Heuristic handover control outperforms deep learning in O-RAN mobility
When Simple Is Enough: Resource-Aware Heuristic versus DDQN for O-RAN Mobility Robustness
Networking and Internet Architecture
Summary
Managing how mobile devices switch between cell towers is tricky, especially in busy or fast-moving situations. The authors compared a simple, resource-aware rule-based method to a complex deep reinforcement learning algorithm for deciding when to hand over connections in a modern open cellular network. They found the simpler method gave better service and used fewer computing resources, while the deep learning method needed training and caused more frequent reconnects. This suggests that straightforward approaches might work better and be easier to run in real networks under many conditions.
What this means in practice
- •For mobile network operators: Implement resource-aware heuristics to improve user connectivity reliability and reduce outages in 5G O-RAN mobility management.
- •For cellular network engineers: Design efficient handover controllers that balance network resources and user movement without complex offline training.
Authors
Ali Deylamy, Nima Afraz
Abstract
Open Radio Access Network (O-RAN) enables mobility-management xApps, but a learned controller is not necessarily the most effective or efficient handover policy. This paper compares standard Event A3, a resource- and mobility-aware heuristic, and a Double Deep Q-Network (DDQN) through a common xApp-oriented interface and paired system-level simulation. The heuristic combines radio quality, target-cell resources, UE mobility, and service class, with weights optimized offline using NSGA-II, while DDQN-Multi uses temporal radio and resource observations. All controllers are evaluated on identical UE trajectories, traffic assignments, and ray-traced radio inputs under Base, High-Mobility, and High-UE scenarios. Performance is assessed using service, handover, resource, energy, and fairness KPIs, complemented by CRITIC--TOPSIS ranking and complexity analysis. Results show that the heuristic achieves the lowest outage in all three scenarios and ranks first in the CRITIC--TOPSIS comparison, while retaining linear online complexity and interpretable decisions. DDQN-Multi improves target feasibility under congestion but requires offline training and produces more handovers and ping-pong events. The results indicate that lightweight resource-aware control can provide a favourable performance-complexity trade-off relative to DDQN under the considered scenarios.