A Survey of Methods and Architectures for Joint Power and Delay Optimization Based Resource Allocation in MIMO-OFDM System using Deep Convolutional Red Piranha Pyramid-Dilated Neural Network: A Review

Abstract

The rapid evolution of wireless communication systems, particularly in 5G and beyond (6G), demands efficient resource allocation strategies for Multi-Input Multi-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) systems. Joint optimization of power and delay has emerged as a critical challenge due to dynamic network conditions, heterogeneous traffic requirements, and stringent Quality of Service (QoS) constraints. Traditional optimization approaches, including convex optimization and heuristic-based algorithms, often fail to address the complexity and scalability issues inherent in modern wireless systems. ecent advancements in deep learning have introduced intelligent and adaptive resource allocation techniques. In particular, deep convolutional neural networks, reinforcement learning models, and hybrid architectures have demonstrated significant improvements in spectrum efficiency, latency reduction, and energy consumption. This paper presents a comprehensive survey of existing methods and architectures for joint power and delay optimization in MIMO-OFDM systems, with a special focus on emerging deep learning models such as pyramid-dilated networks and attention-based frameworks. Furthermore, this review highlights the potential of a novel Deep Convolutional Red Piranha Pyramid-Dilated Neural Network for enhancing resource allocation efficiency. The study critically analyses recent contributions, identifies research gaps, and discusses future directions toward intelligent, secure, and scalable wireless communication systems.