Mitigating Latency in IoT Devices: A Machine Learning Approach to Identifying and Addressing Key Contributing Factors
  IJCTT-book-cover
 		          
 
© 2023 by IJCTT Journal
Volume-71 Issue-11
Year of Publication : 2023
Authors : Karan Gupta, Manvendra Sharma
DOI :  10.14445/22312803/IJCTT-V71I11P101

How to Cite?

Karan Gupta, Manvendra Sharma, "Mitigating Latency in IoT Devices: A Machine Learning Approach to Identifying and Addressing Key Contributing Factors," International Journal of Computer Trends and Technology, vol. 71, no. 11, pp. 1-7, 2023. Crossref, https://doi.org/10.14445/22312803/IJCTT-V71I11P101

Abstract
In the realm of Internet of Things (IoT) systems, latency emerges as a pivotal challenge, jeopardizing both performance and usability, especially in time-sensitive applications. Recognizing the urgency of addressing this challenge, this paper embarks on a comprehensive analysis of synthetic IoT sensor data [1] to discern the predominant factors inducing highlatency events. By employing a lasso regression model [2], the research unveils network availability, communication failures, elevated memory utilization, and high CPU usage as the chief culprits behind latency issues. Augmenting our approach, a random forest classification [3] was employed, which impressively yielded a precision and recall rate between 93-95% in prognosticating high-latency events. Drawing on these insights, the paper advocates for strategies encompassing enhanced connectivity, protocol optimization, additional memory/CPU headroom provision, and a holistic approach to performance management as potent solutions to curtail IoT latency.

Keywords
Internet of Things (IoT), Latency, Classification models, Network availability, Memory utilization, Communication failures.

Reference

[1] J. Chen et al., “Artificial Intelligence in the Internet of Things: Toward Fully Connected Intelligent Sensors,” IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8072-8083, 2020.
[2] Robert Tibshirani, “Regression Shrinkage and Selection via the Lasso,” Journal of the Royal Statistical Society: Series B (Methodological), vol. 58, no. 1, pp. 267-288, 1996.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Leo Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Jayavardhana Gubbi et al., “Internet of Things (IoT): A Vision, Architectural Elements, and Future Directions,” Future Generation Computer Systems, vol. 29, no. 7, pp. 1645-1660, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Charith Perera et al., “A Survey on Internet of Things from Industrial Market Perspective,” IEEE Access, vol. 2, pp. 1660-1679, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jinjiang Wang et al., “Deep Learning for Smart Manufacturing: Methods and Applications,” Journal of Manufacturing Systems, vol. 48, pp. 144-156, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[7] N.V. Chawla et al., “SMOTE: Synthetic Minority Over-Sampling Technique,” Journal of Artificial Intelligence Research, 16, pp. 321- 357, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Trevor Hastie, Jerome Friedman, and Robert Tibshirani, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer Science & Business Media, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Chao Chen, Andy Liaw, and Leo Breiman, “Using Random Forest to Learn Imbalanced Data,” University of California, Berkeley, 2004.
[Publisher Link]
[10] Brent Daniel Mittelstadt, and Luciano Floridi, “The Ethics of Big Data: Current and Foreseeable Issues in Biomedical Contexts,” Science and Engineering Ethics, vol. 22, no. 2, pp. 303-341, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Nadeem, and M.A. Pasha, “A Survey of Communication Protocols for Internet of Things and Related Challenges of Fog and Cloud Computing Integration,” ACM Computing Surveys, vol. 49, no. 1, pp. 1-37, 2016.
[12] P. Kumar, and S. Goyal, “Resource Management in IoT: Vision, Challenges, and Solutions,” International Journal of Computer Applications, vol. 134, no. 1, 2016.
[13] E.R. Tufte, The Visual Display of Quantitative Information, Graphics Press, 2001.
[14] Alessio Botta et al., “Integration of Cloud Computing and Internet of Things: a Survey,” Future Generation Computer Systems, vol. 56, pp. 684-700, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Daniele Miorandi et al., “Internet of Things: Vision, Applications and Research Challenges,” Ad Hoc Networks, vol. 10, no. 7, pp. 1497- 1516, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Gupta et al., “Investigating Network-Induced Latency in Internet of Things Systems,” Journal of Networking, vol. 2, no. 1, pp. 55-65, 2020.
[17] J. Gonzalez et al., “A Comprehensive Exploration of Latency in Internet of Things Systems,” IEEE Internet of Things Journal, vol. 5, no. 3, pp. 2135–2145, 2018.
[18] C. Liu et al., “Dissecting Latency in Wi-Fi based IoT Deployments,” Proceedings of the IEEE Conference on Wireless Communications, 2019.