Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Learning-Based Intermittent CSI Estimation with Adaptive Intervals in Integrated Sensing and Communication Systems

Jie Chen, Xianbin Wang

TL;DR

A deep reinforcement online learning (DROL) framework that first implements an online deep neural network (DNN) to learn the binary CSI updating policy from the experiences is proposed and an efficient algorithm to solve the remaining beamforming design problem is proposed.

Abstract

Due to the distinct objectives and multipath utilization mechanisms between the communication module and radar module, the system design of integrated sensing and communication (ISAC) necessitates two types of channel state information (CSI), i.e., communication CSI representing the whole channel gain and phase shifts, and radar CSI exclusively focused on target mobility and position information. However, current ISAC systems apply an identical mechanism to estimate both types of CSI at the same predetermined estimation interval, leading to significant overhead and compromised performances. Therefore, this paper proposes an intermittent communication and radar CSI estimation scheme with adaptive intervals for individual users/targets, where both types of CSI can be predicted using channel temporal correlations for cost reduction or re-estimated via training signal transmission for improved estimation accuracy. Specifically, we jointly optimize the binary CSI re-estimation/prediction decisions and transmit beamforming matrices for individual users/targets to maximize communication transmission rates and minimize radar tracking errors and costs in a multiple-input single-output (MISO) ISAC system. Unfortunately, this problem has causality issues because it requires comparing system performances under re-estimated CSI and predicted CSI during the optimization. Additionally, the binary decision makes the joint design a mixed integer nonlinear programming (MINLP) problem, resulting in high complexity when using conventional optimization algorithms. Therefore, we propose a deep reinforcement online learning (DROL) framework that first implements an online deep neural network (DNN) to learn the binary CSI updating decisions from the experiences. Given the learned decisions, we propose an efficient algorithm to solve the remaining beamforming design problem efficiently.

Learning-Based Intermittent CSI Estimation with Adaptive Intervals in Integrated Sensing and Communication Systems

TL;DR

A deep reinforcement online learning (DROL) framework that first implements an online deep neural network (DNN) to learn the binary CSI updating policy from the experiences is proposed and an efficient algorithm to solve the remaining beamforming design problem is proposed.

Abstract

Due to the distinct objectives and multipath utilization mechanisms between the communication module and radar module, the system design of integrated sensing and communication (ISAC) necessitates two types of channel state information (CSI), i.e., communication CSI representing the whole channel gain and phase shifts, and radar CSI exclusively focused on target mobility and position information. However, current ISAC systems apply an identical mechanism to estimate both types of CSI at the same predetermined estimation interval, leading to significant overhead and compromised performances. Therefore, this paper proposes an intermittent communication and radar CSI estimation scheme with adaptive intervals for individual users/targets, where both types of CSI can be predicted using channel temporal correlations for cost reduction or re-estimated via training signal transmission for improved estimation accuracy. Specifically, we jointly optimize the binary CSI re-estimation/prediction decisions and transmit beamforming matrices for individual users/targets to maximize communication transmission rates and minimize radar tracking errors and costs in a multiple-input single-output (MISO) ISAC system. Unfortunately, this problem has causality issues because it requires comparing system performances under re-estimated CSI and predicted CSI during the optimization. Additionally, the binary decision makes the joint design a mixed integer nonlinear programming (MINLP) problem, resulting in high complexity when using conventional optimization algorithms. Therefore, we propose a deep reinforcement online learning (DROL) framework that first implements an online deep neural network (DNN) to learn the binary CSI updating decisions from the experiences. Given the learned decisions, we propose an efficient algorithm to solve the remaining beamforming design problem efficiently.
Paper Structure (31 sections, 1 theorem, 51 equations, 17 figures, 1 table, 2 algorithms)

This paper contains 31 sections, 1 theorem, 51 equations, 17 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model
  3. Communication CSI Model
  4. Radar CSI Model
  5. ISAC Signal Model
  6. Communication and Radar Performance Derivations
  7. Communication Performance Derivation
  8. Communication CSI Updating in Stage-I
  9. Communication Rate in Stage-II
  10. Radar Performance Derivation
  11. Radar CSI Updating in Stage-II
  12. Weighted Radar Tracking Error and Cost in Stage-II
  13. Problem Formulation and Algorithm Development
  14. Problem Formulation
  15. Deep Reinforcement Online Learning (DROL) Framework
  16. ...and 16 more sections

Key Result

Theorem 3.1

From eqtcorrR and eq13, the predicted and posterior estimations of radar CSI ${\bf{\hat{x}}}_q^n$ using EKF method are given by where ${\bf{\bar{x}}}_q^n$ is the direct estimation of ${\bf x}_q^n$ defined in eqstate. Besides, we have $\gamma _{qn}^{\rm{r}} = {\sum\nolimits_{k = 1}^K {{{\left| {{\bf{v}}_{\rm{T}}^H\left( {\theta _q^n} \right){\bf{w}}_k^n} \right|}^2}} }$, ${\bm \Gamma} _q^{n - 1} =

Figures (17)

  • Figure 1: The MISO-based ISAC system including one full-duplex BS, $K$ communication users, and $Q$ point targets.
  • Figure 2: An illustration of intermittent CSI estimation frame structure: each frame is divided into Stage-0 (negligible length) and Stage-I/Stage-II (flexible length). The communication CSI is intermittently estimated in Stage-I by transmitting uplink pilot sequences from users, while the radar CSI is intermittently estimated in Stage-II through the echoes of downlink beamformed ISAC signals reflected from targets.
  • Figure 3: Radar target state evolution model.
  • Figure 4: DROL-based dynamic intermittent CSI estimation framework together with transmit beamforming optimization.
  • Figure 8: Average number of potential CSI decisions explored and the selected index of the optimal CSI decision in each frame over a moving average of 50 frames.
  • ...and 12 more figures

Theorems & Definitions (1)

  • Theorem 3.1