Abstract
The problem at hand is to effectively monitor air quality, which requires the computation of sensor data from multiple dimensions and locations. Previous approaches to this problem have utilized centralized machine learning techniques to address it. For edge devices with limited resources, these are frequently inappropriate. This paper deals with this issue by developing a brand-new hybrid deep-learning method for hourly PM2.5 pollutant prediction. The proposed method optimizes the resulting model for edge devices and assesses model performance regarding accuracy and latency on edge devices. Next, we suggest a time-optimized, multi-task offloading model based on the ideas of Optimal Stopping Theory (OST), to increase the likelihood of offloading to the best servers. We offer another OST-based strategy to reduce the overall offloading latency when the server use is nearly distributed uniformly. To forecast hourly PM2.5 concentration, this work uses a deep learning model, Multi-factor Long Short-Term Memory (LSTM), and Deep Reinforcement Learning (DRL). The analysis of the findings using RMSE and MAE errors demonstrates that our suggested model beats other deep learning models. The edge device received 8272 hourly samples, and the RPi4B executed the model twice as quickly as the RPi3B + in all quantization modes. The least time was required for full-integer quantization, which resulted in latencies of 2.19 and 4.73 s for the RPi4B and RPi3B + , correspondingly.
Similar content being viewed by others
Data availability
The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Wardana, I NyomanKusama., Gardner, Julian W., Fahmy, Suhaib A.: Optimising deep learning at the edge for accurate hourly air quality prediction. Sensors 21(4), 1064 (2021)
Mu, Liting, et al.: Multi-Task Offloading Based on Optimal Stopping Theory in Edge Computing Empowered Internet of Vehicles. Entropy 24(6), 814 (2022)
Alkabbani, Hanin, et al.: An improved air quality index machine learning-based forecasting with multivariate data imputation approach. Atmosphere 13(7), 1144 (2022)
Chen, H., Guan, M., Li, H.: Air quality prediction based on integrated dual LSTM model. IEEE Access 9, 93285–93297 (2021)
Islam, N., Saikia, B.K.: Atmospheric particulate matter and potentially hazardous compounds around residential/road side soil in an urban area. Chemosphere 259, 127453 (2020)
Daiber, A., Kuntic, M., Hahad, O., Delogu, L.G., Rohrbach, S., Lisa, F.D., Schulz, R., Münzel, T.: Effects of air pollution particles (ultrafine and fine particulate matter) on mitochondrial function and oxidative stress – Implications for cardiovascular and neurodegenerative diseases. Arch. Biochem. Biophys 696, 108662 (2020)
Castelli, M., Clemente, F.M., Popoviˇc, A., Silva, S., Vanneschi, L.: A Machine Learning Approach to Predict Air Quality in California. Complexity 2020, 8049504 (2020)
Navares, R., Aznarte, J.L.: Predicting air quality with deep learning LSTM: Towards comprehensive models. Ecol. Inform 55, 101019 (2020)
Xayasouk, T., Lee, H., Lee, G.: Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models. Sustainability 12, 2570 (2020)
Seng, D., Zhang, Q., Zhang, X., Chen, G., Chen, X.: Spatiotemporal prediction of air quality based on LSTM neural network. Alex. Eng. J 60, 2021–2032 (2021)
Xu, J.; Chen, L.; Lv, M.; Zhan, C.; Chen, S.; Chang, J. HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method, arXiv:2101.04264 (2021)
Ma, J., Ding, Y., Cheng, J.C., Jiang, F., Wan, Z.: A temporal-spatial interpolation and extrapolation method based on geographic Long Short-Term Memory neural network for PM2.5. J. Clean. Prod 237, 117729 (2019)
Bai, Y., Zeng, B., Li, C., Zhang, J.: An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting. Chemosphere 222, 286–294 (2019)
Zhao, J., Deng, F., Cai, Y., Chen, J.: Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. Chemosphere 220, 486–492 (2019)
Qin, D., Yu, J., Zou, G., Yong, R., Zhao, Q., Zhang, B.: A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration. IEEE Access 7, 20050–20059 (2019)
Qi, Y., Li, Q., Karimian, H., Liu, D.: A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory. Sci. Total Environ. 664, 1–10 (2019)
Zhang, Q.; Lam, J.C.; Li, V.O.; Han, Y. Deep-AIR: A Hybrid CNN-LSTM Framework forFine-Grained Air Pollution Forecast, arXiv:2001.11957 (2020)
