Artificial Intelligence Techniques for Joint Power and Delay Optimization Based Resource Allocation in MIMO-OFDM System Using Deep Convolutional Red Piranha Pyramid-Dilated Neural Network: Trends and Challenges

Abstract

The rapid development of 6G wireless communication systems demands
intelligent resource allocation strategies capable of optimizing both
power consumption and transmission delay in MU-MIMO-OFDM
environments. Traditional optimization techniques struggle with high
dimensional decision spaces, dynamic channel conditions, and stringent
Quality of Service (QoS) requirements. Recently, artificial intelligence
(AI)-driven approaches, particularly deep learning and hybrid
optimization models, have shown significant potential in addressing
these challenges. This paper presents a comprehensive survey of AI
based techniques for joint power and delay optimization in MIMO-OFDM
systems, focusing on advanced architectures such as Deep Convolutional
Pyramid-Dilated Neural Networks (DCPDNN) integrated with
metaheuristic algorithms like Red Piranha Optimization. The proposed
frameworks enable efficient resource allocation by jointly optimizing
transmission power, subcarrier assignment, and delay scheduling.
Recent studies demonstrate improvements in throughput, energy
efficiency, and latency reduction through multi-stage optimization
strategies. Furthermore, reinforcement learning, graph neural
networks, and transformer-based scheduling methods are explored as
emerging solutions for adaptive resource management. A systematic
review of recent literature (2020–2023) highlights trends, performance
trade-offs, and research gaps. The survey concludes with future
directions emphasizing scalable, energy-efficient, and secure AI-driven
wireless communication systems for next-generation networks.