Adaptive Multi-Objective QoS Optimization in Dynamic Wireless Networks Using Machine Learning-Assisted Evolutionary Intelligence
Adaptive Multi-Objective QoS Optimization in Dynamic Wireless Networks Using Machine Learning-Assisted Evolutionary Intelligence
Authors:
Dr. Prasadu Peddi1, Dr. VENU MUNDRAI2, Dr. Gade Venkata Vara Prasad3
Research Guide, Shri Jagdishprasad Jhabarmal Tibrewala University, Jhunjhunūn.
Associate Professor, Head of Department of AIML, Narsimha Reddy Engineering College, Hyderabad.
Asistant Professor, Dep of AIML, Narsimha Reddy Engineering College, Hyderabad,
Abstract: The rapid expansion of heterogeneous wireless infrastructures, including Internet of Things (IoT) networks, mobile ad hoc networks (MANETs), software-defined systems, and emerging 5G/6G communication environments, has substantially increased the complexity of Quality of Service (QoS) management under dynamic operating conditions. Traditional optimization techniques often suffer from slow convergence, high computational complexity, and limited adaptability to fluctuating traffic patterns, node mobility, and network uncertainties. This study proposes a hybrid machine learning-assisted genetic optimization framework for adaptive QoS enhancement in dynamic wireless networks. The framework combines predictive surrogate modelling with evolutionary optimization to accelerate convergence and reduce the computational overhead associated with repeated fitness evaluations. It integrates real-time telemetry acquisition, traffic analytics, feature engineering, adaptive parameter tuning, and closed-loop feedback mechanisms to enable continuous and intelligent optimization.
Performance evaluation using CAIDA Internet backbone traces, CRAWDAD mobility datasets, and NS-3 simulated scenarios demonstrates significant improvements in throughput, latency, packet delivery ratio, jitter, energy efficiency, and convergence speed compared with conventional approaches. The proposed framework offers a scalable and computationally efficient paradigm for next-generation intelligent communication systems and provides a robust foundation for autonomous and adaptive wireless network optimization.
Keywords: Network Optimization, Genetic Algorithms, Quality of Service, Wireless Networks, Evolutionary Optimization, Intelligent Communication Systems, Surrogate Modelling, 5G/6G Networks