Li, T., Hua, M., Wu, X.: A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5). IEEE Access 8, 26933–26940 (2020)
Tao, Q., Liu, F., Li, Y., Sidorov, D.: Air Pollution Forecasting Using a Deep Learning Model Based on 1D Convnets and Bidirectional GRU. IEEE Access 7, 76690–76698 (2019)
Chen, H.C.; Putra, K.T.; Chun-WeiLin, J. A Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks, arXiv:2101.06213 (2021)
Banner, R.; Nahshan, Y.; Soudry, D: Post training 4-bit quantization of convolutional networks for rapid-deployment. In Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada, 8–14 December; Volume 32, pp. 7950–7958 (2019)
Zhang, X., Wen, S., Yan, L., Feng, J., & Xia, Y: A Hybrid-Convolution Spatial–Temporal Recurrent Network For Traffic Flow Prediction. Comput. J. c171 (2022)
Wang, H., Cui, Z., Liu, R., Fang, L., & Sha, Y: A Multi-type Transferable Method for Missing Link Prediction in Heterogeneous Social Networks. IEEE Transactions on Knowledge and Data Engineering (2023)
Yin, L., Wang, L., Tian, J., Yin, Z., Liu, M., … Zheng, W: Atmospheric Density Inversion Based on Swarm-C Satellite Accelerometer. Appl. Sci. 13(6) (2023)
Liu, Y., Tian, J., Zheng, W., Yin, L.: Spatial and temporal distribution characteristics of haze and pollution particles in China based on spatial statistics. Urban climate 41, 101031 (2022)
Tian, J., Liu, Y., Zheng, W., & Yin, L: Smog prediction based on the deep belief - BP neural network model (DBN-BP). Urban Clim. (2021)
Wang, S., Sheng, H., Zhang, Y., Yang, D., Shen, J., … Chen, R. Blockchain-Empowered Distributed Multi-Camera Multi-Target Tracking in Edge Computing. IEEE Transact. Industr. Inform. (2023)
Wu, H.; Judd, P.; Zhang, X.; Isaev, M.; Micikevicius, P: Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation, arXiv:2004.09602 (2020)
Peng, P., You, M., Xu, W., Li, J.: Fully integer-based quantization for mobile convolutional neural network inference. Neurocomputing 432, 194–205 (2021)
Li, J., Alvarez, R: On the quantization of recurrent neural networks, arXiv:2101.05453 (2021)
Benhaddi, M., Ouarzazi, J.: ‘Multivariate time series forecasting with dilated residual convolutional neural networks for urban air quality prediction.’ Arabian J. Sci. Eng. 46(4), 3423–3442 (2021)
X. Song, J. Huang, and D. Song: ‘‘Air quality prediction based on LSTM-Kalman model,’’ in Proc. IEEE 8th Joint Int. Inf. Technol. Artif. Intell. Conf. (ITAIC), Chongqing, China, May, pp. 695–699 (2019)
Wang, J., Li, J., Wang, X., Wang, J., Huang, M.: ‘Air quality prediction using CT-LSTM.’ Neural Comput. Appl. 33(3), 1–14 (2020)
Jianhui, Z., Ting, D., Bo, C.: ‘AQI prediction based on long short- term memory model with spatio-temporal optimizations and fireworks algorithm.’ J. Wuhan Univ. 65(3), 250–262 (2019)
Qin, D., Yu, J., Zou, G., Yong, R., Zhao, Q., Zhang, B.: ‘A novel combined prediction scheme based on CNN and LSTM for urban PM2.5 concentration.’ IEEE Access 7, 20050–20059 (2019)
Li, S., Xie, G., Ren, J., Guo, L., Yang, Y., Xu, X.: ‘Urban PM2.5 concentration prediction via attention-based CNN–LSTM.’ Appl. Sci. 10(6), 1953 (2020)
Zhang, L., Liu, P., Zhao, L., Wang, G., Zhang, W., Liu, J.: ‘Air quality predictions with a semi-supervised bidirectional LSTM neural network.’ Atmos. Pollut. Res. 12(1), 328–339 (2021)
Belavadi, S.V., Rajagopal, S., Ranjani, R., Mohan, R.: Air quality forecasting using LSTM RNN and wireless sensor networks. Procedia Comput. Sci. 170, 241–248 (2020)
X. Sun, W. Xu, H. Jiang: Spatio-temporal prediction of air quality based on recurrent neural networks. in Proc. 52nd Hawaii Int. Conf. Syst. Sci. (HICSS) (2019)
Zou, X., Zhao, J., Zhao, D., Sun, B., He, Y., Fuentes, S.: ‘Air quality prediction based on a spatiotemporal attention mechanism.’ Mobile Inf. Syst. 2021, 1–12 (2021)
Qin, Z., Cen, C., Guo, X.: ‘Prediction of air quality based on KNN- LSTM.’ J. Phys. Conf. 1237(Jun), 042030 (2019)
Zhao, J., Deng, F., Cai, Y., Chen, J.: ‘Long short-term memory—Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction.’ Chemosphere 220, 486–492 (2019)
Meisami, S., Beheshti-Atashgah, M., Aref, M.R.: “Using blockchain to achieve decentralized privacy in IoT healthcare” arXiv preprint arXiv:2109.14812 (2021)
