Article: Design of smart city environment monitoring and optimisation system based on NB-IoT technology Journal: International Journal of Information and Communication Technology (IJICT) 2024 Vol.25 No.10 pp.47 - 61 Abstract: To address the issues of high network latency and large prediction error in urban environment monitoring methods, this article offers a design approach for smart urban environment monitoring and optimisation system. Firstly, the system architecture was designed to deploy the communication network using NB-IOT technology, and the edge server was utilised to perform edge computation on the trace elements of the environment as a way to obtain new locations. Then the optimal weighting algorithm is applied for optimal solution fusion, and the fused measurements are the best monitoring data. Finally, the monitoring data are input into the BP neural network improved by particle swarm optimisation (PSO) method for environmental risk prediction. Experiments indicate that the proposed method reduces the network delay by 2.86 s-13.18 s and the prediction error by 0.0236-0.0777, which not only performs real-time environmental monitoring but also maintains a low prediction error. Inderscience Publishers - linking academia, business and industry through research

Title: Design of smart city environment monitoring and optimisation system based on NB-IoT technology

Authors: Linna Wang; Hongxue Yang

Addresses: Beijing Polytechnic, Beijing 100176, China ' Beijing Polytechnic, Beijing 100176, China

Abstract: To address the issues of high network latency and large prediction error in urban environment monitoring methods, this article offers a design approach for smart urban environment monitoring and optimisation system. Firstly, the system architecture was designed to deploy the communication network using NB-IOT technology, and the edge server was utilised to perform edge computation on the trace elements of the environment as a way to obtain new locations. Then the optimal weighting algorithm is applied for optimal solution fusion, and the fused measurements are the best monitoring data. Finally, the monitoring data are input into the BP neural network improved by particle swarm optimisation (PSO) method for environmental risk prediction. Experiments indicate that the proposed method reduces the network delay by 2.86 s-13.18 s and the prediction error by 0.0236-0.0777, which not only performs real-time environmental monitoring but also maintains a low prediction error.

Keywords: environmental monitoring; NB-IOT technology; optimal weighting; particle swarm optimisation algorithm; PSO; BP neural network.

DOI: 10.1504/IJICT.2024.143334

International Journal of Information and Communication Technology, 2024 Vol.25 No.10, pp.47 - 61

Received: 27 Sep 2024
Accepted: 12 Oct 2024
Published online: 13 Dec 2024 *

Title: Design of smart city environment monitoring and optimisation system based on NB-IoT technology

Keep up-to-date