Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Collaborative Spectrum Sensing in Cognitive and Intelligent Wireless Networks: An Artificial Intelligence Perspective

Peng Yi, Ying-Chang Liang

TL;DR

The paper addresses the challenge of reliable spectrum sensing in dynamic, heterogeneous wireless environments by surveying AI-enabled CSS approaches. It categorizes methods into discriminative DL, generative DL, and DRL, and introduces SemCom as a task-oriented paradigm to reduce reporting overhead while preserving detection performance. Key contributions include a taxonomy of AI models for CSS, discussion of SemCom-enabled CSS architectures, and a candid assessment of limitations and open research directions. The work highlights the potential of AI and semantic-aware communication to enable scalable, robust spectrum intelligence for future networks such as 6G.

Abstract

Artificial intelligence (AI) has become a key enabler for next-generation wireless communication systems, offering powerful tools to cope with the increasing complexity, dynamics, and heterogeneity of modern wireless environments. To illustrate the role and impact of AI in wireless communications, this paper takes collaborative spectrum sensing (CSS) in cognitive and intelligent wireless networks as a representative application and surveys recent advances from an AI perspective. We first introduce the fundamentals of CSS, including the general framework, classical detector design, and fusion strategies. Then, we present an overview of the state-of-the-art research on AI-driven CSS, classified into three categories: discriminative deep learning (DL) models, generative DL models, and deep reinforcement learning (DRL). Furthermore, we explore semantic communication (SemCom) as a promising solution for CSS, in which task-oriented representations are exchanged to reduce reporting overhead while preserving decision-critical information. Finally, we discuss limitations, open challenges, and future research directions at the intersection of AI and wireless communication.

Collaborative Spectrum Sensing in Cognitive and Intelligent Wireless Networks: An Artificial Intelligence Perspective

TL;DR

The paper addresses the challenge of reliable spectrum sensing in dynamic, heterogeneous wireless environments by surveying AI-enabled CSS approaches. It categorizes methods into discriminative DL, generative DL, and DRL, and introduces SemCom as a task-oriented paradigm to reduce reporting overhead while preserving detection performance. Key contributions include a taxonomy of AI models for CSS, discussion of SemCom-enabled CSS architectures, and a candid assessment of limitations and open research directions. The work highlights the potential of AI and semantic-aware communication to enable scalable, robust spectrum intelligence for future networks such as 6G.

Abstract

Artificial intelligence (AI) has become a key enabler for next-generation wireless communication systems, offering powerful tools to cope with the increasing complexity, dynamics, and heterogeneity of modern wireless environments. To illustrate the role and impact of AI in wireless communications, this paper takes collaborative spectrum sensing (CSS) in cognitive and intelligent wireless networks as a representative application and surveys recent advances from an AI perspective. We first introduce the fundamentals of CSS, including the general framework, classical detector design, and fusion strategies. Then, we present an overview of the state-of-the-art research on AI-driven CSS, classified into three categories: discriminative deep learning (DL) models, generative DL models, and deep reinforcement learning (DRL). Furthermore, we explore semantic communication (SemCom) as a promising solution for CSS, in which task-oriented representations are exchanged to reduce reporting overhead while preserving decision-critical information. Finally, we discuss limitations, open challenges, and future research directions at the intersection of AI and wireless communication.
Paper Structure (35 sections, 6 equations, 5 figures, 1 table)

This paper contains 35 sections, 6 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Fundamentals of Cooperative Spectrum Sensing
  3. General Framework
  4. Traditional Detectors
  5. Optimal Methods
  6. Semi-Blind Methods
  7. Totally-Blind Methods
  8. Fusion Strategies
  9. Hard-Decision Fusion
  10. Soft-Data Fusion
  11. AI-Driven Cooperative Spectrum Sensing
  12. Discriminative Deep Learning-Based CSS
  13. Convolutional Neural Networks
  14. Recurrent Neural Networks
  15. Graph Neural Networks
  16. ...and 20 more sections

Figures (5)

  • Figure 1: Illustration of the CSS scenario.
  • Figure 2: Timing structure of the CSS process. Each sensing period consists of a sensing slot followed by a reporting slot.
  • Figure 3: Comparison of architectures between conventional communication and SemCom.
  • Figure 4: System model of SU-SemCom for remote spectrum sensing. The sensor encodes local observations into semantic representations via a semantic encoder and transmits them to the FC, where a semantic decoder infers the PU status.
  • Figure 5: System models of MU-SemCom. (a) Traditional OMA-based reporting, utilizing orthogonal resources (e.g., time or frequency), which results in communication overhead (latency or bandwidth) scaling linearly with the number of sensors. (b) AirComp-based reporting, where semantic representations are concurrently aggregated over the air on the same resource blocks, achieving high spectral efficiency and scalable fusion independent of the network size.