EdgeMeld: An Adaptive Machine Learning Framework for Real-Time Anomaly Detection and Optimization in Industrial IoT Networks

Main Article Content

K. Lakshmi
Garlapadu Jayanthi
Jallu Hima Bindu


The integration of the Internet of Things (IoT) in industrial settings has revolutionized real-time monitoring and control systems but also presents challenges such as effective anomaly detection and network efficiency. The EdgeMeld framework, developed to address these challenges, utilizes adaptive machine learning techniques to enhance anomaly detection and system responsiveness. The objective of this research is to provide a robust solution for real-time anomaly detection in industrial IoT systems, overcoming issues like data congestion, latency, and security vulnerabilities. EdgeMeld's methodology involves a novel hybrid machine learning model that combines deep learning and ensemble learning techniques, implemented within a distributed edge computing architecture to minimize latency and maximize efficiency. The framework operates across three layers—Perception, Network, and Application—each integral to processing and securing data. This study utilizes a synthetic dataset of 1,000 records, simulating typical industrial IoT network environments, to validate the framework's effectiveness. Quantitative analysis shows significant improvements, with EdgeMeld achieving higher accuracy and reduced false positives in anomaly detection compared to existing systems. Furthermore, EdgeMeld's adaptive capabilities allow it to continuously learn and evolve in response to new data, enhancing its applicability and scalability across diverse industrial settings. This research demonstrates that EdgeMeld significantly advances the operational integrity and efficiency of industrial IoT networks, suggesting a scalable, adaptive, and secure approach to managing complex IoT systems.

Article Details

How to Cite
K. Lakshmi, Garlapadu Jayanthi, and Jallu Hima Bindu, “EdgeMeld: An Adaptive Machine Learning Framework for Real-Time Anomaly Detection and Optimization in Industrial IoT Networks”, Int. J. Comput. Eng. Res. Trends, vol. 11, no. 4, pp. 20–31, Apr. 2024.
Research Articles


Misra, S., Roy, C., Sauter, T., Mukherjee, A., & Maiti, J. (2022). Industrial Internet of Things for safety management applications: A survey. IEEE Access, 10, 83415-83439.

Sharma, M., Tomar, A., & Hazra, A. (2024). Edge Computing for Industry 5.0: Fundamental, Applications and Research Challenges. IEEE Internet of Things Journal.

Jaramillo-Alcazar, A., Govea, J., & Villegas-Ch, W. (2023). Anomaly Detection in a Smart Industrial Machinery Plant Using IoT and Machine Learning. Sensors, 23(19), 8286.

George, A. S. (2024). The Role of Fog Computing in Enabling Real-Time IoT Applications. Partners Universal International Innovation Journal, 2(2), 39-54.

Hernandez, L., Garcia, D., & Jurado, F. (2021). Challenges in IoT interoperability: current state and future perspectives. Journal of Network and Computer Applications, 173, 102873.

Kumar, S., & Patel, N. R. (2019). Addressing real-time data processing challenges in IoT-based smart environments. Journal of Real-Time Systems, 55(3), 412-442.

Zhou, M., Wang, H., & Zhang, Y. (2020). IoT framework designs and applications: A review. IEEE Internet of Things Journal, 7(9), 8532-8549.

Lee, J., Kim, Y., & Kang, M. (2019). Machine learning for smart industry: Harnessing data with artificial intelligence. IEEE Transactions on Industrial Informatics, 15(7), 3855-3862.

Singh, D., & Singh, B. (2020). Optimizing IoT networks using deep learning approaches. Journal of Network and Systems Management, 28(4), 882-915.

Zhao, Y., Li, X., & Rahmani, R. (2021). Resource optimization in IoT networks using reinforcement learning. IEEE Access, 9, 76920-76934.

Fernandez, E., & Lopez, P. (2020). The evolution of security in IoT networks. Network Security, 2020(6), 12-15.

Patel, S., & Wang, J. (2021). Challenges in adapting static machine learning models to dynamic IoT environments. Journal of Computer and System Sciences, 119, 79-94.

Smith, J., & Thomas, K. (2022). Real-time data processing in IoT: Opportunities and constraints. Journal of Parallel and Distributed Computing, 154, 65-78.

Lu, J., Tan, L., & Jiang, H. (2021). Review on convolutional neural network (CNN) applied to plant leaf disease classification. Agriculture, 11(8), 707.

Ryan, S. (2021). A Sequence to Image Transformation Technique for Anomaly Detection in Drifting Data Streams: Detection, Segmentation and Generative Models on Multiple Objects (Doctoral dissertation, Université d'Ottawa/University of Ottawa).

Louk, M. H. L., & Tama, B. A. (2023). Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system. Expert Systems with Applications, 213, 119030.