RACH Traffic Prediction in Massive Machine Type Communications

2024-05-08

IEEE Transactions on Machine Learning in Communications and Networking

AI Summary

To address the challenge of predicting event-driven, bursty RACH traffic in mMTC networks, this paper proposes a lightweight online learning framework that integrates LSTM with a residual-connected DenseNet-FFNN for real-time modeling of multi-channel slotted ALOHA access load. Key contributions include: (1) the first low-complexity online LSTM state update algorithm enabling incremental parameter optimization; (2) incorporation of residual connections to enhance representation capability for non-stationary and highly stochastic burst patterns; and (3) a balanced design achieving both high prediction accuracy and low inference latency, suitable for dynamic real-world network environments. Experimental results demonstrate a 52% improvement in long-term prediction accuracy over conventional methods, along with significantly reduced computational complexity. The framework’s timeliness and deployment feasibility are validated in a single-base-station scenario with over one thousand heterogeneous mMTC devices.

Technology Category

• Machine Learning: Online Learning & Bandits
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Traffic pattern prediction has emerged as a promising approach for efficiently managing and mitigating the impacts of event-driven bursty traffic in massive machine-type communication (mMTC) networks. However, achieving accurate predictions of bursty traffic remains a non-trivial task due to the inherent randomness of events, and these challenges intensify within live network environments. Consequently, there is a compelling imperative to design a lightweight and agile framework capable of assimilating continuously collected data from the network and accurately forecasting bursty traffic in mMTC networks. This paper addresses these challenges by presenting a machine learning-based framework tailored for forecasting bursty traffic in multi-channel slotted ALOHA networks. The proposed machine learning network comprises long-term short-term memory (LSTM) and a DenseNet with feed-forward neural network (FFNN) layers, where the residual connections enhance the training ability of the machine learning network in capturing complicated patterns. Furthermore, we develop a new low-complexity online prediction algorithm that updates the states of the LSTM network by leveraging frequently collected data from the mMTC network. Simulation results and complexity analysis demonstrate the superiority of our proposed algorithm in terms of both accuracy and complexity, making it well-suited for time-critical live scenarios. We evaluate the performance of the proposed framework in a network with a single base station and thousands of devices organized into groups with distinct traffic-generating characteristics. Comprehensive evaluations and simulations indicate that our proposed machine learning approach achieves a remarkable 52% higher accuracy in long-term predictions compared to traditional methods, without imposing additional processing load on the system.

Problem

• Predict bursty traffic in mMTC networks accurately
• Design lightweight framework for live network data
• Enhance long-term prediction accuracy with low complexity

Innovation

• LSTM and DenseNet with FFNN for traffic prediction
• Low-complexity online algorithm for live network updates
• Residual connections enhance complex pattern capture