No abstract

Learning-based energy-efficient resource management by heterogeneous RF/VLC for ultra-reliable low-latency industrial IoT networks

No abstract

No abstract

No abstract

No abstract

Indoor location-based services are becoming crucial parts of smart living, smart manufacturing, and all kinds of the Internet of Things. Visible light-based positioning (VLP) system is one of the costefficient and RF radiation-free solutions. However, conventional received signal strength (RSS)-based VLP system suffers inaccurate modeling and intensity variations, especially in 3-D positioning cases. Hence, we propose an artificial neural network (ANN)-based approach for accurate modeling and positioning with on-site data. Likewise, the proposed approach is also proved applicable to accurate modeling of initial time delay distribution of LED chips in VLP systems based on phase differences of arrival (PDOA). To improve the robustness by mitigating the impact of intensity variations, we introduce a selection strategy utilizing both PDOA and RSS measurements. Through simulations, we demonstrate the feasibility of ANN-based onsite modeling and present the robustness of the hybrid positioning system under various levels of intensity variations.INDEX TERMS ANN, pre-training, PDOA, RSS, VLP.

In this paper, a 3D indoor visible light positioning (VLP) system with fast computation time using received signal strength (RSS) is proposed and experimentally demonstrated. Assisted by the deep learning techniques, the complexity of the trilateration problem is greatly reduced, and the trilateration problem can be formulated as a linear mapping leading to faster position estimation than the conventional estimation. Moreover, a new method of off-line preparation is adopted to minimize the workload of the VLP system deployment for more practical usage. The proposition is implemented on an atto-cellular VLP unit, through which the real-time performance and positioning accuracy are demonstrated and validated in a 3D positioning experiment performed in a space of 1.2 × 1.2 × 2 m 3 . The experimental results show that a positioning accuracy of 11.93 cm in confidence of 90% is achieved with 50 times faster the computation time compared to the conventional scheme. INDEX TERMSVisible light communication (VLC), visible light positioning (VLP), received signal strength (RSS), light-emitting diodes (LED), deep learning.