Bozorgkhou, H., Rokni, M.A.: Studying and investigating the impact of marketing mix factors on e-purchase via smart phones (case study: Digikala corporation). Nexo Revista Científica 35(04), 992–1003 (2022)
Abedi, M., Tan, X., Klausner, J.F., Murillo, M.S. and Benard, A.: A Comparison of the Performance of a Data-Driven Surrogate Model of a Dehumidifier with Mathematical Model of Humidification-Dehumidification System. In AIAA SCITECH 2023 Forum (p. 2329) (2023)
Wang, X., Wang, Y., Javaheri, Z., Almutairi, L., Moghadamnejad, N., Younes, O.S.: Federated deep learning for anomaly detection in the internet of things. Comput. Electr. Eng. 108, 108651 (2023)
Chiniforooshan Esfahani, I.: A data-driven physics-informed neural network for predicting the viscosity of nanofluids. AIP Adv. 13(2), 025206 (2023)
Dai, X., Xiao, Z., Jiang, H., Alazab, M., Lui, J. C. S., Dustdar, S.,... Liu, J, Task Co-Offloading for D2D-Assisted Mobile Edge Computing in Industrial Internet of Things. IEEE Transact. Industr. Inform. 19(1), 480–490 (2023)
Jiang, H., Dai, X., Xiao, Z., Iyengar, A. K.: Joint Task Offloading and Resource Allocation for Energy-Constrained Mobile Edge Computing. IEEE Transactions on Mobile Computing (2022)
Dai, X., Xiao, Z., Jiang, H., Lui, J. C. S: UAV-Assisted Task Offloading in Vehicular Edge Computing Networks. IEEE Transactions on Mobile Computing (2023)
Ren, Y., Jiang, H., Ji, N., Yu, H.: TBSM: A traffic burst-sensitive model for short-term prediction under special events. Knowl.-Based Syst. 240, 108120 (2022)
Liu, H., Yuan, H., Hou, J., Hamzaoui, R., Gao, W.: PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling. IEEE Transact Image Process 31, 7389–740 (2022)
Huang, C., Jiang, F., Huang, Q., Wang, X., Han, Z., … Huang, W, Dual-Graph Attention Convolution Network for 3-D Point Cloud Classification. IEEE Transactions on Neural Networks and Learning Systems, 1–13 (2022)
Ni, Q., Guo, J., Wu, W., Wang, H., Wu, J.: Continuous Influence-Based Community Partition for Social Networks. IEEE Transact Network Sci Eng 9(3), 1187–1197 (2022)
Xiong, Z., Li, X., Zhang, X., Deng, M., Xu, F., Zhou, B., … Zeng, M, A Comprehensive Confirmation-based Selfish Node Detection Algorithm for Socially Aware Networks. J Signal Process Syst (2023)
Lv, Z., Yu, Z., Xie, S., & Alamri, A.: Deep Learning-Based Smart Predictive Evaluation for Interactive Multimedia-Enabled Smart Healthcare. ACM Trans. Multimedia Comput. Commun. Appl. 18(1s) (2022)
Liu, Z., Feng, J., Uden, L.: From technology opportunities to ideas generation via cross-cutting patent analysis: Application of generative topographic mapping and link prediction. Technol. Forecast. Soc. Chang. 192, 122565 (2023)
Wang, H., Cui, Z., Liu, R., Fang, L., & Sha, Y, A Multi-type Transferable Method for Missing Link Prediction in Heterogeneous Social Networks. IEEE Transact. Knowledge Data Eng (2023)
Singh, R., Gill, S.: S, Edge AI: A survey. Internet Things Cyber-Phys Syst 3, 71–92 (2023)
Acknowledgements
For Samia Elattar, Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2023R163), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia. Besides, Badr S. Alotaibi is thankful to the Deanship of Scientific Research at Najran University for funding this work, under the Research Groups Funding program grant code (NU/RG/SERC/12/1).
Funding
This research received no specific grant from any funding agency.
Author information
Authors and Affiliations
Contributions
Changyuan Sun: Conceptualization, Methodology, Formal analysis, Supervision, Writing—original draft, Writing—review & editing.
Jingjing Li: Writing—original draft, Writing—review & editing.
Riza Sulaiman: Investigation, Data Curation, Validation, Resources, Writing—review & editing.
Badr S Alotaibi: Project administration, Investigation, Writing—review & editing.
Samia Elattar: Software, Visualization, Writing—original draft.
Mohammed Abuhussain: Software, Visualization, Writing—original draft.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, C., Li, J., Sulaiman, R. et al. Air Quality Prediction and Multi-Task Offloading based on Deep Learning Methods in Edge Computing. J Grid Computing 21, 32 (2023). https://doi.org/10.1007/s10723-023-09671-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10723-023-09671-0