Artificial Intelligence Driven Channel Coding and Resource Optimization for Wireless Networks

TL;DR

The paper surveys how Artificial Intelligence can enhance 5G/5G+ wireless networks, with a focus on AI-driven channel coding, decoding, detection, precoding, and baseband components. It provides a coding-centric taxonomy, reviews DL/RL methods for LDPC/polar codes, neural BP, and end-to-end learning, and discusses AI-enabled resource optimization and security considerations. Key contributions include organized classifications, comparative insights, and a practical roadmap outlining open challenges such as data privacy, fairness, real-time operation, and deployment considerations. The work informs researchers and practitioners on integrating AI into scalable, reliable wireless systems, guiding toward robust implementations in 6G and beyond.

Abstract

The ongoing evolution of 5G and its enhanced version, 5G+, has significantly transformed the telecommunications landscape, driving an unprecedented demand for ultra-high-speed data transmission, ultra-low latency, and resilient connectivity. These capabilities are essential for enabling mission-critical applications such as the Internet of Things, autonomous vehicles, and smart city infrastructures. This paper investigates the important role of Artificial Intelligence (AI) in addressing the key challenges faced by 5G/5G+ networks, including interference mitigation, dynamic resource allocation, and maintaining seamless network operation. The study particularly focuses on AI-driven innovations in coding theory, which offer advanced solutions to the limitations of conventional error correction and modulation techniques. By employing deep learning, reinforcement learning, and neural network-based approaches, this research demonstrates significant advancements in error correction performance, decoding efficiency, and adaptive transmission strategies. Additionally, the integration of AI with emerging technologies, such as massive multiple-input and multiple-output, intelligent reflecting surfaces, and privacy-enhancing mechanisms, is discussed, highlighting their potential to propel the next generation of wireless networks. This paper also provides insights into the transformative impact of AI on modern wireless communication, establishing a foundation for scalable, adaptive, and more efficient network architectures.

Figures (14)

• Figure 1: Illustrates the organization and logical flow of this survey, highlighting the central role of AI-driven channel coding and its interaction with detection, precoding, and other baseband components.
• Figure 2: From 3GPP to 5G/5G+ and 6G.
• Figure 3: Key goals of 5G+ in releases 18 and 19 in terms of efficiency, automation, AI integration, IoT, and security.
• Figure 4: DNN-based MPD architecture: input layer receives signals, hidden layers replicate MPD iterations, and output layer detects symbols using deep learning.
• Figure 5: (a) Standard RL framework where the agent interacts with the environment by taking actions and receiving states and rewards. (b) Q-Learning framework where a Q-table is used to store and update the optimal action-value pairs based on interactions with the environment.