is fully leveraged to achieve an optimal or nearly-optimal policy that can significantly shorten the data volume while maintaining high data quality. The merits of the proposed PPO-ATPC are extensively validated through quantitative comparison with other alternative approaches using three different sensor data collected from real-time environmental monitoring, and in-depth insights into the effectiveness of PPO-ATPC are further provided from diverse perspectives. The performance results show that total data volume for each dataset could be reduced by 73.849%, 89.931%, and 81.310%, with the average RMSE of 0.322, 13.896, and 0.048.
27 September 2023 in Future Generation Computer Systems
10 August 2025 in Future Generation Computer Systems
8 May 2026 in Information Sciences
6 October 2025 in IEEE Transactions on Network Science and Engineering
Group Paging (GP) is essential for scalable device wake-up in Fifth-Generation (5G) Internet of Things (IoT) networks. However, grouping devices with heterogeneous traffic characteristics can lead to energy inefficiency and degraded access reliability. This paper presents Deep Learning-based Group Paging (DL-GP), a unified Deep Learning (DL) framework that learns energy-optimal group assignments while satisfying Quality of Service (QoS) constraints. We formulate GP as an energy-aware optimization problem and solve it using a differentiable model that integrates: (i) a Sinkhorn layer to approximate discrete group labels, (ii) a Log-Sum-Exponential (LSE) surrogate to stably optimize Transmission Frequency (TF) and Discontinuous Reception (DRX) cycles, and (iii) an adaptive retransmission controller to enforce Access Success Rate (ASR) requirements. Trained on synthetic and LoRaWAN traces, DL-GP reduces average device energy consumption by 35% and 17% compared to Greedy and Genetic baselines in large-scale simulations, and by 66% and 64% in a real LoRaWAN deployment, respectively. It maintains low Paging Overhead (PO), satisfies ASR requirements, and achieves sub-millisecond processing latency. These results demonstrate that DL-GP is a practical real-time solution for energy-efficient and QoS-compliant paging in large-scale 5G IoT systems.