Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Edge Intelligence in Satellite-Terrestrial Networks with Hybrid Quantum Computing

Siyue Huang, Lifeng Wang, Xin Wang, Bo Tan, Wei Ni, Kai-Kit Wong

TL;DR

An alternating direction method of multipliers (ADMM)-inspired algorithm is proposed to decompose the joint optimization problem into small-scale subproblems, and a hybrid quantum double deep Q-learning (DDQN) approach is developed to optimize the edge cloud selection.

Abstract

This paper exploits the potential of edge intelligence empowered satellite-terrestrial networks, where users' computation tasks are offloaded to the satellites or terrestrial base stations. The computation task offloading in such networks involves the edge cloud selection and bandwidth allocations for the access and backhaul links, which aims to minimize the energy consumption under the delay and satellites' energy constraints. To address it, an alternating direction method of multipliers (ADMM)-inspired algorithm is proposed to decompose the joint optimization problem into small-scale subproblems. Moreover, we develop a hybrid quantum double deep Q-learning (DDQN) approach to optimize the edge cloud selection. This novel deep reinforcement learning architecture enables that classical and quantum neural networks process information in parallel. Simulation results confirm the efficiency of the proposed algorithm, and indicate that duality gap is tiny and a larger reward can be generated from a few data points compared to the classical DDQN.

Edge Intelligence in Satellite-Terrestrial Networks with Hybrid Quantum Computing

TL;DR

An alternating direction method of multipliers (ADMM)-inspired algorithm is proposed to decompose the joint optimization problem into small-scale subproblems, and a hybrid quantum double deep Q-learning (DDQN) approach is developed to optimize the edge cloud selection.

Abstract

This paper exploits the potential of edge intelligence empowered satellite-terrestrial networks, where users' computation tasks are offloaded to the satellites or terrestrial base stations. The computation task offloading in such networks involves the edge cloud selection and bandwidth allocations for the access and backhaul links, which aims to minimize the energy consumption under the delay and satellites' energy constraints. To address it, an alternating direction method of multipliers (ADMM)-inspired algorithm is proposed to decompose the joint optimization problem into small-scale subproblems. Moreover, we develop a hybrid quantum double deep Q-learning (DDQN) approach to optimize the edge cloud selection. This novel deep reinforcement learning architecture enables that classical and quantum neural networks process information in parallel. Simulation results confirm the efficiency of the proposed algorithm, and indicate that duality gap is tiny and a larger reward can be generated from a few data points compared to the classical DDQN.
Paper Structure (7 sections, 13 equations, 5 figures, 1 table)

This paper contains 7 sections, 13 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Descriptions
  3. Splitting Algorithm Design
  4. Simulation Results
  5. Convergence
  6. Efficiency
  7. Conclusions

Figures (5)

  • Figure 1: Hybrid quantum DDQN architecture with classical and quantum deep Q-networks, where $R_x\left(\theta\right)$ and $R_x\left(\phi\right)$ with the rotations along x-axis and z-axis by the angles $\theta$ and $\phi$ are the single-qubit gates, and $R\left(\alpha,\beta,\gamma\phi\right)$ is the general single qubit unitary gate in the quantum model Yen-Chi2020.
  • Figure 2: The convergence of the proposed hybrid quantum DDQN in comparison with the classical counterpart.
  • Figure 3: Duality gap with $B_{\rm access}^{total}=50$MHz,$B_{\rm S}^{total}=100$MHz and $I=5\times10^5$bits.
  • Figure 4: Effect of the offloaded task size.
  • Figure 5: The total energy consumption under different system bandwidths for the access and backhaul links with $I=5\times10^5$bits.