Priority-Aware EP-ALOHA and Predictive Radio Resource Allocation for Heterogeneous M2M Devices in 5G Networks

This paper proposes a priority-aware EP-ALOHA framework with predictive radio resource allocation for heterogeneous machine-to-machine (M2M) devices in 5G massive machine-type communication (mMTC) networks. The proposed framework extends conventional EP-ALOHA by introducing M2M priority classes, priority-dependent delay constraints, and Exploration Phase resource block (RB) allocation. The RB-allocation problem is formulated as an integer-constrained optimization problem, where the objective is to improve effective radio channel utilization while satisfying delay constraints for different priority classes. A Genetic Algorithm-based optimization procedure is used to generate optimization-derived RB-allocation targets under different traffic and system parameter settings. These targets are then used to train and evaluate predictive RB-allocation models, including Random Forest, Neural Network, Gradient Boosting, and Linear Regression. The simulation results show that the proposed priority-aware EP-ALOHA method achieves a higher successful access probability than the considered baseline schemes within the feasible operating region. For predictive RB allocation, the Neural Network achieved the best test-set performance, with MSE = 25.5002, RMSE = 5.0498 RBs, MAE = 3.2629 RBs, and R2 = 0.9810. A separate computational evaluation showed that Random Forest inference reduced the mean allocation-decision time from 213.54 ms for GA-based optimization to 15.20 ms, corresponding to a 14.05-fold speed-up on the evaluated platform. In addition, M2M device activity probability forecasting is evaluated using Bayesian estimation, LSTM, moving average, and exponential smoothing. LSTM achieves the lowest forecasting error, while exponential smoothing provides a close and computationally simpler alternative. The results indicate that the proposed framework can support proactive and priority-aware resource management for heterogeneous M2M traffic, while the learning-based components are used as approximation and forecasting tools rather than as universally superior solutions.