Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Driven Multi-Modal Adaptive Handover Control Optimization for O-RAN

Abdul Wadud, Fatemeh Golpayegani, Nima Afraz

Abstract

Handover optimization in O-RAN faces growing challenges due to heterogeneous user mobility patterns and rapidly varying radio conditions. Existing ML-based handover schemes typically operate at the near-RT layer, which lack awareness of the mobility-mode and struggle to incorporate a longer-term predictive context. This paper proposes a multi-modal mobility-aware optimization framework in which all predictive intelligence, including mobility mode classification, short-horizon trajectory and RSRP forecasting, and a PPO Actor--Critic policy, runs entirely inside an rApp in the non-RT RIC. The rApp generates per-UE ranked neighbour-cell recommendations and delivers them to the existing handover xApp through the A1 interface. The xApp combines these rankings with instantaneous E2 measurements and performs the final standards-compliant handover decision. This hierarchical design preserves low-latency execution in the xApp while enabling the rApp to supply richer and mode-specific predictive guidance. Evaluation using mobility traces demonstrates that the proposed approach reduces ping-pong handover events and improves handover reliability compared to conventional 3GPP A3-based and ML-based baselines.

AI-Driven Multi-Modal Adaptive Handover Control Optimization for O-RAN

Abstract

Handover optimization in O-RAN faces growing challenges due to heterogeneous user mobility patterns and rapidly varying radio conditions. Existing ML-based handover schemes typically operate at the near-RT layer, which lack awareness of the mobility-mode and struggle to incorporate a longer-term predictive context. This paper proposes a multi-modal mobility-aware optimization framework in which all predictive intelligence, including mobility mode classification, short-horizon trajectory and RSRP forecasting, and a PPO Actor--Critic policy, runs entirely inside an rApp in the non-RT RIC. The rApp generates per-UE ranked neighbour-cell recommendations and delivers them to the existing handover xApp through the A1 interface. The xApp combines these rankings with instantaneous E2 measurements and performs the final standards-compliant handover decision. This hierarchical design preserves low-latency execution in the xApp while enabling the rApp to supply richer and mode-specific predictive guidance. Evaluation using mobility traces demonstrates that the proposed approach reduces ping-pong handover events and improves handover reliability compared to conventional 3GPP A3-based and ML-based baselines.
Paper Structure (22 sections, 6 equations, 6 figures)

This paper contains 22 sections, 6 equations, 6 figures.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. O-RAN 7.2x Setting and Entities
  4. Predictors and near-RT State
  5. Action, Constraints, and A3 View
  6. Objective as a Control Utility
  7. Proposed Multi-Modal Optimization Method
  8. Mobility Mode Classification (MC)
  9. Short-Horizon Prediction
  10. Actor--Critic Handover Policy based Cell Ranker (CR)
  11. Hierarchical rApp–xApp Collaboration for Mobility-Aware Handover Optimization
  12. Handover Decision-Making Workflow
  13. Purpose of the Hierarchical Split
  14. Simulation Results and Performance Analysis
  15. Simulation Setup
  16. ...and 7 more sections

Figures (6)

  • Figure 1: System Model.
  • Figure 2: Proposed Multi-Modal Adaptive Handover Control Framework in O-RAN.
  • Figure 3: Hierarchical rApp–xApp workflow.
  • Figure 4: Confusion matrix for 7-mode classifier (overall accuracy: 99.84%)
  • Figure 5: Short-horizon trajectory prediction: mode-wise actual vs predicted coordinates.
  • ...and 1 more figures