Edge Computing-Enabled Secure Forecasting Nationwide Industry PM2.5 with LLM in the Heterogeneous Network
Open Access
- 30 June 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (13) , 2581
Abstract
The heterogeneous network formed by the deployment and interconnection of various network devices (e.g., sensors) has attracted widespread attention. forecasting on the entire industrial region throughout mainland China is an important application of heterogeneous networks, which has great significance to factory management and human health travel. In recent times, Large Language Models (LLMs) have exhibited notability in terms of time series prediction. However, existing LLMs tend to forecast nationwide industry , which encounters two issues. First, most LLM-based models use centralized training, which requires uploading large amounts of data from sensors to a central cloud. This entire transmission process can lead to security risks of data leakage. Second, LLMs fail to extract spatiotemporal correlations in the nationwide sensor network (heterogeneous network). To tackle these issues, we present a novel framework entitled Spatio-Temporal Large Language Model with Edge Computing Servers (STLLM-ECS) to securely predict nationwide industry in China. In particular, We initially partition the entire sensor network, located in the national industrial region, into several subgraphs. Each subgraph is allocated an edge computing server (ECS) for training and inference, avoiding the security risks caused by data transmission. Additionally, a novel LLM-based approach named Spatio-Temporal Large Language Model (STLLM) is developed to extract spatiotemporal correlations and infer prediction sequences. Experimental results prove the effectiveness of our proposed model.
Keywords
Funding Information
- Research on Distribution Room Condition Sensing Early Warning and Distribution Cable Operation and Inspection Smart Decision-Making Technology (524609220092)
This publication has 29 references indexed in Scilit:
- When Moving Target Defense Meets Attack Prediction in Digital Twins: A Convolutional and Hierarchical Reinforcement Learning ApproachIEEE Journal on Selected Areas in Communications, 2023
- Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer modelScience of The Total Environment, 2022
- Deep learning for air pollutant concentration prediction: A reviewAtmospheric Environment, 2022
- Time Series Analysis and Forecasting of Air Pollution Particulate Matter (PM2.5): An SARIMA and Factor Analysis ApproachIEEE Access, 2021
- A PM2.5 concentration prediction model based on multi-task deep learning for intensive air quality monitoring stationsJournal of Cleaner Production, 2020
- A Wireless Sensor Network for Monitoring Environmental Quality in the Manufacturing IndustryIEEE Access, 2019
- HazeEst: Machine Learning Based Metropolitan Air Pollution Estimation From Fixed and Mobile SensorsIEEE Sensors Journal, 2017
- The Promise of Edge ComputingComputer, 2016
- Application of Gaussian plume models for air pollution simulation at instantaneous emissionsMathematics and Computers in Simulation, 2004
- A faster algorithm for betweenness centrality*The Journal of Mathematical Sociology, 2001