Intelligent RF Planning and Performance Optimization for Carrier Aggregation and Dual Connectivity in 5G-Advanced Networks

Abstract

Next-generation wireless networks leverage Carrier Aggregation (CA) and Dual Connectivity (DC) to deliver enhanced throughput and spectral efficiency by simultaneously utilizing multiple frequency bands. However, coordinating FR1 sub-6 GHz coverage with FR2 mmWave capacity presents significant challenges in resource allocation, inter-band handover management, and QoS maintenance under dynamic traffic conditions. This article proposes an intelligent framework combining predictive algorithms for inter-band handover with reinforcement learning-based load balancing optimization. The framework integrates deterministic propagation models with AI-driven traffic forecasting to enable proactive resource allocation across aggregated carriers. Performance evaluation demonstrates substantial improvements in handover success rates, throughput consistency, and resource utilization compared to conventional rule-based methods. Results from urban and suburban deployment scenarios validate the effectiveness of machine learning models in predicting mobility patterns and optimizing carrier selection. The proposed solution addresses critical gaps in multi-band network planning while ensuring latency requirements and service continuity during CA/DC transitions, providing practical insights for 5G-Advanced and early 6G network deployments.