K-Means-Enhanced LSTM for Dynamic Radio Resource Optimization in Industrial IoT Networks

Author(s)	Ajit Kumar Tiwari, Sunil Patil
Country	India
Abstract	The efficient management of radio resources in industrial internet of things (IIoT) networks is highly demanding to handle dynamic conditions of channels and variations in patterns of data traffic. This research proposes a novel K-Means-enhanced long short-term memory (LSTM) framework for dynamic radio resource management in IIoT networks. The proposed approach trains the cluster-specific LSTM models to predict future network states, by applying k-means clustering to integrate IoT devices based on previously acquired existing features such as data arrival rates and channel gains. These predictions inform a convex optimization solver to allocate transmit power and bandwidth, which maximizes the sum rate of the network while adhering to the resource constraints. The simulation results demonstrate that the proposed method achieves up to 20% higher throughput and 50% lower prediction errors compared to the standalone LSTM and static allocation. The proposed hybrid approach effectively addresses the device heterogeneity and the temporal dynamics, which ultimately offers a scalable solution to the IIoT communication systems.
Keywords	Industrial Internet of Things (IIoT), Radio Resource Management, K-Means Clustering, Long Short-Term Memory (LSTM), Dynamic Optimization, Network Throughput
Field	Computer Applications
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-03-31

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research