Dynamic resource allocation in 5G networks using hybrid RL-CNN model for optimized latency and quality of service.

The rapid deployment of 5G networks necessitates innovative solutions for efficient and dynamic resource allocation. Current strategies, although effective to some extent, lack real-time adaptability and scalability in complex, dynamically-changing environments. This paper introduces the Dynamic Resource Allocator using RL-CNN (DRARLCNN), a novel machine learning model addressing these shortcomings. By merging Convolutional Neural Networks (CNN) for feature extraction and Reinforcement Learning (RL) for decision-making, DRARLCNN optimizes resource allocation, minimizing latency and maximizing Quality of Service (QoS). Utilizing a state-of-the-art "5G Resource Allocation Dataset", the research employs Python, TensorFlow, and OpenAI Gym to implement and test the model in a simulated 5 G environment. Results demonstrate the effectiveness of DRARLCNN, showcasing an impressive R2 score of 0.517, MSE of 0.035, and RMSE of 0.188, surpassing existing methods in allocation efficiency and latency. The DRARLCNN model not only outperforms existing methods in allocation efficiency and latency but also sets a new benchmark for future research in dynamic 5G resource allocation. Through its innovative approach and promising results, DRARLCNN opens avenues for further advancements in optimizing resource allocation within dynamic 5G networks.

Stable route selection for adaptive packet transmission in 5G-based mobile communications.

The poor connectivity among mobile nodes introduces uncertainty in packet loss as the path link is not measured in this network. The focus is placed on communication cost to achieve valid packet transmission. Because the high-distance path selected for packet transmission incurs higher communication costs, it increases energy consumption and packet loss rate. So, the proposed dispersed path selection for communication (DPAC) method is constructed to obtain the best minimum distance routing path. This path operates with the help of queue variation is handled the data packets maintenance, and the time slot exceeds its limit. Packets are kept waiting to increase the packet broadcasting efficiency. A multipath jamming detection algorithm is constructed to provide a link-based path packet overload detection scheme to identify the packet overload. It also separates the path based on its characteristics to control overload. It reduces energy consumption and packet loss rate.