Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sequential In-Network Processing for Cell-Free Massive MIMO with Capacity-Constrained Parallel Radio Stripes

Sangwon Jo, Hoon Lee, Seok-Hwan Park

TL;DR

This work designs the uplink signal processing for a CF-mMIMO system with parallel radio stripes and proposes an efficient sequential INP design, which achieves a sum-rate gain of up to 82.92% compared to baseline schemes.

Abstract

To ensure coherent signal processing across distributed Access Points (APs) in Cell-Free Massive Multiple-Input Multiple-Output (CF-mMIMO) systems, a fronthaul connection between the APs and a Central Processor (CP) is imperative. We consider a fronthaul network employing parallel radio stripes. In this system, APs are grouped into multiple segments where APs within each segment are sequentially connected through a radio stripe. This fronthaul topology strikes a balance between standard star and bus topologies, which deploy parallel or serial connections of all APs. Our focus lies in designing the uplink signal processing for a CF-mMIMO system with parallel radio stripes. We tackle the challenge of finite-capacity fronthaul links by addressing the design of In-Network Processing (INP) strategies at APs. These strategies involve linearly combining received signals and compressing the combining output for fronthaul transmission, aiming to maximize the sum-rate performance. Given the high complexity and the stringent requirement for global Channel State Information (CSI) in jointly optimizing INP strategies across all APs, we propose an efficient sequential design approach. Numerical results demonstrate that the proposed sequential INP design achieves a sum-rate gain of up to 82.92% compared to baseline schemes.

Sequential In-Network Processing for Cell-Free Massive MIMO with Capacity-Constrained Parallel Radio Stripes

TL;DR

This work designs the uplink signal processing for a CF-mMIMO system with parallel radio stripes and proposes an efficient sequential INP design, which achieves a sum-rate gain of up to 82.92% compared to baseline schemes.

Abstract

To ensure coherent signal processing across distributed Access Points (APs) in Cell-Free Massive Multiple-Input Multiple-Output (CF-mMIMO) systems, a fronthaul connection between the APs and a Central Processor (CP) is imperative. We consider a fronthaul network employing parallel radio stripes. In this system, APs are grouped into multiple segments where APs within each segment are sequentially connected through a radio stripe. This fronthaul topology strikes a balance between standard star and bus topologies, which deploy parallel or serial connections of all APs. Our focus lies in designing the uplink signal processing for a CF-mMIMO system with parallel radio stripes. We tackle the challenge of finite-capacity fronthaul links by addressing the design of In-Network Processing (INP) strategies at APs. These strategies involve linearly combining received signals and compressing the combining output for fronthaul transmission, aiming to maximize the sum-rate performance. Given the high complexity and the stringent requirement for global Channel State Information (CSI) in jointly optimizing INP strategies across all APs, we propose an efficient sequential design approach. Numerical results demonstrate that the proposed sequential INP design achieves a sum-rate gain of up to 82.92% compared to baseline schemes.

Paper Structure

This paper contains 23 sections, 1 theorem, 45 equations, 7 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background and Motivation
  3. Related Work
  4. Main Contribution
  5. Organization
  6. System Models
  7. Fronthaul network model
  8. Channel Training and Estimation Error Model
  9. Payload Data Transmission on Access Channel
  10. Sequential In-Network Signal Processing
  11. Proposed Sequential INP Strategy
  12. Problem Formulation
  13. Proposed Sequential INP Optimization
  14. Design of Linear combining matrices $\{\mathbf{U}, \mathbf{V}\}$
  15. Design of Quantization Noise Covariance Matrix $\boldsymbol{\Omega}$
  16. ...and 8 more sections

Key Result

Theorem 1

The solution $\mathbf{a}_{m,i}$ to the problem (eq:problem-successive-Omega-modified) is given as for $k\in\mathcal{K}$, with $[\cdot]^{+} = \max\{\cdot,0\}$. Here, the optimal Lagrange multiplier $\lambda_{m,i}$ is chosen to satisfy Such $\lambda_{m,i}$ can be found via the bisection method Boyd:Cambridge, since the left-hand side of (eq:condition-optimal-Lagrange-multiplier) monotonically decr

Figures (7)

  • Figure 1: Illustration of the uplink of a CF-mMIMO system with a fronthaul network of $M=4$ radio stripes.
  • Figure 2: Illustration of the INP operations at the APs.
  • Figure 3: Illustration of procedures for AP $(m,i)$ to optimizing its INP strategy and share the SI with AP $(m,i-1)$ and AP $(m,i+1)$.
  • Figure 4: Average sum-rate versus the fronthaul capacity $C_F$ with $M \in \{1, 4\}$, $L=32/M$, $N=24$, and $K=20$.
  • Figure 5: Average sum-rate versus the number of stripes $M$ with $L=24/M$, $N=24$, $C_F=10$, and $K=20$.
  • ...and 2 more figures

Theorems & Definitions (2)

  • Theorem 1
  • proof