Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CVaR-Based Variational Quantum Optimization for User Association in Handoff-Aware Vehicular Networks

Zijiang Yan, Hao Zhou, Jianhua Pei, Aryan Kaushik, Hina Tabassum, Ping Wang

TL;DR

This work addresses assignment of vehicular network users to base stations (GAP) under handoff dynamics by formulating the problem as a QUBO and solving it with a CVaR-augmented variational quantum eigensolver. The authors implement a hybrid quantum-classical framework where a parameterized quantum circuit encodes binary association variables and a CVaR objective concentrates optimization on the lowest-energy tail to improve convergence on NISQ devices. They demonstrate a 23.5% improvement in average data rate over a deep neural network benchmark and analyze robustness across qubit counts, base-station counts, and circuit depths. The results suggest CVaR-VQE provides a practical, noise-tolerant path to near-optimal user association in dynamic vehicular networks, with clear directions for extending to more complex scenarios.

Abstract

Efficient resource allocation is essential for optimizing various tasks in wireless networks, which are usually formulated as generalized assignment problems (GAP). GAP, as a generalized version of the linear sum assignment problem, involves both equality and inequality constraints that add computational challenges. In this work, we present a novel Conditional Value at Risk (CVaR)-based Variational Quantum Eigensolver (VQE) framework to address GAP in vehicular networks (VNets). Our approach leverages a hybrid quantum-classical structure, integrating a tailored cost function that balances both objective and constraint-specific penalties to improve solution quality and stability. Using the CVaR-VQE model, we handle the GAP efficiently by focusing optimization on the lower tail of the solution space, enhancing both convergence and resilience on noisy intermediate-scale quantum (NISQ) devices. We apply this framework to a user-association problem in VNets, where our method achieves 23.5% improvement compared to the deep neural network (DNN) approach.

CVaR-Based Variational Quantum Optimization for User Association in Handoff-Aware Vehicular Networks

TL;DR

This work addresses assignment of vehicular network users to base stations (GAP) under handoff dynamics by formulating the problem as a QUBO and solving it with a CVaR-augmented variational quantum eigensolver. The authors implement a hybrid quantum-classical framework where a parameterized quantum circuit encodes binary association variables and a CVaR objective concentrates optimization on the lowest-energy tail to improve convergence on NISQ devices. They demonstrate a 23.5% improvement in average data rate over a deep neural network benchmark and analyze robustness across qubit counts, base-station counts, and circuit depths. The results suggest CVaR-VQE provides a practical, noise-tolerant path to near-optimal user association in dynamic vehicular networks, with clear directions for extending to more complex scenarios.

Abstract

Efficient resource allocation is essential for optimizing various tasks in wireless networks, which are usually formulated as generalized assignment problems (GAP). GAP, as a generalized version of the linear sum assignment problem, involves both equality and inequality constraints that add computational challenges. In this work, we present a novel Conditional Value at Risk (CVaR)-based Variational Quantum Eigensolver (VQE) framework to address GAP in vehicular networks (VNets). Our approach leverages a hybrid quantum-classical structure, integrating a tailored cost function that balances both objective and constraint-specific penalties to improve solution quality and stability. Using the CVaR-VQE model, we handle the GAP efficiently by focusing optimization on the lower tail of the solution space, enhancing both convergence and resilience on noisy intermediate-scale quantum (NISQ) devices. We apply this framework to a user-association problem in VNets, where our method achieves 23.5% improvement compared to the deep neural network (DNN) approach.
Paper Structure (16 sections, 18 equations, 4 figures)

This paper contains 16 sections, 18 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Vehicular Network System Model
  3. Quadratic Unconstraint Binary Optimization
  4. Proposed CVaR based VQE Approach
  5. Parametrized Quantum Operations and Variational Quantum Algorithms
  6. Variational Quantum Eigensolver Algorithm
  7. Conditional Value at Risk-Variatiational Quantum Eigensolver (CVaR-VQE)
  8. Case Study: BS-User Association in VNet
  9. VNet Parameter Settings
  10. DNN Benchmark
  11. Proposed CVaR-VQE Framework
  12. Convergence Analysis
  13. Evaluation based on different number of qubits
  14. Evaluation based on different number of BSs
  15. Evaluation based on VQE circuit depth $p$
  16. ...and 1 more sections

Figures (4)

  • Figure 1: CVaR-VQE Framework with proposed VNet Model
  • Figure 2: Overview of the quantum neural network (QNN)
  • Figure 3: Overview of the Variation Quantum Circuit (Ansatz)
  • Figure 4: Simulation results and comparisons